WIP

4682: Speed Up Filter ANDs operations r=Kerollmops a=Kerollmops

This PR fixes #4659 and improves the way we do AND operations by using the latest [RoaringBitmap feature to do intersections with serialized bitmaps](https://github.com/RoaringBitmap/roaring-rs/pull/281). Doing so drastically reduces the time spent reading, copying bytes in memory to use and keep a subset of the containers in the bitmap.

### Some Example Results

With a 45M documents dataset running on a good NVMe. This example filter was taking 77ms and with this PR only 13ms (6x speedup):

```sql
artist = 'The Beatles' AND (duration 150 TO 500 OR duration NOT EXISTS) AND genres IN [Rock, 'Rock and Roll'] AND rating > 4 AND released_year 1960 TO 1990
```

By reordering the filter AND clauses we can reach a constant 8ms execution time. However, note that it is a manual operation. On the other side the previous filter pipeline is still at a constant 45ms execution time with this filter. (6x speedup)

```sql
artist = 'The Beatles' AND genres IN [Rock, 'Rock and Roll'] AND released_year 1960 TO 1990 AND (duration 150 TO 500 OR duration NOT EXISTS)
```

### To Do
- [x] Rebase on `release-v1.9.0`.
- [ ] ~Skip branches of the facet/filter tree when nothing is in common with the universe~ slower this way.
- [x] When the universe is required use the universe given in parameter if possible.

Co-authored-by: Clément Renault <clement@meilisearch.com>

.github/workflows/bench-pr.yml

@@ -43,4 +43,11 @@ jobs:
 
         - name: Run benchmarks on PR ${{ github.event.issue.id }}
           run: |
-            cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" --reason "[Comment](${{ github.event.comment.html_url }}) on [#${{ github.event.issue.number }}](${{ github.event.issue.html_url }})" -- ${{ steps.command.outputs.command-arguments }}
+            cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" \
+               --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" \
+               --reason "[Comment](${{ github.event.comment.html_url }}) on [#${{ github.event.issue.number }}](${{ github.event.issue.html_url }})" \
+               -- ${{ steps.command.outputs.command-arguments }} > benchlinks.txt
+
+        - name: Send comment in PR
+          run: |
+            gh pr comment ${{github.event.issue.number}} --body-file benchlinks.txt

Cargo.toml

@@ -22,7 +22,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.8.0"
+version = "1.9.0"
 authors = [
     "Quentin de Quelen <quentin@dequelen.me>",
     "Clément Renault <clement@meilisearch.com>",

README.md

@@ -25,7 +25,7 @@
 
 <p align="center">⚡ A lightning-fast search engine that fits effortlessly into your apps, websites, and workflow 🔍</p>
 
-Meilisearch helps you shape a delightful search experience in a snap, offering features that work out-of-the-box to speed up your workflow.
+[Meilisearch](https://www.meilisearch.com) helps you shape a delightful search experience in a snap, offering features that work out of the box to speed up your workflow.
 
 <p align="center" name="demo">
   <a href="https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-gif#gh-light-mode-only" target="_blank">
@@ -39,8 +39,8 @@ Meilisearch helps you shape a delightful search experience in a snap, offering f
 🔥 [**Try it!**](https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-link) 🔥
 
 ## ✨ Features
-
-- **Search-as-you-type:** find search results in less than 50 milliseconds
+- **Hybrid search:** Combine the best of both [semantic](https://www.meilisearch.com/docs/learn/experimental/vector_search) & full-text search to get the most relevant results
+- **Search-as-you-type:** find & display results in less than 50 milliseconds to provide an intuitive experience
 - **[Typo tolerance](https://www.meilisearch.com/docs/learn/configuration/typo_tolerance?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** get relevant matches even when queries contain typos and misspellings
 - **[Filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features) and [faceted search](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** enhance your users' search experience with custom filters and build a faceted search interface in a few lines of code
 - **[Sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** sort results based on price, date, or pretty much anything else your users need
@@ -55,15 +55,15 @@ Meilisearch helps you shape a delightful search experience in a snap, offering f
 
 ## 📖 Documentation
 
-You can consult Meilisearch's documentation at [https://www.meilisearch.com/docs](https://www.meilisearch.com/docs/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=docs).
+You can consult Meilisearch's documentation at [meilisearch.com/docs](https://www.meilisearch.com/docs/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=docs).
 
 ## 🚀 Getting started
 
 For basic instructions on how to set up Meilisearch, add documents to an index, and search for documents, take a look at our [Quick Start](https://www.meilisearch.com/docs/learn/getting_started/quick_start?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=get-started) guide.
 
-## ⚡ Supercharge your Meilisearch experience
+## 🌍 Supercharge your Meilisearch experience
 
-Say goodbye to server deployment and manual updates with [Meilisearch Cloud](https://www.meilisearch.com/cloud?utm_campaign=oss&utm_source=github&utm_medium=meilisearch). No credit card required.
+Say goodbye to server deployment and manual updates with [Meilisearch Cloud](https://www.meilisearch.com/cloud?utm_campaign=oss&utm_source=github&utm_medium=meilisearch). Additional features include analytics & monitoring in many regions around the world. No credit card is required.
 
 ## 🧰 SDKs & integration tools
 
@@ -85,13 +85,13 @@ Finally, for more in-depth information, refer to our articles explaining fundame
 
 Meilisearch collects **anonymized** data from users to help us improve our product. You can [deactivate this](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=telemetry#how-to-disable-data-collection) whenever you want.
 
-To request deletion of collected data, please write to us at [privacy@meilisearch.com](mailto:privacy@meilisearch.com). Don't forget to include your `Instance UID` in the message, as this helps us quickly find and delete your data.
+To request deletion of collected data, please write to us at [privacy@meilisearch.com](mailto:privacy@meilisearch.com). Remember to include your `Instance UID` in the message, as this helps us quickly find and delete your data.
 
 If you want to know more about the kind of data we collect and what we use it for, check the [telemetry section](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=telemetry#how-to-disable-data-collection) of our documentation.
 
 ## 📫 Get in touch!
 
-Meilisearch is a search engine created by [Meili](https://www.welcometothejungle.com/en/companies/meilisearch), a software development company based in France and with team members all over the world. Want to know more about us? [Check out our blog!](https://blog.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=contact)
+Meilisearch is a search engine created by [Meili]([https://www.welcometothejungle.com/en/companies/meilisearch](https://www.meilisearch.com/careers)), a software development company headquartered in France and with team members all over the world. Want to know more about us? [Check out our blog!](https://blog.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=contact)
 
 🗞 [Subscribe to our newsletter](https://meilisearch.us2.list-manage.com/subscribe?u=27870f7b71c908a8b359599fb&id=79582d828e) if you don't want to miss any updates! We promise we won't clutter your mailbox: we only send one edition every two months.
 

build-info/Cargo.toml

@@ -15,4 +15,4 @@ time = { version = "0.3.34", features = ["parsing"] }
 
 [build-dependencies]
 anyhow = "1.0.80"
-vergen-gitcl = "1.0.0-beta.2"
+vergen-git2 = "1.0.0-beta.2"

build-info/build.rs

@@ -8,7 +8,7 @@ fn emit_git_variables() -> anyhow::Result<()> {
     // Note: any code that needs VERGEN_ environment variables should take care to define them manually in the Dockerfile and pass them
     // in the corresponding GitHub workflow (publish_docker.yml).
     // This is due to the Dockerfile building the binary outside of the git directory.
-    let mut builder = vergen_gitcl::GitclBuilder::default();
+    let mut builder = vergen_git2::Git2Builder::default();
 
     builder.branch(true);
     builder.commit_timestamp(true);
@@ -16,6 +16,7 @@ fn emit_git_variables() -> anyhow::Result<()> {
     builder.describe(true, true, None);
     builder.sha(false);
 
-    let gitcl = builder.build()?;
-    vergen_gitcl::Emitter::default().fail_on_error().add_instructions(&gitcl)?.emit()
+    let git2 = builder.build()?;
+
+    vergen_git2::Emitter::default().fail_on_error().add_instructions(&git2)?.emit()
 }

dump/src/reader/mod.rs

@@ -197,6 +197,140 @@ pub(crate) mod test {
     use super::*;
     use crate::reader::v6::RuntimeTogglableFeatures;
 
+    #[test]
+    fn import_dump_v6_with_vectors() {
+        // dump containing two indexes
+        //
+        // "vector", configured with an embedder
+        // contains:
+        // - one document with an overriden vector,
+        // - one document with a natural vector
+        // - one document with a _vectors map containing one additional embedder name and a natural vector
+        // - one document with a _vectors map containing one additional embedder name and an overriden vector
+        //
+        // "novector", no embedder
+        // contains:
+        // - a document without vector
+        // - a document with a random _vectors field
+        let dump = File::open("tests/assets/v6-with-vectors.dump").unwrap();
+        let mut dump = DumpReader::open(dump).unwrap();
+
+        // top level infos
+        insta::assert_display_snapshot!(dump.date().unwrap(), @"2024-05-16 15:51:34.151044 +00:00:00");
+        insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @"None");
+
+        // tasks
+        let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
+        meili_snap::snapshot_hash!(meili_snap::json_string!(tasks), @"278f63325ef06ca04d01df98d8207b94");
+        assert_eq!(update_files.len(), 10);
+        assert!(update_files[0].is_none()); // the dump creation
+        assert!(update_files[1].is_none());
+        assert!(update_files[2].is_none());
+        assert!(update_files[3].is_none());
+        assert!(update_files[4].is_none());
+        assert!(update_files[5].is_none());
+        assert!(update_files[6].is_none());
+        assert!(update_files[7].is_none());
+        assert!(update_files[8].is_none());
+        assert!(update_files[9].is_none());
+
+        // indexes
+        let mut indexes = dump.indexes().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        // the index are not ordered in any way by default
+        indexes.sort_by_key(|index| index.metadata().uid.to_string());
+
+        let mut vector_index = indexes.pop().unwrap();
+        let mut novector_index = indexes.pop().unwrap();
+        assert!(indexes.is_empty());
+
+        // vector
+
+        insta::assert_json_snapshot!(vector_index.metadata(), @r###"
+        {
+          "uid": "vector",
+          "primaryKey": "id",
+          "createdAt": "2024-05-16T15:33:17.240962Z",
+          "updatedAt": "2024-05-16T15:40:55.723052Z"
+        }
+        "###);
+
+        {
+            let documents: Result<Vec<_>> = vector_index.documents().unwrap().collect();
+            let mut documents = documents.unwrap();
+            assert_eq!(documents.len(), 4);
+
+            documents.sort_by_key(|doc| doc.get("id").unwrap().to_string());
+
+            {
+                let document = documents.pop().unwrap();
+                insta::assert_json_snapshot!(document);
+            }
+
+            {
+                let document = documents.pop().unwrap();
+                insta::assert_json_snapshot!(document);
+            }
+
+            {
+                let document = documents.pop().unwrap();
+                insta::assert_json_snapshot!(document);
+            }
+
+            {
+                let document = documents.pop().unwrap();
+                insta::assert_json_snapshot!(document);
+            }
+        }
+
+        // novector
+
+        insta::assert_json_snapshot!(novector_index.metadata(), @r###"
+        {
+          "uid": "novector",
+          "primaryKey": "id",
+          "createdAt": "2024-05-16T15:33:03.568055Z",
+          "updatedAt": "2024-05-16T15:33:07.530217Z"
+        }
+        "###);
+
+        insta::assert_json_snapshot!(novector_index.settings().unwrap().embedders, @"null");
+
+        {
+            let documents: Result<Vec<_>> = novector_index.documents().unwrap().collect();
+            let mut documents = documents.unwrap();
+            assert_eq!(documents.len(), 2);
+
+            documents.sort_by_key(|doc| doc.get("id").unwrap().to_string());
+
+            {
+                let document = documents.pop().unwrap();
+                insta::assert_json_snapshot!(document, @r###"
+                {
+                  "id": "e1",
+                  "other": "random1",
+                  "_vectors": "toto"
+                }
+                "###);
+            }
+
+            {
+                let document = documents.pop().unwrap();
+                insta::assert_json_snapshot!(document, @r###"
+                {
+                  "id": "e0",
+                  "other": "random0"
+                }
+                "###);
+            }
+        }
+
+        assert_eq!(
+            dump.features().unwrap().unwrap(),
+            RuntimeTogglableFeatures { vector_store: true, ..Default::default() }
+        );
+    }
+
     #[test]
     fn import_dump_v6_experimental() {
         let dump = File::open("tests/assets/v6-with-experimental.dump").unwrap();

dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-5.snap

@@ -0,0 +1,783 @@
+---
+source: dump/src/reader/mod.rs
+expression: document
+---
+{
+  "id": "e3",
+  "desc": "overriden vector + map",
+  "_vectors": {
+    "default": [
+      0.2,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1
+    ],
+    "toto": [
+      0.1
+    ]
+  }
+}

dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-6.snap

@@ -0,0 +1,786 @@
+---
+source: dump/src/reader/mod.rs
+expression: document
+---
+{
+  "id": "e2",
+  "desc": "natural vector + map",
+  "_vectors": {
+    "toto": [],
+    "default": {
+      "embeddings": [
+        [
+          -0.05189208313822746,
+          -0.9273212552070618,
+          0.1443813145160675,
+          0.0932632014155388,
+          0.2665371894836426,
+          0.36266782879829407,
+          0.6402910947799683,
+          0.32014018297195435,
+          0.030915971845388412,
+          -0.9312191605567932,
+          -0.3718109726905823,
+          -0.2700554132461548,
+          -1.1014580726623535,
+          0.9154956936836244,
+          -0.3406888246536255,
+          1.0077725648880005,
+          0.6577560901641846,
+          -0.3955195546150207,
+          -0.4148270785808563,
+          0.1855088472366333,
+          0.5062315464019775,
+          -0.3632686734199524,
+          -0.2277890294790268,
+          0.2560805082321167,
+          -0.3853609561920166,
+          -0.1604762226343155,
+          -0.13947471976280212,
+          -0.20147813856601715,
+          -0.4466346800327301,
+          -0.3761846721172333,
+          0.1443382054567337,
+          0.18205296993255615,
+          0.49359792470932007,
+          -0.22538000345230105,
+          -0.4996317625045776,
+          -0.22734887897968292,
+          -0.6034309267997742,
+          -0.7857939600944519,
+          -0.34923747181892395,
+          -0.3466345965862274,
+          0.21176661550998688,
+          -0.5101462006568909,
+          -0.3403083384037018,
+          0.000315118464641273,
+          0.236465722322464,
+          -0.10246097296476364,
+          -1.3013339042663574,
+          0.3419138789176941,
+          -0.32963496446609497,
+          -0.0901619717478752,
+          -0.5426247119903564,
+          0.22656650841236117,
+          -0.44758284091949463,
+          0.14151698350906372,
+          -0.1089438870549202,
+          0.5500766634941101,
+          -0.670711100101471,
+          -0.6227269768714905,
+          0.3894464075565338,
+          -0.27609574794769287,
+          0.7028202414512634,
+          -0.19697771966457367,
+          0.328511506319046,
+          0.5063360929489136,
+          0.4065195322036743,
+          0.2614171802997589,
+          -0.30274391174316406,
+          1.0393824577331543,
+          -0.7742937207221985,
+          -0.7874112129211426,
+          -0.6749666929244995,
+          0.5190866589546204,
+          0.004123548045754433,
+          -0.28312963247299194,
+          -0.038731709122657776,
+          -1.0142987966537476,
+          -0.09519586712121964,
+          0.8755272626876831,
+          0.4876938760280609,
+          0.7811151742935181,
+          0.85174959897995,
+          0.11826585978269576,
+          0.5373436808586121,
+          0.3649002015590668,
+          0.19064077734947205,
+          -0.00287026260048151,
+          -0.7305403351783752,
+          -0.015206154435873032,
+          -0.7899249196052551,
+          0.19407285749912265,
+          0.08596625179052353,
+          -0.28976231813430786,
+          -0.1525907665491104,
+          0.3798313438892365,
+          0.050306469202041626,
+          -0.5697937607765198,
+          0.4219021201133728,
+          0.276252806186676,
+          0.1559903472661972,
+          0.10030482709407806,
+          -0.4043720066547394,
+          -0.1969818025827408,
+          0.5739826560020447,
+          0.2116064727306366,
+          -1.4620544910430908,
+          -0.7802462577819824,
+          -0.24739810824394223,
+          -0.09791352599859238,
+          -0.4413802027702331,
+          0.21549351513385773,
+          -0.9520436525344848,
+          -0.08762510865926743,
+          0.08154498040676117,
+          -0.6154940724372864,
+          -1.01079523563385,
+          0.885427713394165,
+          0.6967288851737976,
+          0.27186504006385803,
+          -0.43194177746772766,
+          -0.11248451471328735,
+          0.7576630711555481,
+          0.4998855590820313,
+          0.0264343973249197,
+          0.9872855544090272,
+          0.5634694695472717,
+          0.053698331117630005,
+          0.19410227239131927,
+          0.3570743501186371,
+          -0.23670297861099243,
+          -0.9114483594894408,
+          0.07884842902421951,
+          0.7318344116210938,
+          0.44630110263824463,
+          0.08745364099740982,
+          -0.347101628780365,
+          -0.4314247667789459,
+          -0.5060274004936218,
+          0.003706763498485088,
+          0.44320008158683777,
+          -0.00788921769708395,
+          -0.1368623524904251,
+          -0.17391923069953918,
+          0.14473655819892883,
+          0.10927865654230118,
+          0.6974599361419678,
+          0.005052129738032818,
+          -0.016953065991401672,
+          -0.1256176233291626,
+          -0.036742497235536575,
+          0.5591985583305359,
+          -0.37619709968566895,
+          0.22429119050502777,
+          0.5403043031692505,
+          -0.8603790998458862,
+          -0.3456307053565979,
+          0.9292937517166138,
+          0.5074859261512756,
+          0.6310645937919617,
+          -0.3091641068458557,
+          0.46902573108673096,
+          0.7891915440559387,
+          0.4499550759792328,
+          0.2744995653629303,
+          0.2712305784225464,
+          -0.04349074140191078,
+          -0.3638863265514374,
+          0.7839881777763367,
+          0.7352104783058167,
+          -0.19457511603832245,
+          -0.5957832932472229,
+          -0.43704694509506226,
+          -1.084769368171692,
+          0.4904985725879669,
+          0.5385226011276245,
+          0.1891629993915558,
+          0.12338479608297348,
+          0.8315675258636475,
+          -0.07830192148685455,
+          1.0916285514831543,
+          -0.28066861629486084,
+          -1.3585069179534912,
+          0.5203898549079895,
+          0.08678033947944641,
+          -0.2566044330596924,
+          0.09484415501356123,
+          -0.0180208683013916,
+          1.0264745950698853,
+          -0.023572135716676712,
+          0.5864979028701782,
+          0.7625196576118469,
+          -0.2543414533138275,
+          -0.8877770900726318,
+          0.7611982822418213,
+          -0.06220436468720436,
+          0.937336564064026,
+          0.2704363465309143,
+          -0.37733694911003113,
+          0.5076137781143188,
+          -0.30641937255859375,
+          0.6252772808074951,
+          -0.0823579877614975,
+          -0.03736555948853493,
+          0.4131673276424408,
+          -0.6514252424240112,
+          0.12918265163898468,
+          -0.4483584463596344,
+          0.6750786304473877,
+          -0.37008383870124817,
+          -0.02324833907186985,
+          0.38027650117874146,
+          -0.26374951004981995,
+          0.4346931278705597,
+          0.42882832884788513,
+          -0.48798441886901855,
+          1.1882442235946655,
+          0.5132288336753845,
+          0.5284568667411804,
+          -0.03538886830210686,
+          0.29620853066444397,
+          -1.0683696269989014,
+          0.25936177372932434,
+          0.10404160618782043,
+          -0.25796034932136536,
+          0.027896970510482788,
+          -0.09225251525640488,
+          1.4811025857925415,
+          0.641173779964447,
+          -0.13838383555412292,
+          -0.3437179923057556,
+          0.5667019486427307,
+          -0.5400741696357727,
+          0.31090837717056274,
+          0.6470608115196228,
+          -0.3747067153453827,
+          -0.7364534735679626,
+          -0.07431528717279434,
+          0.5173454880714417,
+          -0.6578747034072876,
+          0.7107478976249695,
+          -0.7918999791145325,
+          -0.0648345872759819,
+          0.609937846660614,
+          -0.7329513430595398,
+          0.9741371870040894,
+          0.17912346124649048,
+          -0.02658769302070141,
+          0.5162150859832764,
+          -0.3978803157806397,
+          -0.7833885550498962,
+          -0.6497276425361633,
+          -0.3898126780986786,
+          -0.0952848568558693,
+          0.2663288116455078,
+          -0.1604052186012268,
+          0.373076468706131,
+          -0.8357769250869751,
+          -0.05217683315277099,
+          -0.2680160701274872,
+          0.8389158248901367,
+          0.6833611130714417,
+          -0.6712407469749451,
+          0.7406917214393616,
+          -0.44522786140441895,
+          -0.34645363688468933,
+          -0.27384576201438904,
+          -0.9878405928611756,
+          -0.8166060447692871,
+          0.06268279999494553,
+          0.38567957282066345,
+          -0.3274703919887543,
+          0.5296315550804138,
+          -0.11810623109340668,
+          0.23029841482639313,
+          0.08616159111261368,
+          -0.2195747196674347,
+          0.09430307894945145,
+          0.4057176411151886,
+          0.4892159104347229,
+          -0.1636916548013687,
+          -0.6071445345878601,
+          0.41256585717201233,
+          0.622254490852356,
+          -0.41223976016044617,
+          -0.6686707139015198,
+          -0.7474371790885925,
+          -0.8509522080421448,
+          -0.16754287481307983,
+          -0.9078601002693176,
+          -0.29653599858283997,
+          -0.5020652413368225,
+          0.4692700505256653,
+          0.01281109917908907,
+          -0.16071580350399017,
+          0.03388889133930206,
+          -0.020511148497462273,
+          0.5027827024459839,
+          -0.20729811489582065,
+          0.48107290267944336,
+          0.33669769763946533,
+          -0.5275911688804626,
+          0.48271527886390686,
+          0.2738940715789795,
+          -0.033152539283037186,
+          -0.13629786670207977,
+          -0.05965912342071533,
+          -0.26200807094573975,
+          0.04002794995903969,
+          -0.34095603227615356,
+          -3.986898899078369,
+          -0.46819332242012024,
+          -0.422744482755661,
+          -0.169097900390625,
+          0.6008929014205933,
+          0.058016058057546616,
+          -0.11401277780532836,
+          -0.3077819049358368,
+          -0.09595538675785063,
+          0.6723822355270386,
+          0.19367831945419312,
+          0.28304359316825867,
+          0.1609862744808197,
+          0.7567598819732666,
+          0.6889985799789429,
+          0.06907720118761063,
+          -0.04188092052936554,
+          -0.7434936165809631,
+          0.13321782648563385,
+          0.8456063270568848,
+          -0.10364038497209548,
+          -0.45084846019744873,
+          -0.4758241474628449,
+          0.43882066011428833,
+          -0.6432598829269409,
+          0.7217311859130859,
+          -0.24189773201942444,
+          0.12737572193145752,
+          -1.1008601188659668,
+          -0.3305315673351288,
+          0.14614742994308472,
+          -0.7819333076477051,
+          0.5287120342254639,
+          -0.055538054555654526,
+          0.1877404749393463,
+          -0.6907662153244019,
+          0.5616975426673889,
+          -0.4611121714115143,
+          -0.26109233498573303,
+          -0.12898315489292145,
+          -0.3724522292613983,
+          -0.7191406488418579,
+          -0.4425233602523804,
+          -0.644108235836029,
+          0.8424481153488159,
+          0.17532426118850708,
+          -0.5121750235557556,
+          -0.6467239260673523,
+          -0.0008507720194756985,
+          0.7866212129592896,
+          -0.02644744887948036,
+          -0.005045140627771616,
+          0.015782782807946205,
+          0.16334445774555206,
+          -0.1913367658853531,
+          -0.13697923719882965,
+          -0.6684983372688293,
+          0.18346354365348816,
+          -0.341105580329895,
+          0.5427411198616028,
+          0.3779832422733307,
+          -0.6778115034103394,
+          -0.2931850254535675,
+          -0.8805161714553833,
+          -0.4212774932384491,
+          -0.5368952751159668,
+          -1.3937891721725464,
+          -1.225494146347046,
+          0.4276703894138336,
+          1.1205668449401855,
+          -0.6005299687385559,
+          0.15732505917549133,
+          -0.3914784789085388,
+          -1.357046604156494,
+          -0.4707142114639282,
+          -0.1497287154197693,
+          -0.25035548210144043,
+          -0.34328439831733704,
+          0.39083412289619446,
+          0.1623048633337021,
+          -0.9275814294815063,
+          -0.6430015563964844,
+          0.2973862886428833,
+          0.5580436587333679,
+          -0.6232585310935974,
+          -0.6611042022705078,
+          0.4015969038009643,
+          -1.0232892036437988,
+          -0.2585645020008087,
+          -0.5431421399116516,
+          0.5021264553070068,
+          -0.48601630330085754,
+          -0.010242084041237833,
+          0.5862035155296326,
+          0.7316920161247253,
+          0.4036808013916016,
+          0.4269520044326782,
+          -0.705938458442688,
+          0.7747307419776917,
+          0.10164368897676468,
+          0.7887958884239197,
+          -0.9612497091293336,
+          0.12755516171455383,
+          0.06812842190265656,
+          -0.022603651508688927,
+          0.14722754061222076,
+          -0.5588505268096924,
+          -0.20689940452575684,
+          0.3557641804218292,
+          -0.6812759637832642,
+          0.2860803008079529,
+          -0.38954633474349976,
+          0.1759403496980667,
+          -0.5678874850273132,
+          -0.1692986786365509,
+          -0.14578519761562347,
+          0.5711379051208496,
+          1.0208125114440918,
+          0.7759483456611633,
+          -0.372348427772522,
+          -0.5460885763168335,
+          0.7190321683883667,
+          -0.6914990544319153,
+          0.13365162909030914,
+          -0.4854792356491089,
+          0.4054908752441406,
+          0.4502798914909363,
+          -0.3041122555732727,
+          -0.06726965308189392,
+          -0.05570871382951737,
+          -0.0455719493329525,
+          0.4785125255584717,
+          0.8867972493171692,
+          0.4107886850833893,
+          0.6121342182159424,
+          -0.20477132499217987,
+          -0.5598517656326294,
+          -0.6443566679954529,
+          -0.5905212759971619,
+          -0.5571200251579285,
+          0.17573799192905426,
+          -0.28621870279312134,
+          0.1685224026441574,
+          0.09719007462263109,
+          -0.04223639518022537,
+          -0.28623101115226746,
+          -0.1449810117483139,
+          -0.3789580464363098,
+          -0.5227636098861694,
+          -0.049728814512491226,
+          0.7849089503288269,
+          0.16792525351047516,
+          0.9849340915679932,
+          -0.6559549570083618,
+          0.35723909735679626,
+          -0.6822739243507385,
+          1.2873116731643677,
+          0.19993330538272855,
+          0.03512010723352432,
+          -0.6972134113311768,
+          0.18453484773635864,
+          -0.2437680810689926,
+          0.2156416028738022,
+          0.5230382680892944,
+          0.22020135819911957,
+          0.8314080238342285,
+          0.15627102553844452,
+          -0.7330264449119568,
+          0.3888184726238251,
+          -0.22034703195095065,
+          0.5457669496536255,
+          -0.48084837198257446,
+          -0.45576658844947815,
+          -0.09287727624177931,
+          -0.06968110054731369,
+          0.35125672817230225,
+          -0.4278119504451752,
+          0.2038476765155792,
+          0.11392722278833388,
+          0.9433983564376832,
+          -0.4097744226455689,
+          0.035297419875860214,
+          -0.4274404048919678,
+          -0.25100165605545044,
+          1.0943366289138794,
+          -0.07634022831916809,
+          -0.2925529479980469,
+          -0.7512530088424683,
+          0.2649727463722229,
+          -0.4078235328197479,
+          -0.3372223973274231,
+          0.05190162733197212,
+          0.005654910113662481,
+          -0.0001571219472680241,
+          -0.35445958375930786,
+          -0.7837416529655457,
+          0.1500556766986847,
+          0.4383024573326111,
+          0.6099548935890198,
+          0.05951934307813645,
+          -0.21325334906578064,
+          0.0199207104742527,
+          -0.22704418003559113,
+          -0.6481077671051025,
+          0.37442275881767273,
+          -1.015955924987793,
+          0.38637226819992065,
+          -0.06489371508359909,
+          -0.494120329618454,
+          0.3469836115837097,
+          0.15402406454086304,
+          -0.7660972476005554,
+          -0.7053225040435791,
+          -0.25964751839637756,
+          0.014004424214363098,
+          -0.2860170006752014,
+          -0.17565494775772095,
+          -0.45117494463920593,
+          -0.0031954257283359766,
+          0.09676837921142578,
+          -0.514464259147644,
+          0.41698193550109863,
+          -0.21642713248729703,
+          -0.5398141145706177,
+          -0.3647628426551819,
+          0.37005379796028137,
+          0.239425927400589,
+          -0.08833975344896317,
+          0.934946596622467,
+          -0.48340797424316406,
+          0.6241437792778015,
+          -0.7253676652908325,
+          -0.04303571209311485,
+          1.1125205755233765,
+          -0.15692919492721558,
+          -0.2914651036262512,
+          -0.5117168426513672,
+          0.21365483105182648,
+          0.4924402534961701,
+          0.5269662141799927,
+          0.0352792888879776,
+          -0.149167999625206,
+          -0.6019760370254517,
+          0.08245442807674408,
+          0.4900692105293274,
+          0.518824577331543,
+          -0.00005570516441366635,
+          -0.553304135799408,
+          0.22217543423175812,
+          0.5047767758369446,
+          0.135724738240242,
+          1.1511540412902832,
+          -0.3541218340396881,
+          -0.9712511897087096,
+          0.8353699445724487,
+          -0.39227569103240967,
+          -0.9117669463157654,
+          -0.26349931955337524,
+          0.05597023293375969,
+          0.20695461332798004,
+          0.3178807199001312,
+          1.0663238763809204,
+          0.5062212347984314,
+          0.7288597822189331,
+          0.09899299591779707,
+          0.553720235824585,
+          0.675009548664093,
+          -0.20067055523395536,
+          0.3138423264026642,
+          -0.6886593103408813,
+          -0.2910398542881012,
+          -1.3186300992965698,
+          -0.4684459865093231,
+          -0.095743365585804,
+          -0.1257995069026947,
+          -0.4858281314373016,
+          -0.4935407340526581,
+          -0.3266896903514862,
+          -0.3928797245025635,
+          -0.40803104639053345,
+          -0.9975396394729614,
+          0.4229583740234375,
+          0.37309643626213074,
+          0.4431034922599793,
+          0.30364808440208435,
+          -0.3765178918838501,
+          0.5616499185562134,
+          0.16904796659946442,
+          -0.7343707084655762,
+          0.2560209631919861,
+          0.6166825294494629,
+          0.3200829327106476,
+          -0.4483652710914612,
+          0.16224201023578644,
+          -0.31495288014411926,
+          -0.42713335156440735,
+          0.7270734906196594,
+          0.7049484848976135,
+          -0.0571461021900177,
+          0.04477125033736229,
+          -0.6647796034812927,
+          1.183672308921814,
+          0.36199676990509033,
+          0.046881116926670074,
+          0.4515796303749085,
+          0.9278061985969543,
+          0.31471705436706543,
+          -0.7073333859443665,
+          -0.3443860113620758,
+          0.5440067052841187,
+          -0.15020819008350372,
+          -0.541202962398529,
+          0.5203295946121216,
+          1.2192286252975464,
+          -0.9983593225479126,
+          -0.18758884072303772,
+          0.2758221924304962,
+          -0.6511523723602295,
+          -0.1584404855966568,
+          -0.236241415143013,
+          0.2692437767982483,
+          -0.4941152036190033,
+          0.4987454116344452,
+          -0.3331359028816223,
+          0.3163745701313019,
+          0.745529294013977,
+          -0.2905873656272888,
+          0.13602906465530396,
+          0.4679684340953827,
+          1.0555986166000366,
+          1.075700044631958,
+          0.5368486046791077,
+          -0.5118206739425659,
+          0.8668332099914551,
+          -0.5726966857910156,
+          -0.7811751961708069,
+          0.1938626915216446,
+          -0.1929349899291992,
+          0.1757766306400299,
+          0.6384295225143433,
+          0.26462844014167786,
+          0.9542630314826964,
+          0.19313029944896695,
+          1.264248013496399,
+          -0.6304428577423096,
+          0.0487106591463089,
+          -0.16211535036563873,
+          -0.7894763350486755,
+          0.3582514822483063,
+          -0.04153040423989296,
+          0.635784387588501,
+          0.6554391980171204,
+          -0.47010496258735657,
+          -0.8302040696144104,
+          -0.1350124627351761,
+          0.2568812072277069,
+          0.13614831864833832,
+          -0.2563649117946625,
+          -1.0434694290161133,
+          0.3232482671737671,
+          0.47882452607154846,
+          0.4298652410507202,
+          1.0563770532608032,
+          -0.28917592763900757,
+          -0.8533256649971008,
+          0.10648339986801147,
+          0.6376127004623413,
+          -0.20832888782024384,
+          0.2370245456695557,
+          0.0018312990432605147,
+          -0.2034837007522583,
+          0.01051164511591196,
+          -1.105310082435608,
+          0.29724350571632385,
+          0.15604574978351593,
+          0.1973688006401062,
+          0.44394731521606445,
+          0.3974513411521912,
+          -0.13625948131084442,
+          0.9571986198425292,
+          0.2257384955883026,
+          0.2323588728904724,
+          -0.5583669543266296,
+          -0.7854922413825989,
+          0.1647188365459442,
+          -1.6098142862319946,
+          0.318587988615036,
+          -0.13399995863437653,
+          -0.2172701060771942,
+          -0.767514705657959,
+          -0.5813586711883545,
+          -0.3195130527019501,
+          -0.04894036799669266,
+          0.2929930090904236,
+          -0.8213384747505188,
+          0.07181350141763687,
+          0.7469993829727173,
+          0.6407455801963806,
+          0.16365697979927063,
+          0.7870153188705444,
+          0.6524736881256104,
+          0.6399973630905151,
+          -0.04992736503481865,
+          -0.03959266096353531,
+          -0.2512352466583252,
+          0.8448855876922607,
+          -0.1422702670097351,
+          0.1216789186000824,
+          -1.2647287845611572,
+          0.5931149125099182,
+          0.7186052203178406,
+          -0.06118432432413101,
+          -1.1942816972732544,
+          -0.17677085101604462,
+          0.31543800234794617,
+          -0.32252824306488037,
+          0.8255583047866821,
+          -0.14529970288276672,
+          -0.2695446312427521,
+          -0.33378756046295166,
+          -0.1653425395488739,
+          0.1454019844532013,
+          -0.3920115828514099,
+          0.912214994430542,
+          -0.7279734015464783,
+          0.7374742031097412,
+          0.933980405330658,
+          0.13429680466651917,
+          -0.514870285987854,
+          0.3989711999893189,
+          -0.11613689363002776,
+          0.4022413492202759,
+          -0.9990655779838562,
+          -0.33749932050704956,
+          -0.4334589838981629,
+          -1.376373291015625,
+          -0.2993924915790558,
+          -0.09454808384180068,
+          -0.01314175222069025,
+          -0.001090060803107917,
+          0.2137461006641388,
+          0.2938512861728668,
+          0.17508235573768616,
+          0.8260607123374939,
+          -0.7218498587608337,
+          0.2414487451314926,
+          -0.47296759486198425,
+          -0.3002610504627228,
+          -1.238540768623352,
+          0.08663805574178696,
+          0.6805586218833923,
+          0.5909030437469482,
+          -0.42807504534721375,
+          -0.22887496650218964,
+          0.47537800669670105,
+          -1.0474627017974854,
+          0.6338009238243103,
+          0.06548397243022919,
+          0.4971011281013489,
+          1.3484878540039063
+        ]
+      ],
+      "userProvided": false
+    }
+  }
+}

dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-7.snap

@@ -0,0 +1,785 @@
+---
+source: dump/src/reader/mod.rs
+expression: document
+---
+{
+  "id": "e1",
+  "desc": "natural vector",
+  "_vectors": {
+    "default": {
+      "embeddings": [
+        [
+          -0.2979458272457123,
+          -0.5288640856742859,
+          -0.019957859069108963,
+          -0.18495318293571472,
+          0.7429973483085632,
+          0.5238497257232666,
+          0.432366281747818,
+          0.32744166254997253,
+          0.0020762972999364138,
+          -0.9507834911346436,
+          -0.35097137093544006,
+          0.08469701558351517,
+          -1.4176613092422483,
+          0.4647577106952667,
+          -0.69340580701828,
+          1.0372896194458008,
+          0.3716741800308227,
+          0.06031008064746857,
+          -0.6152024269104004,
+          0.007914665155112743,
+          0.7954924702644348,
+          -0.20773003995418549,
+          0.09376765787601472,
+          0.04508133605122566,
+          -0.2084471583366394,
+          -0.1518009901046753,
+          0.018195509910583496,
+          -0.07044368237257004,
+          -0.18119366466999057,
+          -0.4480230510234833,
+          0.3822529911994934,
+          0.1911812424659729,
+          0.4674372375011444,
+          0.06963984668254852,
+          -0.09341949224472046,
+          0.005675444379448891,
+          -0.6774799227714539,
+          -0.7066726684570313,
+          -0.39256376028060913,
+          0.04005039855837822,
+          0.2084812968969345,
+          -0.7872875928878784,
+          -0.8205880522727966,
+          0.2919981777667999,
+          -0.06004738807678223,
+          -0.4907574355602264,
+          -1.5937862396240234,
+          0.24249385297298431,
+          -0.14709846675395966,
+          -0.11860740929841997,
+          -0.8299489617347717,
+          0.472964346408844,
+          -0.497518390417099,
+          -0.22205302119255063,
+          -0.4196169078350067,
+          0.32697558403015137,
+          -0.360930860042572,
+          -0.9789686799049376,
+          0.1887447088956833,
+          -0.403737336397171,
+          0.18524253368377688,
+          0.3768732249736786,
+          0.3666233420372009,
+          0.3511938452720642,
+          0.6985810995101929,
+          0.41721710562705994,
+          0.09754953533411026,
+          0.6204307079315186,
+          -1.0762996673583984,
+          -0.06263761967420578,
+          -0.7376511693000793,
+          0.6849768161773682,
+          -0.1745152473449707,
+          -0.40449759364128113,
+          0.20757411420345304,
+          -0.8424443006515503,
+          0.330015629529953,
+          0.3489064872264862,
+          1.0954371690750122,
+          0.8487558960914612,
+          1.1076823472976685,
+          0.61430823802948,
+          0.4155903458595276,
+          0.4111340939998626,
+          0.05753209814429283,
+          -0.06429877132177353,
+          -0.765606164932251,
+          -0.41703930497169495,
+          -0.508820652961731,
+          0.19859947264194489,
+          -0.16607828438282013,
+          -0.28112146258354187,
+          0.11032675206661224,
+          0.38809511065483093,
+          -0.36498191952705383,
+          -0.48671194911003113,
+          0.6755134463310242,
+          0.03958442434668541,
+          0.4478721618652344,
+          -0.10335399955511092,
+          -0.9546685814857484,
+          -0.6087718605995178,
+          0.17498846352100372,
+          0.08320838958024979,
+          -1.4478336572647097,
+          -0.605027437210083,
+          -0.5867993235588074,
+          -0.14711688458919525,
+          -0.5447602272033691,
+          -0.026259321719408035,
+          -0.6997418403625488,
+          -0.07349082082509995,
+          0.10638900846242905,
+          -0.7133527398109436,
+          -0.9396815299987792,
+          1.087092399597168,
+          1.1885089874267578,
+          0.4011896848678589,
+          -0.4089202582836151,
+          -0.10938972979784012,
+          0.6726722121238708,
+          0.24576938152313232,
+          -0.24247920513153076,
+          1.1499971151351929,
+          0.47813335061073303,
+          -0.05331678315997124,
+          0.32338133454322815,
+          0.4870913326740265,
+          -0.23144258558750153,
+          -1.2023426294326782,
+          0.2349330335855484,
+          1.080536961555481,
+          0.29334118962287903,
+          0.391574501991272,
+          -0.15818795561790466,
+          -0.2948290705680847,
+          -0.024689948186278343,
+          0.06602869182825089,
+          0.5937030911445618,
+          -0.047901444137096405,
+          -0.512734591960907,
+          -0.35780075192451477,
+          0.28751692175865173,
+          0.4298716187477112,
+          0.9242428541183472,
+          -0.17208744585514069,
+          0.11515070497989656,
+          -0.0335976779460907,
+          -0.3422986567020416,
+          0.5344581604003906,
+          0.19895796477794647,
+          0.33001241087913513,
+          0.6390730142593384,
+          -0.6074934005737305,
+          -0.2553696632385254,
+          0.9644920229911804,
+          0.2699219584465027,
+          0.6403993368148804,
+          -0.6380003690719604,
+          -0.027310986071825027,
+          0.638815701007843,
+          0.27719101309776306,
+          -0.13553589582443237,
+          0.750195324420929,
+          0.1224869191646576,
+          -0.20613941550254825,
+          0.8444448709487915,
+          0.16200250387191772,
+          -0.24750925600528717,
+          -0.739950954914093,
+          -0.28443849086761475,
+          -1.176282525062561,
+          0.516107976436615,
+          0.3774825632572174,
+          0.10906043648719788,
+          0.07962015271186829,
+          0.7384604215621948,
+          -0.051241904497146606,
+          1.1730090379714966,
+          -0.4828610122203827,
+          -1.404372215270996,
+          0.8811132311820984,
+          -0.3839482367038727,
+          0.022516896948218346,
+          -0.0491158664226532,
+          -0.43027013540267944,
+          1.2049334049224854,
+          -0.27309560775756836,
+          0.6883630752563477,
+          0.8264574408531189,
+          -0.5020735263824463,
+          -0.4874092042446137,
+          0.6007202863693237,
+          -0.4965405762195587,
+          1.1302915811538696,
+          0.032572727650403976,
+          -0.3731859028339386,
+          0.658271849155426,
+          -0.9023059010505676,
+          0.7400162220001221,
+          0.014550759457051754,
+          -0.19699542224407196,
+          0.2319706380367279,
+          -0.789058268070221,
+          -0.14905710518360138,
+          -0.5826214551925659,
+          0.207652747631073,
+          -0.4507439732551574,
+          -0.3163885474205017,
+          0.3604124188423157,
+          -0.45119962096214294,
+          0.3428427278995514,
+          0.3005594313144684,
+          -0.36026081442832947,
+          1.1014249324798584,
+          0.40884315967559814,
+          0.34991952776908875,
+          -0.1806638240814209,
+          0.27440476417541504,
+          -0.7118373513221741,
+          0.4645499587059021,
+          0.214790478348732,
+          -0.2343102991580963,
+          0.10500429570674896,
+          -0.28034430742263794,
+          1.2267805337905884,
+          1.0561333894729614,
+          -0.497364342212677,
+          -0.6143305897712708,
+          0.24963727593421936,
+          -0.33136463165283203,
+          -0.01473914459347725,
+          0.495918869972229,
+          -0.6985538005828857,
+          -1.0033197402954102,
+          0.35937801003456116,
+          0.6325868368148804,
+          -0.6808838844299316,
+          1.0354058742523191,
+          -0.7214401960372925,
+          -0.33318862318992615,
+          0.874398410320282,
+          -0.6594992280006409,
+          0.6830640435218811,
+          -0.18534131348133087,
+          0.024834271520376205,
+          0.19901277124881744,
+          -0.5992477536201477,
+          -1.2126628160476685,
+          -0.9245557188987732,
+          -0.3898217976093292,
+          -0.1286519467830658,
+          0.4217943847179413,
+          -0.1143646091222763,
+          0.5630772709846497,
+          -0.5240639448165894,
+          0.21152715384960177,
+          -0.3792001008987427,
+          0.8266305327415466,
+          1.170984387397766,
+          -0.8072142004966736,
+          0.11382893472909927,
+          -0.17953898012638092,
+          -0.1789460331201553,
+          -0.15078622102737427,
+          -1.2082908153533936,
+          -0.7812382578849792,
+          -0.10903695970773696,
+          0.7303897142410278,
+          -0.39054441452026367,
+          0.19511254131793976,
+          -0.09121843427419662,
+          0.22400228679180145,
+          0.30143046379089355,
+          0.1141919493675232,
+          0.48112115263938904,
+          0.7307931780815125,
+          0.09701362252235413,
+          -0.2795647978782654,
+          -0.3997688889503479,
+          0.5540812611579895,
+          0.564578115940094,
+          -0.40065160393714905,
+          -0.3629159033298493,
+          -0.3789091110229492,
+          -0.7298538088798523,
+          -0.6996853351593018,
+          -0.4477842152118683,
+          -0.289089560508728,
+          -0.6430277824401855,
+          0.2344944179058075,
+          0.3742927014827728,
+          -0.5079357028007507,
+          0.28841453790664673,
+          0.06515737622976303,
+          0.707315981388092,
+          0.09498685598373412,
+          0.8365515470504761,
+          0.10002726316452026,
+          -0.7695478200912476,
+          0.6264724135398865,
+          0.7562043070793152,
+          -0.23112858831882477,
+          -0.2871039807796478,
+          -0.25010058283805847,
+          0.2783474028110504,
+          -0.03224996477365494,
+          -0.9119359850883484,
+          -3.6940200328826904,
+          -0.5099936127662659,
+          -0.1604711413383484,
+          0.17453284561634064,
+          0.41759559512138367,
+          0.1419190913438797,
+          -0.11362407356500626,
+          -0.33312007784843445,
+          0.11511333286762238,
+          0.4667884409427643,
+          -0.0031647447030991316,
+          0.15879854559898376,
+          0.3042248487472534,
+          0.5404849052429199,
+          0.8515422344207764,
+          0.06286454200744629,
+          0.43790125846862793,
+          -0.8682025074958801,
+          -0.06363756954669952,
+          0.5547921657562256,
+          -0.01483887154608965,
+          -0.07361344993114471,
+          -0.929947018623352,
+          0.3502565622329712,
+          -0.5080993175506592,
+          1.0380364656448364,
+          -0.2017953395843506,
+          0.21319580078125,
+          -1.0763001441955566,
+          -0.556368887424469,
+          0.1949922740459442,
+          -0.6445739269256592,
+          0.6791343688964844,
+          0.21188358962535855,
+          0.3736183941364288,
+          -0.21800459921360016,
+          0.7597446441650391,
+          -0.3732394874095917,
+          -0.4710160195827484,
+          0.025146087631583217,
+          0.05341297015547752,
+          -0.9522109627723694,
+          -0.6000866889953613,
+          -0.08469046652317047,
+          0.5966026186943054,
+          0.3444081246852875,
+          -0.461188405752182,
+          -0.5279349088668823,
+          0.10296865552663804,
+          0.5175143480300903,
+          -0.20671147108078003,
+          0.13392412662506104,
+          0.4812754988670349,
+          0.2993808686733246,
+          -0.3005635440349579,
+          0.5141698122024536,
+          -0.6239235401153564,
+          0.2877119481563568,
+          -0.4452739953994751,
+          0.5621107816696167,
+          0.5047508478164673,
+          -0.4226335883140564,
+          -0.18578553199768064,
+          -1.1967322826385498,
+          0.28178197145462036,
+          -0.8692031502723694,
+          -1.1812998056411743,
+          -1.4526212215423584,
+          0.4645712077617645,
+          0.9327932000160216,
+          -0.6560136675834656,
+          0.461549699306488,
+          -0.5621527433395386,
+          -1.328449010848999,
+          -0.08676894754171371,
+          0.00021918353741057217,
+          -0.18864136934280396,
+          0.1259666532278061,
+          0.18240638077259064,
+          -0.14919660985469818,
+          -0.8965857625007629,
+          -0.7539900541305542,
+          0.013973715715110302,
+          0.504276692867279,
+          -0.704748272895813,
+          -0.6428424119949341,
+          0.6303996443748474,
+          -0.5404738187789917,
+          -0.31176653504371643,
+          -0.21262824535369873,
+          0.18736739456653595,
+          -0.7998970746994019,
+          0.039946746081113815,
+          0.7390344738960266,
+          0.4283199906349182,
+          0.3795057237148285,
+          0.07204607129096985,
+          -0.9230587482452391,
+          0.9440426230430604,
+          0.26272690296173096,
+          0.5598306655883789,
+          -1.0520871877670288,
+          -0.2677186131477356,
+          -0.1888762265443802,
+          0.30426350235939026,
+          0.4746131896972656,
+          -0.5746733546257019,
+          -0.4197768568992615,
+          0.8565112948417664,
+          -0.6767723560333252,
+          0.23448683321475983,
+          -0.2010004222393036,
+          0.4112907350063324,
+          -0.6497949957847595,
+          -0.418667733669281,
+          -0.4950824975967407,
+          0.44438859820365906,
+          1.026281714439392,
+          0.482397586107254,
+          -0.26220494508743286,
+          -0.3640787005424499,
+          0.5907743573188782,
+          -0.8771642446517944,
+          0.09708411991596222,
+          -0.3671700060367584,
+          0.4331349730491638,
+          0.619417667388916,
+          -0.2684665620326996,
+          -0.5123821496963501,
+          -0.1502324342727661,
+          -0.012190685607492924,
+          0.3580845892429352,
+          0.8617186546325684,
+          0.3493645489215851,
+          1.0270192623138428,
+          0.18297909200191495,
+          -0.5881339311599731,
+          -0.1733516901731491,
+          -0.5040576457977295,
+          -0.340370237827301,
+          -0.26767754554748535,
+          -0.28570041060447693,
+          -0.032928116619586945,
+          0.6029254794120789,
+          0.17397655546665192,
+          0.09346921741962431,
+          0.27815181016921997,
+          -0.46699589490890503,
+          -0.8148876428604126,
+          -0.3964351713657379,
+          0.3812595009803772,
+          0.13547226786613464,
+          0.7126688361167908,
+          -0.3473474085330963,
+          -0.06573959439992905,
+          -0.6483767032623291,
+          1.4808889627456665,
+          0.30924928188323975,
+          -0.5085946917533875,
+          -0.8613000512123108,
+          0.3048902451992035,
+          -0.4241599142551422,
+          0.15909206867218018,
+          0.5764641761779785,
+          -0.07879110425710678,
+          1.015336513519287,
+          0.07599356025457382,
+          -0.7025855779647827,
+          0.30047643184661865,
+          -0.35094937682151794,
+          0.2522146999835968,
+          -0.2338722199201584,
+          -0.8326804637908936,
+          -0.13695412874221802,
+          -0.03452421352267265,
+          0.47974953055381775,
+          -0.18385636806488037,
+          0.32438594102859497,
+          0.1797013282775879,
+          0.787494957447052,
+          -0.12579888105392456,
+          -0.07507286965847015,
+          -0.4389670491218567,
+          0.2720070779323578,
+          0.8138866424560547,
+          0.01974171027541161,
+          -0.3057698905467987,
+          -0.6709924936294556,
+          0.0885881632566452,
+          -0.2862754464149475,
+          0.03475658595561981,
+          -0.1285519152879715,
+          0.3838353455066681,
+          -0.2944154739379883,
+          -0.4204859137535095,
+          -0.4416137933731079,
+          0.13426260650157928,
+          0.36733248829841614,
+          0.573428750038147,
+          -0.14928072690963745,
+          -0.026076916605234143,
+          0.33286052942276,
+          -0.5340145826339722,
+          -0.17279052734375,
+          -0.01154550164937973,
+          -0.6620771884918213,
+          0.18390542268753052,
+          -0.08265615254640579,
+          -0.2489682286977768,
+          0.2429984211921692,
+          -0.044153645634651184,
+          -0.986578404903412,
+          -0.33574509620666504,
+          -0.5387663841247559,
+          0.19767941534519196,
+          0.12540718913078308,
+          -0.3403128981590271,
+          -0.4154576361179352,
+          0.17275673151016235,
+          0.09407442808151244,
+          -0.5414086580276489,
+          0.4393929839134216,
+          0.1725579798221588,
+          -0.4998118281364441,
+          -0.6926208138465881,
+          0.16552448272705078,
+          0.6659538149833679,
+          -0.10949844866991044,
+          0.986426830291748,
+          0.01748848147690296,
+          0.4003709554672241,
+          -0.5430638194084167,
+          0.35347291827201843,
+          0.6887399554252625,
+          0.08274628221988678,
+          0.13407137989997864,
+          -0.591465950012207,
+          0.3446292281150818,
+          0.6069018244743347,
+          0.1935492902994156,
+          -0.0989871397614479,
+          0.07008486241102219,
+          -0.8503749370574951,
+          -0.09507356584072112,
+          0.6259510517120361,
+          0.13934025168418884,
+          0.06392545253038406,
+          -0.4112265408039093,
+          -0.08475656062364578,
+          0.4974113404750824,
+          -0.30606114864349365,
+          1.111435890197754,
+          -0.018766529858112335,
+          -0.8422622680664063,
+          0.4325508773326874,
+          -0.2832120656967163,
+          -0.4859798848628998,
+          -0.41498348116874695,
+          0.015977520495653152,
+          0.5292825698852539,
+          0.4538311660289765,
+          1.1328668594360352,
+          0.22632671892642975,
+          0.7918671369552612,
+          0.33401933312416077,
+          0.7306135296821594,
+          0.3548600673675537,
+          0.12506209313869476,
+          0.8573207855224609,
+          -0.5818327069282532,
+          -0.6953738927841187,
+          -1.6171947717666626,
+          -0.1699674427509308,
+          0.6318262815475464,
+          -0.05671752244234085,
+          -0.28145185112953186,
+          -0.3976689279079437,
+          -0.2041076272726059,
+          -0.5495951175689697,
+          -0.5152917504310608,
+          -0.9309796094894408,
+          0.101932130753994,
+          0.1367802917957306,
+          0.1490798443555832,
+          0.5304336547851563,
+          -0.5082434415817261,
+          0.06688683480024338,
+          0.14657628536224365,
+          -0.782435953617096,
+          0.2962816655635834,
+          0.6965363621711731,
+          0.8496337532997131,
+          -0.3042965829372406,
+          0.04343798756599426,
+          0.0330701619386673,
+          -0.5662598013877869,
+          1.1086925268173218,
+          0.756072998046875,
+          -0.204134538769722,
+          0.2404300570487976,
+          -0.47848284244537354,
+          1.3659011125564575,
+          0.5645433068275452,
+          -0.15836156904697418,
+          0.43395575881004333,
+          0.5944653749465942,
+          1.0043466091156006,
+          -0.49446743726730347,
+          -0.5954391360282898,
+          0.5341240763664246,
+          0.020598189905285835,
+          -0.4036853015422821,
+          0.4473709762096405,
+          1.1998231410980225,
+          -0.9317775368690492,
+          -0.23321466147899628,
+          0.2052552700042725,
+          -0.7423108816146851,
+          -0.19917210936546328,
+          -0.1722569614648819,
+          -0.034072667360305786,
+          -0.00671181408688426,
+          0.46396249532699585,
+          -0.1372445821762085,
+          0.053376372903585434,
+          0.7392690777778625,
+          -0.38447609543800354,
+          0.07497968524694443,
+          0.5197252631187439,
+          1.3746477365493774,
+          0.9060075879096984,
+          0.20000585913658145,
+          -0.4053704142570496,
+          0.7497360110282898,
+          -0.34087055921554565,
+          -1.101803183555603,
+          0.273650586605072,
+          -0.5125769376754761,
+          0.22472351789474487,
+          0.480757474899292,
+          -0.19845178723335263,
+          0.8857700824737549,
+          0.30752456188201904,
+          1.1109285354614258,
+          -0.6768012642860413,
+          0.524367094039917,
+          -0.22495046257972717,
+          -0.4224412739276886,
+          0.40753406286239624,
+          -0.23133376240730288,
+          0.3297771215438843,
+          0.4905449151992798,
+          -0.6813114285469055,
+          -0.7543983459472656,
+          -0.5599071383476257,
+          0.14351597428321838,
+          -0.029278717935085297,
+          -0.3970443606376648,
+          -0.303079217672348,
+          0.24161772429943085,
+          0.008353390730917454,
+          -0.0062365154735744,
+          1.0824860334396362,
+          -0.3704061508178711,
+          -1.0337258577346802,
+          0.04638749733567238,
+          1.163011074066162,
+          -0.31737643480300903,
+          0.013986887410283089,
+          0.19223114848136905,
+          -0.2260770797729492,
+          -0.210910826921463,
+          -1.0191949605941772,
+          0.22356095910072327,
+          0.09353553503751756,
+          0.18096882104873657,
+          0.14867214858531952,
+          0.43408671021461487,
+          -0.33312076330184937,
+          0.8173948526382446,
+          0.6428242921829224,
+          0.20215003192424777,
+          -0.6634518504142761,
+          -0.4132290482521057,
+          0.29815030097961426,
+          -1.579406976699829,
+          -0.0981958732008934,
+          -0.03941014781594277,
+          0.1709178239107132,
+          -0.5481140613555908,
+          -0.5338194966316223,
+          -0.3528362512588501,
+          -0.11561278253793716,
+          -0.21793591976165771,
+          -1.1570470333099363,
+          0.2157980799674988,
+          0.42083489894866943,
+          0.9639263153076172,
+          0.09747201204299928,
+          0.15671424567699432,
+          0.4034591615200043,
+          0.6728067994117737,
+          -0.5216875672340393,
+          0.09657668322324751,
+          -0.2416689097881317,
+          0.747975766658783,
+          0.1021689772605896,
+          0.11652665585279463,
+          -1.0484966039657593,
+          0.8489304780960083,
+          0.7169828414916992,
+          -0.09012343734502792,
+          -1.3173753023147583,
+          0.057890523225069046,
+          -0.006231260951608419,
+          -0.1018214002251625,
+          0.936040461063385,
+          -0.0502331368625164,
+          -0.4284322261810303,
+          -0.38209280371665955,
+          -0.22668412327766416,
+          0.0782942995429039,
+          -0.4881664514541626,
+          0.9268959760665894,
+          0.001867273123934865,
+          0.42261114716529846,
+          0.8283362984657288,
+          0.4256294071674347,
+          -0.7965338826179504,
+          0.4840078353881836,
+          -0.19861412048339844,
+          0.33977967500686646,
+          -0.4604192078113556,
+          -0.3107339143753052,
+          -0.2839638590812683,
+          -1.5734281539916992,
+          0.005220232997089624,
+          0.09239906817674635,
+          -0.7828494906425476,
+          -0.1397123783826828,
+          0.2576255202293396,
+          0.21372435986995697,
+          -0.23169949650764465,
+          0.4016408920288086,
+          -0.462497353553772,
+          -0.2186472862958908,
+          -0.5617868900299072,
+          -0.3649831712245941,
+          -1.1585862636566162,
+          -0.08222806453704834,
+          0.931126832962036,
+          0.4327389597892761,
+          -0.46451422572135925,
+          -0.5430706143379211,
+          -0.27434298396110535,
+          -0.9479129314422609,
+          0.1845661848783493,
+          0.3972720205783844,
+          0.4883299469947815,
+          1.04031240940094
+        ]
+      ],
+      "userProvided": false
+    }
+  }
+}

dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-8.snap

@@ -0,0 +1,780 @@
+---
+source: dump/src/reader/mod.rs
+expression: document
+---
+{
+  "id": "e0",
+  "desc": "overriden vector",
+  "_vectors": {
+    "default": [
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1,
+      0.1
+    ]
+  }
+}

index-scheduler/Cargo.toml

@@ -22,7 +22,6 @@ flate2 = "1.0.28"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
 page_size = "0.5.0"
-puffin = { version = "0.16.0", features = ["serialization"] }
 rayon = "1.8.1"
 roaring = { version = "0.10.2", features = ["serde"] }
 serde = { version = "1.0.195", features = ["derive"] }

index-scheduler/src/batch.rs

@@ -31,6 +31,9 @@ use meilisearch_types::milli::heed::CompactionOption;
 use meilisearch_types::milli::update::{
     IndexDocumentsConfig, IndexDocumentsMethod, IndexerConfig, Settings as MilliSettings,
 };
+use meilisearch_types::milli::vector::parsed_vectors::{
+    ExplicitVectors, VectorOrArrayOfVectors, RESERVED_VECTORS_FIELD_NAME,
+};
 use meilisearch_types::milli::{self, Filter};
 use meilisearch_types::settings::{apply_settings_to_builder, Settings, Unchecked};
 use meilisearch_types::tasks::{Details, IndexSwap, Kind, KindWithContent, Status, Task};
@@ -526,8 +529,6 @@ impl IndexScheduler {
         #[cfg(test)]
         self.maybe_fail(crate::tests::FailureLocation::InsideCreateBatch)?;
 
-        puffin::profile_function!();
-
         let enqueued = &self.get_status(rtxn, Status::Enqueued)?;
         let to_cancel = self.get_kind(rtxn, Kind::TaskCancelation)? & enqueued;
 
@@ -636,8 +637,6 @@ impl IndexScheduler {
             self.breakpoint(crate::Breakpoint::InsideProcessBatch);
         }
 
-        puffin::profile_function!(batch.to_string());
-
         match batch {
             Batch::TaskCancelation { mut task, previous_started_at, previous_processing_tasks } => {
                 // 1. Retrieve the tasks that matched the query at enqueue-time.
@@ -916,8 +915,55 @@ impl IndexScheduler {
                         if self.must_stop_processing.get() {
                             return Err(Error::AbortedTask);
                         }
-                        let (_id, doc) = ret?;
-                        let document = milli::obkv_to_json(&all_fields, &fields_ids_map, doc)?;
+
+                        let (id, doc) = ret?;
+
+                        let mut document = milli::obkv_to_json(&all_fields, &fields_ids_map, doc)?;
+
+                        'inject_vectors: {
+                            let embeddings = index.embeddings(&rtxn, id)?;
+
+                            if embeddings.is_empty() {
+                                break 'inject_vectors;
+                            }
+
+                            let vectors = document
+                                .entry(RESERVED_VECTORS_FIELD_NAME.to_owned())
+                                .or_insert(serde_json::Value::Object(Default::default()));
+
+                            let serde_json::Value::Object(vectors) = vectors else {
+                                return Err(milli::Error::UserError(
+                                    milli::UserError::InvalidVectorsMapType {
+                                        document_id: {
+                                            if let Ok(Some(Ok(index))) = index
+                                                .external_id_of(&rtxn, std::iter::once(id))
+                                                .map(|it| it.into_iter().next())
+                                            {
+                                                index
+                                            } else {
+                                                format!("internal docid={id}")
+                                            }
+                                        },
+                                        value: vectors.clone(),
+                                    },
+                                )
+                                .into());
+                            };
+
+                            for (embedder_name, embeddings) in embeddings {
+                                // don't change the entry if it already exists, because it was user-provided
+                                vectors.entry(embedder_name).or_insert_with(|| {
+                                    let embeddings = ExplicitVectors {
+                                        embeddings: VectorOrArrayOfVectors::from_array_of_vectors(
+                                            embeddings,
+                                        ),
+                                        user_provided: false,
+                                    };
+                                    serde_json::to_value(embeddings).unwrap()
+                                });
+                            }
+                        }
+
                         index_dumper.push_document(&document)?;
                     }
 
@@ -1176,8 +1222,6 @@ impl IndexScheduler {
         index: &'i Index,
         operation: IndexOperation,
     ) -> Result<Vec<Task>> {
-        puffin::profile_function!();
-
         match operation {
             IndexOperation::DocumentClear { mut tasks, .. } => {
                 let count = milli::update::ClearDocuments::new(index_wtxn, index).execute()?;

index-scheduler/src/features.rs

@@ -68,19 +68,6 @@ impl RoFeatures {
             .into())
         }
     }
-
-    pub fn check_puffin(&self) -> Result<()> {
-        if self.runtime.export_puffin_reports {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action: "Outputting Puffin reports to disk",
-                feature: "export puffin reports",
-                issue_link: "https://github.com/meilisearch/product/discussions/693",
-            }
-            .into())
-        }
-    }
 }
 
 impl FeatureData {

index-scheduler/src/insta_snapshot.rs

@@ -32,7 +32,6 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
         features: _,
         max_number_of_tasks: _,
         max_number_of_batched_tasks: _,
-        puffin_frame: _,
         wake_up: _,
         dumps_path: _,
         snapshots_path: _,

index-scheduler/src/lib.rs

@@ -33,7 +33,6 @@ pub type Result<T> = std::result::Result<T, Error>;
 pub type TaskId = u32;
 
 use std::collections::{BTreeMap, HashMap};
-use std::fs::File;
 use std::io::{self, BufReader, Read};
 use std::ops::{Bound, RangeBounds};
 use std::path::{Path, PathBuf};
@@ -59,7 +58,6 @@ use meilisearch_types::milli::vector::{Embedder, EmbedderOptions, EmbeddingConfi
 use meilisearch_types::milli::{self, CboRoaringBitmapCodec, Index, RoaringBitmapCodec, BEU32};
 use meilisearch_types::task_view::TaskView;
 use meilisearch_types::tasks::{Kind, KindWithContent, Status, Task};
-use puffin::FrameView;
 use rayon::current_num_threads;
 use rayon::prelude::{IntoParallelIterator, ParallelIterator};
 use roaring::RoaringBitmap;
@@ -344,9 +342,6 @@ pub struct IndexScheduler {
     /// The Authorization header to send to the webhook URL.
     pub(crate) webhook_authorization_header: Option<String>,
 
-    /// A frame to output the indexation profiling files to disk.
-    pub(crate) puffin_frame: Arc<puffin::GlobalFrameView>,
-
     /// The path used to create the dumps.
     pub(crate) dumps_path: PathBuf,
 
@@ -401,7 +396,6 @@ impl IndexScheduler {
             cleanup_enabled: self.cleanup_enabled,
             max_number_of_tasks: self.max_number_of_tasks,
             max_number_of_batched_tasks: self.max_number_of_batched_tasks,
-            puffin_frame: self.puffin_frame.clone(),
             snapshots_path: self.snapshots_path.clone(),
             dumps_path: self.dumps_path.clone(),
             auth_path: self.auth_path.clone(),
@@ -500,7 +494,6 @@ impl IndexScheduler {
             env,
             // we want to start the loop right away in case meilisearch was ctrl+Ced while processing things
             wake_up: Arc::new(SignalEvent::auto(true)),
-            puffin_frame: Arc::new(puffin::GlobalFrameView::default()),
             autobatching_enabled: options.autobatching_enabled,
             cleanup_enabled: options.cleanup_enabled,
             max_number_of_tasks: options.max_number_of_tasks,
@@ -621,10 +614,6 @@ impl IndexScheduler {
                 run.wake_up.wait();
 
                 loop {
-                    let puffin_enabled = run.features().check_puffin().is_ok();
-                    puffin::set_scopes_on(puffin_enabled);
-                    puffin::GlobalProfiler::lock().new_frame();
-
                     match run.tick() {
                         Ok(TickOutcome::TickAgain(_)) => (),
                         Ok(TickOutcome::WaitForSignal) => run.wake_up.wait(),
@@ -636,31 +625,6 @@ impl IndexScheduler {
                             }
                         }
                     }
-
-                    // Let's write the previous frame to disk but only if
-                    // the user wanted to profile with puffin.
-                    if puffin_enabled {
-                        let mut frame_view = run.puffin_frame.lock();
-                        if !frame_view.is_empty() {
-                            let now = OffsetDateTime::now_utc();
-                            let mut file = match File::create(format!("{}.puffin", now)) {
-                                Ok(file) => file,
-                                Err(e) => {
-                                    tracing::error!("{e}");
-                                    continue;
-                                }
-                            };
-                            if let Err(e) = frame_view.save_to_writer(&mut file) {
-                                tracing::error!("{e}");
-                            }
-                            if let Err(e) = file.sync_all() {
-                                tracing::error!("{e}");
-                            }
-                            // We erase this frame view as it is no more useful. We want to
-                            // measure the new frames now that we exported the previous ones.
-                            *frame_view = FrameView::default();
-                        }
-                    }
                 }
             })
             .unwrap();
@@ -1774,6 +1738,7 @@ mod tests {
     use big_s::S;
     use crossbeam::channel::RecvTimeoutError;
     use file_store::File;
+    use insta::assert_json_snapshot;
     use meili_snap::{json_string, snapshot};
     use meilisearch_auth::AuthFilter;
     use meilisearch_types::document_formats::DocumentFormatError;
@@ -1851,7 +1816,7 @@ mod tests {
 
             // To be 100% consistent between all test we're going to start the scheduler right now
             // and ensure it's in the expected starting state.
-            let breakpoint = match receiver.recv_timeout(std::time::Duration::from_secs(1)) {
+            let breakpoint = match receiver.recv_timeout(std::time::Duration::from_secs(10)) {
                 Ok(b) => b,
                 Err(RecvTimeoutError::Timeout) => {
                     panic!("The scheduler seems to be waiting for a new task while your test is waiting for a breakpoint.")
@@ -1962,7 +1927,7 @@ mod tests {
         fn advance(&mut self) -> Breakpoint {
             let (breakpoint_1, b) = match self
                 .test_breakpoint_rcv
-                .recv_timeout(std::time::Duration::from_secs(5))
+                .recv_timeout(std::time::Duration::from_secs(50))
             {
                 Ok(b) => b,
                 Err(RecvTimeoutError::Timeout) => {
@@ -1983,7 +1948,7 @@ mod tests {
 
             let (breakpoint_2, b) = match self
                 .test_breakpoint_rcv
-                .recv_timeout(std::time::Duration::from_secs(5))
+                .recv_timeout(std::time::Duration::from_secs(50))
             {
                 Ok(b) => b,
                 Err(RecvTimeoutError::Timeout) => {
@@ -4982,4 +4947,233 @@ mod tests {
         ----------------------------------------------------------------------
         "###);
     }
+
+    #[test]
+    fn import_vectors() {
+        use meilisearch_types::settings::{Settings, Unchecked};
+        use milli::update::Setting;
+
+        let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
+
+        let mut new_settings: Box<Settings<Unchecked>> = Box::default();
+        let mut embedders = BTreeMap::default();
+        let embedding_settings = milli::vector::settings::EmbeddingSettings {
+            source: Setting::Set(milli::vector::settings::EmbedderSource::Rest),
+            api_key: Setting::Set(S("My super secret")),
+            url: Setting::Set(S("http://localhost:7777")),
+            dimensions: Setting::Set(384),
+            ..Default::default()
+        };
+        embedders.insert(S("A_fakerest"), Setting::Set(embedding_settings));
+
+        let embedding_settings = milli::vector::settings::EmbeddingSettings {
+            source: Setting::Set(milli::vector::settings::EmbedderSource::HuggingFace),
+            model: Setting::Set(S("sentence-transformers/all-MiniLM-L6-v2")),
+            revision: Setting::Set(S("e4ce9877abf3edfe10b0d82785e83bdcb973e22e")),
+            document_template: Setting::Set(S("{{doc.doggo}} the {{doc.breed}} best doggo")),
+            ..Default::default()
+        };
+        embedders.insert(S("B_small_hf"), Setting::Set(embedding_settings));
+
+        new_settings.embedders = Setting::Set(embedders);
+
+        index_scheduler
+            .register(
+                KindWithContent::SettingsUpdate {
+                    index_uid: S("doggos"),
+                    new_settings,
+                    is_deletion: false,
+                    allow_index_creation: true,
+                },
+                None,
+                false,
+            )
+            .unwrap();
+        index_scheduler.assert_internally_consistent();
+
+        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_registering_settings_task_vectors");
+
+        {
+            let rtxn = index_scheduler.read_txn().unwrap();
+            let task = index_scheduler.get_task(&rtxn, 0).unwrap().unwrap();
+            let task = meilisearch_types::task_view::TaskView::from_task(&task);
+            insta::assert_json_snapshot!(task.details);
+        }
+
+        handle.advance_n_successful_batches(1);
+        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "settings_update_processed_vectors");
+
+        {
+            let rtxn = index_scheduler.read_txn().unwrap();
+            let task = index_scheduler.get_task(&rtxn, 0).unwrap().unwrap();
+            let task = meilisearch_types::task_view::TaskView::from_task(&task);
+            insta::assert_json_snapshot!(task.details);
+        }
+
+        let (fakerest_name, simple_hf_name, beagle_embed, lab_embed, patou_embed) = {
+            let index = index_scheduler.index("doggos").unwrap();
+            let rtxn = index.read_txn().unwrap();
+
+            let configs = index.embedding_configs(&rtxn).unwrap();
+            // for consistency with the below
+            #[allow(clippy::get_first)]
+            let (name, fakerest_config) = configs.get(0).unwrap();
+            insta::assert_json_snapshot!(name, @r###""A_fakerest""###);
+            insta::assert_json_snapshot!(fakerest_config.embedder_options);
+            let fakerest_name = name.clone();
+
+            let (name, simple_hf_config) = configs.get(1).unwrap();
+            insta::assert_json_snapshot!(name, @r###""B_small_hf""###);
+            insta::assert_json_snapshot!(simple_hf_config.embedder_options);
+            let simple_hf_name = name.clone();
+
+            let configs = index_scheduler.embedders(configs).unwrap();
+            let (hf_embedder, _) = configs.get(&simple_hf_name).unwrap();
+            let beagle_embed = hf_embedder.embed_one(S("Intel the beagle best doggo")).unwrap();
+            let lab_embed = hf_embedder.embed_one(S("Max the lab best doggo")).unwrap();
+            let patou_embed = hf_embedder.embed_one(S("kefir the patou best doggo")).unwrap();
+            (fakerest_name, simple_hf_name, beagle_embed, lab_embed, patou_embed)
+        };
+
+        // add one doc, specifying vectors
+
+        let doc = serde_json::json!(
+                    {
+                        "id": 0,
+                        "doggo": "Intel",
+                        "breed": "beagle",
+                        "_vectors": {
+                            &fakerest_name: {
+                                // this will never trigger regeneration, which is good because we can't actually generate with
+                                // this embedder
+                                "userProvided": true,
+                                "embeddings": beagle_embed,
+                            },
+                            &simple_hf_name: {
+                                // this will be regenerated on updates
+                                "userProvided": false,
+                                "embeddings": lab_embed,
+                            },
+                            "noise": [0.1, 0.2, 0.3]
+                        }
+                    }
+        );
+
+        let (uuid, mut file) = index_scheduler.create_update_file_with_uuid(0u128).unwrap();
+        let documents_count = read_json(doc.to_string().as_bytes(), &mut file).unwrap();
+        assert_eq!(documents_count, 1);
+        file.persist().unwrap();
+
+        index_scheduler
+            .register(
+                KindWithContent::DocumentAdditionOrUpdate {
+                    index_uid: S("doggos"),
+                    primary_key: Some(S("id")),
+                    method: UpdateDocuments,
+                    content_file: uuid,
+                    documents_count,
+                    allow_index_creation: true,
+                },
+                None,
+                false,
+            )
+            .unwrap();
+        index_scheduler.assert_internally_consistent();
+
+        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after adding Intel");
+
+        handle.advance_one_successful_batch();
+
+        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "adding Intel succeeds");
+
+        // check embeddings
+        {
+            let index = index_scheduler.index("doggos").unwrap();
+            let rtxn = index.read_txn().unwrap();
+
+            let embeddings = index.embeddings(&rtxn, 0).unwrap();
+
+            assert_json_snapshot!(embeddings[&simple_hf_name][0] == lab_embed, @"true");
+            assert_json_snapshot!(embeddings[&fakerest_name][0] == beagle_embed, @"true");
+
+            let doc = index.documents(&rtxn, std::iter::once(0)).unwrap()[0].1;
+            let fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
+            let doc = obkv_to_json(
+                &[
+                    fields_ids_map.id("doggo").unwrap(),
+                    fields_ids_map.id("breed").unwrap(),
+                    fields_ids_map.id("_vectors").unwrap(),
+                ],
+                &fields_ids_map,
+                doc,
+            )
+            .unwrap();
+            assert_json_snapshot!(doc, {"._vectors.A_fakerest.embeddings" => "[vector]"});
+        }
+
+        // update the doc, specifying vectors
+
+        let doc = serde_json::json!(
+                    {
+                        "id": 0,
+                        "doggo": "kefir",
+                        "breed": "patou",
+                    }
+        );
+
+        let (uuid, mut file) = index_scheduler.create_update_file_with_uuid(1u128).unwrap();
+        let documents_count = read_json(doc.to_string().as_bytes(), &mut file).unwrap();
+        assert_eq!(documents_count, 1);
+        file.persist().unwrap();
+
+        index_scheduler
+            .register(
+                KindWithContent::DocumentAdditionOrUpdate {
+                    index_uid: S("doggos"),
+                    primary_key: None,
+                    method: UpdateDocuments,
+                    content_file: uuid,
+                    documents_count,
+                    allow_index_creation: true,
+                },
+                None,
+                false,
+            )
+            .unwrap();
+        index_scheduler.assert_internally_consistent();
+
+        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "Intel to kefir");
+
+        handle.advance_one_successful_batch();
+        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "Intel to kefir succeeds");
+
+        {
+            // check embeddings
+            {
+                let index = index_scheduler.index("doggos").unwrap();
+                let rtxn = index.read_txn().unwrap();
+
+                let embeddings = index.embeddings(&rtxn, 0).unwrap();
+
+                // automatically changed to patou
+                assert_json_snapshot!(embeddings[&simple_hf_name][0] == patou_embed, @"true");
+                // remained beagle because set to userProvided
+                assert_json_snapshot!(embeddings[&fakerest_name][0] == beagle_embed, @"true");
+
+                let doc = index.documents(&rtxn, std::iter::once(0)).unwrap()[0].1;
+                let fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
+                let doc = obkv_to_json(
+                    &[
+                        fields_ids_map.id("doggo").unwrap(),
+                        fields_ids_map.id("breed").unwrap(),
+                        fields_ids_map.id("_vectors").unwrap(),
+                    ],
+                    &fields_ids_map,
+                    doc,
+                )
+                .unwrap();
+                assert_json_snapshot!(doc, {"._vectors.A_fakerest.embeddings" => "[vector]"});
+            }
+        }
+    }
 }

index-scheduler/src/snapshots/index_scheduler__tests__import_vectors-12.snap

@@ -0,0 +1,19 @@
+---
+source: index-scheduler/src/lib.rs
+expression: doc
+---
+{
+  "doggo": "kefir",
+  "breed": "patou",
+  "_vectors": {
+    "A_fakerest": {
+      "embeddings": "[vector]",
+      "userProvided": true
+    },
+    "noise": [
+      0.1,
+      0.2,
+      0.3
+    ]
+  }
+}

index-scheduler/src/snapshots/index_scheduler__tests__import_vectors-2.snap

@@ -0,0 +1,20 @@
+---
+source: index-scheduler/src/lib.rs
+expression: task.details
+---
+{
+  "embedders": {
+    "A_fakerest": {
+      "source": "rest",
+      "apiKey": "MyXXXX...",
+      "dimensions": 384,
+      "url": "http://localhost:7777"
+    },
+    "B_small_hf": {
+      "source": "huggingFace",
+      "model": "sentence-transformers/all-MiniLM-L6-v2",
+      "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
+      "documentTemplate": "{{doc.doggo}} the {{doc.breed}} best doggo"
+    }
+  }
+}

index-scheduler/src/snapshots/index_scheduler__tests__import_vectors-4.snap

@@ -0,0 +1,23 @@
+---
+source: index-scheduler/src/lib.rs
+expression: fakerest_config.embedder_options
+---
+{
+  "Rest": {
+    "api_key": "My super secret",
+    "distribution": null,
+    "dimensions": 384,
+    "url": "http://localhost:7777",
+    "query": null,
+    "input_field": [
+      "input"
+    ],
+    "path_to_embeddings": [
+      "data"
+    ],
+    "embedding_object": [
+      "embedding"
+    ],
+    "input_type": "text"
+  }
+}

index-scheduler/src/snapshots/index_scheduler__tests__import_vectors-6.snap

@@ -0,0 +1,11 @@
+---
+source: index-scheduler/src/lib.rs
+expression: simple_hf_config.embedder_options
+---
+{
+  "HuggingFace": {
+    "model": "sentence-transformers/all-MiniLM-L6-v2",
+    "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
+    "distribution": null
+  }
+}

index-scheduler/src/snapshots/index_scheduler__tests__import_vectors-9.snap

@@ -0,0 +1,19 @@
+---
+source: index-scheduler/src/lib.rs
+expression: doc
+---
+{
+  "doggo": "Intel",
+  "breed": "beagle",
+  "_vectors": {
+    "A_fakerest": {
+      "embeddings": "[vector]",
+      "userProvided": true
+    },
+    "noise": [
+      0.1,
+      0.2,
+      0.3
+    ]
+  }
+}

index-scheduler/src/snapshots/index_scheduler__tests__import_vectors.snap

@@ -0,0 +1,20 @@
+---
+source: index-scheduler/src/lib.rs
+expression: task.details
+---
+{
+  "embedders": {
+    "A_fakerest": {
+      "source": "rest",
+      "apiKey": "MyXXXX...",
+      "dimensions": 384,
+      "url": "http://localhost:7777"
+    },
+    "B_small_hf": {
+      "source": "huggingFace",
+      "model": "sentence-transformers/all-MiniLM-L6-v2",
+      "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
+      "documentTemplate": "{{doc.doggo}} the {{doc.breed}} best doggo"
+    }
+  }
+}

index-scheduler/src/snapshots/lib.rs/import_vectors/Intel to kefir succeeds.snap

@@ -0,0 +1,49 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
+2 {uid: 2, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
+----------------------------------------------------------------------
+### Status:
+enqueued []
+succeeded [0,1,2,]
+----------------------------------------------------------------------
+### Kind:
+"documentAdditionOrUpdate" [1,2,]
+"settingsUpdate" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,1,2,]
+----------------------------------------------------------------------
+### Index Mapper:
+doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1, "doggo": 1, "id": 1} }
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+[timestamp] [1,]
+[timestamp] [2,]
+----------------------------------------------------------------------
+### Started At:
+[timestamp] [0,]
+[timestamp] [1,]
+[timestamp] [2,]
+----------------------------------------------------------------------
+### Finished At:
+[timestamp] [0,]
+[timestamp] [1,]
+[timestamp] [2,]
+----------------------------------------------------------------------
+### File Store:
+
+----------------------------------------------------------------------
+

index-scheduler/src/snapshots/lib.rs/import_vectors/Intel to kefir.snap

@@ -0,0 +1,48 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
+2 {uid: 2, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
+----------------------------------------------------------------------
+### Status:
+enqueued [2,]
+succeeded [0,1,]
+----------------------------------------------------------------------
+### Kind:
+"documentAdditionOrUpdate" [1,2,]
+"settingsUpdate" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,1,2,]
+----------------------------------------------------------------------
+### Index Mapper:
+doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1, "doggo": 1, "id": 1} }
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+[timestamp] [1,]
+[timestamp] [2,]
+----------------------------------------------------------------------
+### Started At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### Finished At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### File Store:
+00000000-0000-0000-0000-000000000001
+
+----------------------------------------------------------------------
+

index-scheduler/src/snapshots/lib.rs/import_vectors/adding Intel succeeds.snap

@@ -0,0 +1,45 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
+----------------------------------------------------------------------
+### Status:
+enqueued []
+succeeded [0,1,]
+----------------------------------------------------------------------
+### Kind:
+"documentAdditionOrUpdate" [1,]
+"settingsUpdate" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,1,]
+----------------------------------------------------------------------
+### Index Mapper:
+doggos: { number_of_documents: 1, field_distribution: {"_vectors": 1, "breed": 1, "doggo": 1, "id": 1} }
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### Started At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### Finished At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### File Store:
+
+----------------------------------------------------------------------
+

index-scheduler/src/snapshots/lib.rs/import_vectors/after adding Intel.snap

@@ -0,0 +1,44 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+1 {uid: 1, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
+----------------------------------------------------------------------
+### Status:
+enqueued [1,]
+succeeded [0,]
+----------------------------------------------------------------------
+### Kind:
+"documentAdditionOrUpdate" [1,]
+"settingsUpdate" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,1,]
+----------------------------------------------------------------------
+### Index Mapper:
+doggos: { number_of_documents: 0, field_distribution: {} }
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+[timestamp] [1,]
+----------------------------------------------------------------------
+### Started At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### Finished At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### File Store:
+00000000-0000-0000-0000-000000000000
+
+----------------------------------------------------------------------
+

index-scheduler/src/snapshots/lib.rs/import_vectors/after_registering_settings_task_vectors.snap

@@ -0,0 +1,36 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+----------------------------------------------------------------------
+### Status:
+enqueued [0,]
+----------------------------------------------------------------------
+### Kind:
+"settingsUpdate" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,]
+----------------------------------------------------------------------
+### Index Mapper:
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### Started At:
+----------------------------------------------------------------------
+### Finished At:
+----------------------------------------------------------------------
+### File Store:
+
+----------------------------------------------------------------------
+

index-scheduler/src/snapshots/lib.rs/import_vectors/settings_update_processed_vectors.snap

@@ -0,0 +1,40 @@
+---
+source: index-scheduler/src/lib.rs
+---
+### Autobatching Enabled = true
+### Processing Tasks:
+[]
+----------------------------------------------------------------------
+### All Tasks:
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, query: NotSet, input_field: NotSet, path_to_embeddings: NotSet, embedding_object: NotSet, input_type: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+----------------------------------------------------------------------
+### Status:
+enqueued []
+succeeded [0,]
+----------------------------------------------------------------------
+### Kind:
+"settingsUpdate" [0,]
+----------------------------------------------------------------------
+### Index Tasks:
+doggos [0,]
+----------------------------------------------------------------------
+### Index Mapper:
+doggos: { number_of_documents: 0, field_distribution: {} }
+
+----------------------------------------------------------------------
+### Canceled By:
+
+----------------------------------------------------------------------
+### Enqueued At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### Started At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### Finished At:
+[timestamp] [0,]
+----------------------------------------------------------------------
+### File Store:
+
+----------------------------------------------------------------------
+

meilisearch-types/Cargo.toml

@@ -11,7 +11,7 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-actix-web = { version = "4.5.1", default-features = false }
+actix-web = { version = "4.6.0", default-features = false }
 anyhow = "1.0.79"
 convert_case = "0.6.0"
 csv = "1.3.0"
@@ -30,7 +30,12 @@ serde_json = "1.0.111"
 tar = "0.4.40"
 tempfile = "3.9.0"
 thiserror = "1.0.56"
-time = { version = "0.3.31", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+time = { version = "0.3.31", features = [
+    "serde-well-known",
+    "formatting",
+    "parsing",
+    "macros",
+] }
 tokio = "1.35"
 uuid = { version = "1.6.1", features = ["serde", "v4"] }
 

meilisearch-types/src/deserr/mod.rs

@@ -189,3 +189,6 @@ merge_with_error_impl_take_error_message!(ParseTaskKindError);
 merge_with_error_impl_take_error_message!(ParseTaskStatusError);
 merge_with_error_impl_take_error_message!(IndexUidFormatError);
 merge_with_error_impl_take_error_message!(InvalidSearchSemanticRatio);
+merge_with_error_impl_take_error_message!(InvalidSearchRankingScoreThreshold);
+merge_with_error_impl_take_error_message!(InvalidSimilarRankingScoreThreshold);
+merge_with_error_impl_take_error_message!(InvalidSimilarId);

meilisearch-types/src/error.rs

@@ -239,18 +239,25 @@ InvalidIndexUid                       , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchAttributesToSearchOn     , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchAttributesToCrop         , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchAttributesToHighlight    , InvalidRequest       , BAD_REQUEST ;
+InvalidSimilarAttributesToRetrieve    , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchAttributesToRetrieve     , InvalidRequest       , BAD_REQUEST ;
+InvalidSearchRankingScoreThreshold    , InvalidRequest       , BAD_REQUEST ;
+InvalidSimilarRankingScoreThreshold   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchCropLength               , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchCropMarker               , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchFacets                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchSemanticRatio            , InvalidRequest       , BAD_REQUEST ;
 InvalidFacetSearchFacetName           , InvalidRequest       , BAD_REQUEST ;
+InvalidSimilarId                      , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchFilter                   , InvalidRequest       , BAD_REQUEST ;
+InvalidSimilarFilter                  , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchHighlightPostTag         , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchHighlightPreTag          , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchHitsPerPage              , InvalidRequest       , BAD_REQUEST ;
+InvalidSimilarLimit                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchLimit                    , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchMatchingStrategy         , InvalidRequest       , BAD_REQUEST ;
+InvalidSimilarOffset                  , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchOffset                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchPage                     , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchQ                        , InvalidRequest       , BAD_REQUEST ;
@@ -259,7 +266,9 @@ InvalidFacetSearchName                , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchVector                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchShowMatchesPosition      , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchShowRankingScore         , InvalidRequest       , BAD_REQUEST ;
+InvalidSimilarShowRankingScore        , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchShowRankingScoreDetails  , InvalidRequest       , BAD_REQUEST ;
+InvalidSimilarShowRankingScoreDetails , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchSort                     , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDisplayedAttributes    , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDistinctAttribute      , InvalidRequest       , BAD_REQUEST ;
@@ -322,7 +331,8 @@ UnretrievableErrorCode                , InvalidRequest       , BAD_REQUEST ;
 UnsupportedMediaType                  , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE ;
 
 // Experimental features
-VectorEmbeddingError                  , InvalidRequest       , BAD_REQUEST
+VectorEmbeddingError                  , InvalidRequest       , BAD_REQUEST ;
+NotFoundSimilarId                     , InvalidRequest       , BAD_REQUEST
 }
 
 impl ErrorCode for JoinError {
@@ -384,7 +394,6 @@ impl ErrorCode for milli::Error {
                     UserError::InvalidGeoField { .. } => Code::InvalidDocumentGeoField,
                     UserError::InvalidVectorDimensions { .. } => Code::InvalidVectorDimensions,
                     UserError::InvalidVectorsMapType { .. } => Code::InvalidVectorsType,
-                    UserError::InvalidVectorsType { .. } => Code::InvalidVectorsType,
                     UserError::TooManyVectors(_, _) => Code::TooManyVectors,
                     UserError::SortError(_) => Code::InvalidSearchSort,
                     UserError::InvalidMinTypoWordLenSetting(_, _) => {
@@ -487,6 +496,32 @@ impl fmt::Display for deserr_codes::InvalidSearchSemanticRatio {
     }
 }
 
+impl fmt::Display for deserr_codes::InvalidSimilarId {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        write!(
+            f,
+            "the value of `id` is invalid. \
+            A document identifier can be of type integer or string, \
+            only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_)."
+        )
+    }
+}
+
+impl fmt::Display for deserr_codes::InvalidSearchRankingScoreThreshold {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        write!(
+            f,
+            "the value of `rankingScoreThreshold` is invalid, expected a float between `0.0` and `1.0`."
+        )
+    }
+}
+
+impl fmt::Display for deserr_codes::InvalidSimilarRankingScoreThreshold {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        deserr_codes::InvalidSearchRankingScoreThreshold.fmt(f)
+    }
+}
+
 #[macro_export]
 macro_rules! internal_error {
     ($target:ty : $($other:path), *) => {

meilisearch-types/src/features.rs

@@ -6,7 +6,6 @@ pub struct RuntimeTogglableFeatures {
     pub vector_store: bool,
     pub metrics: bool,
     pub logs_route: bool,
-    pub export_puffin_reports: bool,
 }
 
 #[derive(Default, Debug, Clone, Copy)]

meilisearch/Cargo.toml

@@ -14,20 +14,20 @@ default-run = "meilisearch"
 
 [dependencies]
 actix-cors = "0.7.0"
-actix-http = { version = "3.6.0", default-features = false, features = [
+actix-http = { version = "3.7.0", default-features = false, features = [
     "compress-brotli",
     "compress-gzip",
     "rustls-0_21",
 ] }
 actix-utils = "3.0.1"
-actix-web = { version = "4.5.1", default-features = false, features = [
+actix-web = { version = "4.6.0", default-features = false, features = [
     "macros",
     "compress-brotli",
     "compress-gzip",
     "cookies",
     "rustls-0_21",
 ] }
-actix-web-static-files = { git = "https://github.com/kilork/actix-web-static-files.git", rev = "2d3b6160", optional = true }
+actix-web-static-files = { version = "4.0.1", optional = true }
 anyhow = { version = "1.0.79", features = ["backtrace"] }
 async-stream = "0.3.5"
 async-trait = "0.1.77"
@@ -67,7 +67,6 @@ permissive-json-pointer = { path = "../permissive-json-pointer" }
 pin-project-lite = "0.2.13"
 platform-dirs = "0.3.0"
 prometheus = { version = "0.13.3", features = ["process"] }
-puffin = { version = "0.16.0", features = ["serialization"] }
 rand = "0.8.5"
 rayon = "1.8.0"
 regex = "1.10.2"
@@ -106,13 +105,13 @@ url = { version = "2.5.0", features = ["serde"] }
 tracing = "0.1.40"
 tracing-subscriber = { version = "0.3.18", features = ["json"] }
 tracing-trace = { version = "0.1.0", path = "../tracing-trace" }
-tracing-actix-web = "0.7.9"
+tracing-actix-web = "0.7.10"
 build-info = { version = "1.7.0", path = "../build-info" }
 
 [dev-dependencies]
 actix-rt = "2.9.0"
 assert-json-diff = "2.0.2"
-brotli = "3.4.0"
+brotli = "6.0.0"
 insta = "1.34.0"
 manifest-dir-macros = "0.1.18"
 maplit = "1.0.2"
@@ -132,7 +131,7 @@ reqwest = { version = "0.11.23", features = [
 sha-1 = { version = "0.10.1", optional = true }
 static-files = { version = "0.2.3", optional = true }
 tempfile = { version = "3.9.0", optional = true }
-zip = { version = "1.3.1", features = ["deflate"], default-features = false, optional = true }
+zip = { version = "0.6.6", optional = true }
 
 [features]
 default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]

meilisearch/src/analytics/mock_analytics.rs

@@ -25,6 +25,18 @@ impl SearchAggregator {
     pub fn succeed(&mut self, _: &dyn Any) {}
 }
 
+#[derive(Default)]
+pub struct SimilarAggregator;
+
+#[allow(dead_code)]
+impl SimilarAggregator {
+    pub fn from_query(_: &dyn Any, _: &dyn Any) -> Self {
+        Self
+    }
+
+    pub fn succeed(&mut self, _: &dyn Any) {}
+}
+
 #[derive(Default)]
 pub struct MultiSearchAggregator;
 
@@ -66,6 +78,8 @@ impl Analytics for MockAnalytics {
     fn publish(&self, _event_name: String, _send: Value, _request: Option<&HttpRequest>) {}
     fn get_search(&self, _aggregate: super::SearchAggregator) {}
     fn post_search(&self, _aggregate: super::SearchAggregator) {}
+    fn get_similar(&self, _aggregate: super::SimilarAggregator) {}
+    fn post_similar(&self, _aggregate: super::SimilarAggregator) {}
     fn post_multi_search(&self, _aggregate: super::MultiSearchAggregator) {}
     fn post_facet_search(&self, _aggregate: super::FacetSearchAggregator) {}
     fn add_documents(

meilisearch/src/analytics/mod.rs

@@ -22,6 +22,8 @@ pub type SegmentAnalytics = mock_analytics::MockAnalytics;
 #[cfg(not(feature = "analytics"))]
 pub type SearchAggregator = mock_analytics::SearchAggregator;
 #[cfg(not(feature = "analytics"))]
+pub type SimilarAggregator = mock_analytics::SimilarAggregator;
+#[cfg(not(feature = "analytics"))]
 pub type MultiSearchAggregator = mock_analytics::MultiSearchAggregator;
 #[cfg(not(feature = "analytics"))]
 pub type FacetSearchAggregator = mock_analytics::FacetSearchAggregator;
@@ -32,6 +34,8 @@ pub type SegmentAnalytics = segment_analytics::SegmentAnalytics;
 #[cfg(feature = "analytics")]
 pub type SearchAggregator = segment_analytics::SearchAggregator;
 #[cfg(feature = "analytics")]
+pub type SimilarAggregator = segment_analytics::SimilarAggregator;
+#[cfg(feature = "analytics")]
 pub type MultiSearchAggregator = segment_analytics::MultiSearchAggregator;
 #[cfg(feature = "analytics")]
 pub type FacetSearchAggregator = segment_analytics::FacetSearchAggregator;
@@ -86,6 +90,12 @@ pub trait Analytics: Sync + Send {
     /// This method should be called to aggregate a post search
     fn post_search(&self, aggregate: SearchAggregator);
 
+    /// This method should be called to aggregate a get similar request
+    fn get_similar(&self, aggregate: SimilarAggregator);
+
+    /// This method should be called to aggregate a post similar request
+    fn post_similar(&self, aggregate: SimilarAggregator);
+
     /// This method should be called to aggregate a post array of searches
     fn post_multi_search(&self, aggregate: MultiSearchAggregator);
 

meilisearch/src/analytics/segment_analytics.rs

@@ -36,8 +36,9 @@ use crate::routes::indexes::facet_search::FacetSearchQuery;
 use crate::routes::{create_all_stats, Stats};
 use crate::search::{
     FacetSearchResult, MatchingStrategy, SearchQuery, SearchQueryWithIndex, SearchResult,
-    DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
-    DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEMANTIC_RATIO,
+    SimilarQuery, SimilarResult, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
+    DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
+    DEFAULT_SEMANTIC_RATIO,
 };
 use crate::Opt;
 
@@ -73,6 +74,8 @@ pub enum AnalyticsMsg {
     BatchMessage(Track),
     AggregateGetSearch(SearchAggregator),
     AggregatePostSearch(SearchAggregator),
+    AggregateGetSimilar(SimilarAggregator),
+    AggregatePostSimilar(SimilarAggregator),
     AggregatePostMultiSearch(MultiSearchAggregator),
     AggregatePostFacetSearch(FacetSearchAggregator),
     AggregateAddDocuments(DocumentsAggregator),
@@ -149,6 +152,8 @@ impl SegmentAnalytics {
             update_documents_aggregator: DocumentsAggregator::default(),
             get_fetch_documents_aggregator: DocumentsFetchAggregator::default(),
             post_fetch_documents_aggregator: DocumentsFetchAggregator::default(),
+            get_similar_aggregator: SimilarAggregator::default(),
+            post_similar_aggregator: SimilarAggregator::default(),
         });
         tokio::spawn(segment.run(index_scheduler.clone(), auth_controller.clone()));
 
@@ -184,6 +189,14 @@ impl super::Analytics for SegmentAnalytics {
         let _ = self.sender.try_send(AnalyticsMsg::AggregatePostSearch(aggregate));
     }
 
+    fn get_similar(&self, aggregate: SimilarAggregator) {
+        let _ = self.sender.try_send(AnalyticsMsg::AggregateGetSimilar(aggregate));
+    }
+
+    fn post_similar(&self, aggregate: SimilarAggregator) {
+        let _ = self.sender.try_send(AnalyticsMsg::AggregatePostSimilar(aggregate));
+    }
+
     fn post_facet_search(&self, aggregate: FacetSearchAggregator) {
         let _ = self.sender.try_send(AnalyticsMsg::AggregatePostFacetSearch(aggregate));
     }
@@ -379,6 +392,8 @@ pub struct Segment {
     update_documents_aggregator: DocumentsAggregator,
     get_fetch_documents_aggregator: DocumentsFetchAggregator,
     post_fetch_documents_aggregator: DocumentsFetchAggregator,
+    get_similar_aggregator: SimilarAggregator,
+    post_similar_aggregator: SimilarAggregator,
 }
 
 impl Segment {
@@ -441,6 +456,8 @@ impl Segment {
                         Some(AnalyticsMsg::AggregateUpdateDocuments(agreg)) => self.update_documents_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregateGetFetchDocuments(agreg)) => self.get_fetch_documents_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregatePostFetchDocuments(agreg)) => self.post_fetch_documents_aggregator.aggregate(agreg),
+                        Some(AnalyticsMsg::AggregateGetSimilar(agreg)) => self.get_similar_aggregator.aggregate(agreg),
+                        Some(AnalyticsMsg::AggregatePostSimilar(agreg)) => self.post_similar_aggregator.aggregate(agreg),
                         None => (),
                     }
                 }
@@ -494,6 +511,8 @@ impl Segment {
             update_documents_aggregator,
             get_fetch_documents_aggregator,
             post_fetch_documents_aggregator,
+            get_similar_aggregator,
+            post_similar_aggregator,
         } = self;
 
         if let Some(get_search) =
@@ -541,6 +560,18 @@ impl Segment {
         {
             let _ = self.batcher.push(post_fetch_documents).await;
         }
+
+        if let Some(get_similar_documents) =
+            take(get_similar_aggregator).into_event(user, "Similar GET")
+        {
+            let _ = self.batcher.push(get_similar_documents).await;
+        }
+
+        if let Some(post_similar_documents) =
+            take(post_similar_aggregator).into_event(user, "Similar POST")
+        {
+            let _ = self.batcher.push(post_similar_documents).await;
+        }
         let _ = self.batcher.flush().await;
     }
 }
@@ -617,6 +648,7 @@ pub struct SearchAggregator {
     // scoring
     show_ranking_score: bool,
     show_ranking_score_details: bool,
+    ranking_score_threshold: bool,
 }
 
 impl SearchAggregator {
@@ -645,6 +677,7 @@ impl SearchAggregator {
             matching_strategy,
             attributes_to_search_on,
             hybrid,
+            ranking_score_threshold,
         } = query;
 
         let mut ret = Self::default();
@@ -717,6 +750,7 @@ impl SearchAggregator {
 
         ret.show_ranking_score = *show_ranking_score;
         ret.show_ranking_score_details = *show_ranking_score_details;
+        ret.ranking_score_threshold = ranking_score_threshold.is_some();
 
         if let Some(hybrid) = hybrid {
             ret.semantic_ratio = hybrid.semantic_ratio != DEFAULT_SEMANTIC_RATIO();
@@ -790,6 +824,7 @@ impl SearchAggregator {
             hybrid,
             total_degraded,
             total_used_negative_operator,
+            ranking_score_threshold,
         } = other;
 
         if self.timestamp.is_none() {
@@ -873,6 +908,7 @@ impl SearchAggregator {
         // scoring
         self.show_ranking_score |= show_ranking_score;
         self.show_ranking_score_details |= show_ranking_score_details;
+        self.ranking_score_threshold |= ranking_score_threshold;
     }
 
     pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
@@ -914,6 +950,7 @@ impl SearchAggregator {
             hybrid,
             total_degraded,
             total_used_negative_operator,
+            ranking_score_threshold,
         } = self;
 
         if total_received == 0 {
@@ -984,6 +1021,7 @@ impl SearchAggregator {
                 "scoring": {
                     "show_ranking_score": show_ranking_score,
                     "show_ranking_score_details": show_ranking_score_details,
+                    "ranking_score_threshold": ranking_score_threshold,
                 },
             });
 
@@ -1056,6 +1094,7 @@ impl MultiSearchAggregator {
                     matching_strategy: _,
                     attributes_to_search_on: _,
                     hybrid: _,
+                    ranking_score_threshold: _,
                 } = query;
 
                 index_uid.as_str()
@@ -1203,6 +1242,7 @@ impl FacetSearchAggregator {
             matching_strategy,
             attributes_to_search_on,
             hybrid,
+            ranking_score_threshold,
         } = query;
 
         let mut ret = Self::default();
@@ -1217,7 +1257,8 @@ impl FacetSearchAggregator {
             || filter.is_some()
             || *matching_strategy != MatchingStrategy::default()
             || attributes_to_search_on.is_some()
-            || hybrid.is_some();
+            || hybrid.is_some()
+            || ranking_score_threshold.is_some();
 
         ret
     }
@@ -1558,3 +1599,242 @@ impl DocumentsFetchAggregator {
         })
     }
 }
+
+#[derive(Default)]
+pub struct SimilarAggregator {
+    timestamp: Option<OffsetDateTime>,
+
+    // context
+    user_agents: HashSet<String>,
+
+    // requests
+    total_received: usize,
+    total_succeeded: usize,
+    time_spent: BinaryHeap<usize>,
+
+    // filter
+    filter_with_geo_radius: bool,
+    filter_with_geo_bounding_box: bool,
+    // every time a request has a filter, this field must be incremented by the number of terms it contains
+    filter_sum_of_criteria_terms: usize,
+    // every time a request has a filter, this field must be incremented by one
+    filter_total_number_of_criteria: usize,
+    used_syntax: HashMap<String, usize>,
+
+    // Whether a non-default embedder was specified
+    embedder: bool,
+
+    // pagination
+    max_limit: usize,
+    max_offset: usize,
+
+    // formatting
+    max_attributes_to_retrieve: usize,
+
+    // scoring
+    show_ranking_score: bool,
+    show_ranking_score_details: bool,
+    ranking_score_threshold: bool,
+}
+
+impl SimilarAggregator {
+    #[allow(clippy::field_reassign_with_default)]
+    pub fn from_query(query: &SimilarQuery, request: &HttpRequest) -> Self {
+        let SimilarQuery {
+            id: _,
+            embedder,
+            offset,
+            limit,
+            attributes_to_retrieve: _,
+            show_ranking_score,
+            show_ranking_score_details,
+            filter,
+            ranking_score_threshold,
+        } = query;
+
+        let mut ret = Self::default();
+        ret.timestamp = Some(OffsetDateTime::now_utc());
+
+        ret.total_received = 1;
+        ret.user_agents = extract_user_agents(request).into_iter().collect();
+
+        if let Some(ref filter) = filter {
+            static RE: Lazy<Regex> = Lazy::new(|| Regex::new("AND | OR").unwrap());
+            ret.filter_total_number_of_criteria = 1;
+
+            let syntax = match filter {
+                Value::String(_) => "string".to_string(),
+                Value::Array(values) => {
+                    if values.iter().map(|v| v.to_string()).any(|s| RE.is_match(&s)) {
+                        "mixed".to_string()
+                    } else {
+                        "array".to_string()
+                    }
+                }
+                _ => "none".to_string(),
+            };
+            // convert the string to a HashMap
+            ret.used_syntax.insert(syntax, 1);
+
+            let stringified_filters = filter.to_string();
+            ret.filter_with_geo_radius = stringified_filters.contains("_geoRadius(");
+            ret.filter_with_geo_bounding_box = stringified_filters.contains("_geoBoundingBox(");
+            ret.filter_sum_of_criteria_terms = RE.split(&stringified_filters).count();
+        }
+
+        ret.max_limit = *limit;
+        ret.max_offset = *offset;
+
+        ret.show_ranking_score = *show_ranking_score;
+        ret.show_ranking_score_details = *show_ranking_score_details;
+        ret.ranking_score_threshold = ranking_score_threshold.is_some();
+
+        ret.embedder = embedder.is_some();
+
+        ret
+    }
+
+    pub fn succeed(&mut self, result: &SimilarResult) {
+        let SimilarResult { id: _, hits: _, processing_time_ms, hits_info: _ } = result;
+
+        self.total_succeeded = self.total_succeeded.saturating_add(1);
+
+        self.time_spent.push(*processing_time_ms as usize);
+    }
+
+    /// Aggregate one [SimilarAggregator] into another.
+    pub fn aggregate(&mut self, mut other: Self) {
+        let Self {
+            timestamp,
+            user_agents,
+            total_received,
+            total_succeeded,
+            ref mut time_spent,
+            filter_with_geo_radius,
+            filter_with_geo_bounding_box,
+            filter_sum_of_criteria_terms,
+            filter_total_number_of_criteria,
+            used_syntax,
+            max_limit,
+            max_offset,
+            max_attributes_to_retrieve,
+            show_ranking_score,
+            show_ranking_score_details,
+            embedder,
+            ranking_score_threshold,
+        } = other;
+
+        if self.timestamp.is_none() {
+            self.timestamp = timestamp;
+        }
+
+        // context
+        for user_agent in user_agents.into_iter() {
+            self.user_agents.insert(user_agent);
+        }
+
+        // request
+        self.total_received = self.total_received.saturating_add(total_received);
+        self.total_succeeded = self.total_succeeded.saturating_add(total_succeeded);
+        self.time_spent.append(time_spent);
+
+        // filter
+        self.filter_with_geo_radius |= filter_with_geo_radius;
+        self.filter_with_geo_bounding_box |= filter_with_geo_bounding_box;
+        self.filter_sum_of_criteria_terms =
+            self.filter_sum_of_criteria_terms.saturating_add(filter_sum_of_criteria_terms);
+        self.filter_total_number_of_criteria =
+            self.filter_total_number_of_criteria.saturating_add(filter_total_number_of_criteria);
+        for (key, value) in used_syntax.into_iter() {
+            let used_syntax = self.used_syntax.entry(key).or_insert(0);
+            *used_syntax = used_syntax.saturating_add(value);
+        }
+
+        self.embedder |= embedder;
+
+        // pagination
+        self.max_limit = self.max_limit.max(max_limit);
+        self.max_offset = self.max_offset.max(max_offset);
+
+        // formatting
+        self.max_attributes_to_retrieve =
+            self.max_attributes_to_retrieve.max(max_attributes_to_retrieve);
+
+        // scoring
+        self.show_ranking_score |= show_ranking_score;
+        self.show_ranking_score_details |= show_ranking_score_details;
+        self.ranking_score_threshold |= ranking_score_threshold;
+    }
+
+    pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
+        let Self {
+            timestamp,
+            user_agents,
+            total_received,
+            total_succeeded,
+            time_spent,
+            filter_with_geo_radius,
+            filter_with_geo_bounding_box,
+            filter_sum_of_criteria_terms,
+            filter_total_number_of_criteria,
+            used_syntax,
+            max_limit,
+            max_offset,
+            max_attributes_to_retrieve,
+            show_ranking_score,
+            show_ranking_score_details,
+            embedder,
+            ranking_score_threshold,
+        } = self;
+
+        if total_received == 0 {
+            None
+        } else {
+            // we get all the values in a sorted manner
+            let time_spent = time_spent.into_sorted_vec();
+            // the index of the 99th percentage of value
+            let percentile_99th = time_spent.len() * 99 / 100;
+            // We are only interested by the slowest value of the 99th fastest results
+            let time_spent = time_spent.get(percentile_99th);
+
+            let properties = json!({
+                "user-agent": user_agents,
+                "requests": {
+                    "99th_response_time": time_spent.map(|t| format!("{:.2}", t)),
+                    "total_succeeded": total_succeeded,
+                    "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
+                    "total_received": total_received,
+                },
+                "filter": {
+                   "with_geoRadius": filter_with_geo_radius,
+                   "with_geoBoundingBox": filter_with_geo_bounding_box,
+                   "avg_criteria_number": format!("{:.2}", filter_sum_of_criteria_terms as f64 / filter_total_number_of_criteria as f64),
+                   "most_used_syntax": used_syntax.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
+                },
+                "hybrid": {
+                    "embedder": embedder,
+                },
+                "pagination": {
+                   "max_limit": max_limit,
+                   "max_offset": max_offset,
+                },
+                "formatting": {
+                    "max_attributes_to_retrieve": max_attributes_to_retrieve,
+                },
+                "scoring": {
+                    "show_ranking_score": show_ranking_score,
+                    "show_ranking_score_details": show_ranking_score_details,
+                    "ranking_score_threshold": ranking_score_threshold,
+                },
+            });
+
+            Some(Track {
+                timestamp,
+                user: user.clone(),
+                event: event_name.to_string(),
+                properties,
+                ..Default::default()
+            })
+        }
+    }
+}

meilisearch/src/routes/features.rs

@@ -47,8 +47,6 @@ pub struct RuntimeTogglableFeatures {
     pub metrics: Option<bool>,
     #[deserr(default)]
     pub logs_route: Option<bool>,
-    #[deserr(default)]
-    pub export_puffin_reports: Option<bool>,
 }
 
 async fn patch_features(
@@ -68,21 +66,13 @@ async fn patch_features(
         vector_store: new_features.0.vector_store.unwrap_or(old_features.vector_store),
         metrics: new_features.0.metrics.unwrap_or(old_features.metrics),
         logs_route: new_features.0.logs_route.unwrap_or(old_features.logs_route),
-        export_puffin_reports: new_features
-            .0
-            .export_puffin_reports
-            .unwrap_or(old_features.export_puffin_reports),
     };
 
     // explicitly destructure for analytics rather than using the `Serialize` implementation, because
     // the it renames to camelCase, which we don't want for analytics.
     // **Do not** ignore fields with `..` or `_` here, because we want to add them in the future.
-    let meilisearch_types::features::RuntimeTogglableFeatures {
-        vector_store,
-        metrics,
-        logs_route,
-        export_puffin_reports,
-    } = new_features;
+    let meilisearch_types::features::RuntimeTogglableFeatures { vector_store, metrics, logs_route } =
+        new_features;
 
     analytics.publish(
         "Experimental features Updated".to_string(),
@@ -90,7 +80,6 @@ async fn patch_features(
             "vector_store": vector_store,
             "metrics": metrics,
             "logs_route": logs_route,
-            "export_puffin_reports": export_puffin_reports,
         }),
         Some(&req),
     );

meilisearch/src/routes/indexes/facet_search.rs

@@ -14,8 +14,8 @@ use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
 use crate::routes::indexes::search::search_kind;
 use crate::search::{
-    add_search_rules, perform_facet_search, HybridQuery, MatchingStrategy, SearchQuery,
-    DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
+    add_search_rules, perform_facet_search, HybridQuery, MatchingStrategy, RankingScoreThreshold,
+    SearchQuery, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
     DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
 };
 use crate::search_queue::SearchQueue;
@@ -46,6 +46,8 @@ pub struct FacetSearchQuery {
     pub matching_strategy: MatchingStrategy,
     #[deserr(default, error = DeserrJsonError<InvalidSearchAttributesToSearchOn>, default)]
     pub attributes_to_search_on: Option<Vec<String>>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchRankingScoreThreshold>, default)]
+    pub ranking_score_threshold: Option<RankingScoreThreshold>,
 }
 
 pub async fn search(
@@ -69,7 +71,7 @@ pub async fn search(
 
     // Tenant token search_rules.
     if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
-        add_search_rules(&mut search_query, search_rules);
+        add_search_rules(&mut search_query.filter, search_rules);
     }
 
     let index = index_scheduler.index(&index_uid)?;
@@ -103,6 +105,7 @@ impl From<FacetSearchQuery> for SearchQuery {
             matching_strategy,
             attributes_to_search_on,
             hybrid,
+            ranking_score_threshold,
         } = value;
 
         SearchQuery {
@@ -128,6 +131,7 @@ impl From<FacetSearchQuery> for SearchQuery {
             vector,
             attributes_to_search_on,
             hybrid,
+            ranking_score_threshold,
         }
     }
 }

meilisearch/src/routes/indexes/mod.rs

@@ -29,6 +29,7 @@ pub mod documents;
 pub mod facet_search;
 pub mod search;
 pub mod settings;
+pub mod similar;
 
 pub fn configure(cfg: &mut web::ServiceConfig) {
     cfg.service(
@@ -48,6 +49,7 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
             .service(web::scope("/documents").configure(documents::configure))
             .service(web::scope("/search").configure(search::configure))
             .service(web::scope("/facet-search").configure(facet_search::configure))
+            .service(web::scope("/similar").configure(similar::configure))
             .service(web::scope("/settings").configure(settings::configure)),
     );
 }

meilisearch/src/routes/indexes/search.rs

@@ -19,9 +19,10 @@ use crate::extractors::authentication::GuardedData;
 use crate::extractors::sequential_extractor::SeqHandler;
 use crate::metrics::MEILISEARCH_DEGRADED_SEARCH_REQUESTS;
 use crate::search::{
-    add_search_rules, perform_search, HybridQuery, MatchingStrategy, SearchKind, SearchQuery,
-    SemanticRatio, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
-    DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET, DEFAULT_SEMANTIC_RATIO,
+    add_search_rules, perform_search, HybridQuery, MatchingStrategy, RankingScoreThreshold,
+    SearchKind, SearchQuery, SemanticRatio, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
+    DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
+    DEFAULT_SEARCH_OFFSET, DEFAULT_SEMANTIC_RATIO,
 };
 use crate::search_queue::SearchQueue;
 
@@ -82,6 +83,21 @@ pub struct SearchQueryGet {
     pub hybrid_embedder: Option<String>,
     #[deserr(default, error = DeserrQueryParamError<InvalidSearchSemanticRatio>)]
     pub hybrid_semantic_ratio: Option<SemanticRatioGet>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchRankingScoreThreshold>)]
+    pub ranking_score_threshold: Option<RankingScoreThresholdGet>,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, deserr::Deserr)]
+#[deserr(try_from(String) = TryFrom::try_from -> InvalidSearchRankingScoreThreshold)]
+pub struct RankingScoreThresholdGet(RankingScoreThreshold);
+
+impl std::convert::TryFrom<String> for RankingScoreThresholdGet {
+    type Error = InvalidSearchRankingScoreThreshold;
+
+    fn try_from(s: String) -> Result<Self, Self::Error> {
+        let f: f64 = s.parse().map_err(|_| InvalidSearchRankingScoreThreshold)?;
+        Ok(RankingScoreThresholdGet(RankingScoreThreshold::try_from(f)?))
+    }
 }
 
 #[derive(Debug, Clone, Copy, Default, PartialEq, deserr::Deserr)]
@@ -152,6 +168,7 @@ impl From<SearchQueryGet> for SearchQuery {
             matching_strategy: other.matching_strategy,
             attributes_to_search_on: other.attributes_to_search_on.map(|o| o.into_iter().collect()),
             hybrid,
+            ranking_score_threshold: other.ranking_score_threshold.map(|o| o.0),
         }
     }
 }
@@ -196,7 +213,7 @@ pub async fn search_with_url_query(
 
     // Tenant token search_rules.
     if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
-        add_search_rules(&mut query, search_rules);
+        add_search_rules(&mut query.filter, search_rules);
     }
 
     let mut aggregate = SearchAggregator::from_query(&query, &req);
@@ -235,7 +252,7 @@ pub async fn search_with_post(
 
     // Tenant token search_rules.
     if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
-        add_search_rules(&mut query, search_rules);
+        add_search_rules(&mut query.filter, search_rules);
     }
 
     let mut aggregate = SearchAggregator::from_query(&query, &req);

meilisearch/src/routes/indexes/similar.rs

@@ -0,0 +1,188 @@
+use actix_web::web::{self, Data};
+use actix_web::{HttpRequest, HttpResponse};
+use deserr::actix_web::{AwebJson, AwebQueryParameter};
+use index_scheduler::IndexScheduler;
+use meilisearch_types::deserr::query_params::Param;
+use meilisearch_types::deserr::{DeserrJsonError, DeserrQueryParamError};
+use meilisearch_types::error::deserr_codes::{
+    InvalidEmbedder, InvalidSimilarAttributesToRetrieve, InvalidSimilarFilter, InvalidSimilarId,
+    InvalidSimilarLimit, InvalidSimilarOffset, InvalidSimilarRankingScoreThreshold,
+    InvalidSimilarShowRankingScore, InvalidSimilarShowRankingScoreDetails,
+};
+use meilisearch_types::error::{ErrorCode as _, ResponseError};
+use meilisearch_types::index_uid::IndexUid;
+use meilisearch_types::keys::actions;
+use meilisearch_types::serde_cs::vec::CS;
+use serde_json::Value;
+use tracing::debug;
+
+use super::ActionPolicy;
+use crate::analytics::{Analytics, SimilarAggregator};
+use crate::extractors::authentication::GuardedData;
+use crate::extractors::sequential_extractor::SeqHandler;
+use crate::search::{
+    add_search_rules, perform_similar, RankingScoreThresholdSimilar, SearchKind, SimilarQuery,
+    SimilarResult, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
+};
+
+pub fn configure(cfg: &mut web::ServiceConfig) {
+    cfg.service(
+        web::resource("")
+            .route(web::get().to(SeqHandler(similar_get)))
+            .route(web::post().to(SeqHandler(similar_post))),
+    );
+}
+
+pub async fn similar_get(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
+    index_uid: web::Path<String>,
+    params: AwebQueryParameter<SimilarQueryGet, DeserrQueryParamError>,
+    req: HttpRequest,
+    analytics: web::Data<dyn Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+
+    let query = params.0.try_into()?;
+
+    let mut aggregate = SimilarAggregator::from_query(&query, &req);
+
+    debug!(parameters = ?query, "Similar get");
+
+    let similar = similar(index_scheduler, index_uid, query).await;
+
+    if let Ok(similar) = &similar {
+        aggregate.succeed(similar);
+    }
+    analytics.get_similar(aggregate);
+
+    let similar = similar?;
+
+    debug!(returns = ?similar, "Similar get");
+    Ok(HttpResponse::Ok().json(similar))
+}
+
+pub async fn similar_post(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
+    index_uid: web::Path<String>,
+    params: AwebJson<SimilarQuery, DeserrJsonError>,
+    req: HttpRequest,
+    analytics: web::Data<dyn Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+
+    let query = params.into_inner();
+    debug!(parameters = ?query, "Similar post");
+
+    let mut aggregate = SimilarAggregator::from_query(&query, &req);
+
+    let similar = similar(index_scheduler, index_uid, query).await;
+
+    if let Ok(similar) = &similar {
+        aggregate.succeed(similar);
+    }
+    analytics.post_similar(aggregate);
+
+    let similar = similar?;
+
+    debug!(returns = ?similar, "Similar post");
+    Ok(HttpResponse::Ok().json(similar))
+}
+
+async fn similar(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
+    index_uid: IndexUid,
+    mut query: SimilarQuery,
+) -> Result<SimilarResult, ResponseError> {
+    let features = index_scheduler.features();
+
+    features.check_vector("Using the similar API")?;
+
+    // Tenant token search_rules.
+    if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
+        add_search_rules(&mut query.filter, search_rules);
+    }
+
+    let index = index_scheduler.index(&index_uid)?;
+
+    let (embedder_name, embedder) =
+        SearchKind::embedder(&index_scheduler, &index, query.embedder.as_deref(), None)?;
+
+    tokio::task::spawn_blocking(move || perform_similar(&index, query, embedder_name, embedder))
+        .await?
+}
+
+#[derive(Debug, deserr::Deserr)]
+#[deserr(error = DeserrQueryParamError, rename_all = camelCase, deny_unknown_fields)]
+pub struct SimilarQueryGet {
+    #[deserr(error = DeserrQueryParamError<InvalidSimilarId>)]
+    id: Param<String>,
+    #[deserr(default = Param(DEFAULT_SEARCH_OFFSET()), error = DeserrQueryParamError<InvalidSimilarOffset>)]
+    offset: Param<usize>,
+    #[deserr(default = Param(DEFAULT_SEARCH_LIMIT()), error = DeserrQueryParamError<InvalidSimilarLimit>)]
+    limit: Param<usize>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSimilarAttributesToRetrieve>)]
+    attributes_to_retrieve: Option<CS<String>>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSimilarFilter>)]
+    filter: Option<String>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSimilarShowRankingScore>)]
+    show_ranking_score: Param<bool>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSimilarShowRankingScoreDetails>)]
+    show_ranking_score_details: Param<bool>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSimilarRankingScoreThreshold>, default)]
+    pub ranking_score_threshold: Option<RankingScoreThresholdGet>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidEmbedder>)]
+    pub embedder: Option<String>,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, deserr::Deserr)]
+#[deserr(try_from(String) = TryFrom::try_from -> InvalidSimilarRankingScoreThreshold)]
+pub struct RankingScoreThresholdGet(RankingScoreThresholdSimilar);
+
+impl std::convert::TryFrom<String> for RankingScoreThresholdGet {
+    type Error = InvalidSimilarRankingScoreThreshold;
+
+    fn try_from(s: String) -> Result<Self, Self::Error> {
+        let f: f64 = s.parse().map_err(|_| InvalidSimilarRankingScoreThreshold)?;
+        Ok(RankingScoreThresholdGet(RankingScoreThresholdSimilar::try_from(f)?))
+    }
+}
+
+impl TryFrom<SimilarQueryGet> for SimilarQuery {
+    type Error = ResponseError;
+
+    fn try_from(
+        SimilarQueryGet {
+            id,
+            offset,
+            limit,
+            attributes_to_retrieve,
+            filter,
+            show_ranking_score,
+            show_ranking_score_details,
+            embedder,
+            ranking_score_threshold,
+        }: SimilarQueryGet,
+    ) -> Result<Self, Self::Error> {
+        let filter = match filter {
+            Some(f) => match serde_json::from_str(&f) {
+                Ok(v) => Some(v),
+                _ => Some(Value::String(f)),
+            },
+            None => None,
+        };
+
+        Ok(SimilarQuery {
+            id: id.0.try_into().map_err(|code: InvalidSimilarId| {
+                ResponseError::from_msg(code.to_string(), code.error_code())
+            })?,
+            offset: offset.0,
+            limit: limit.0,
+            filter,
+            embedder,
+            attributes_to_retrieve: attributes_to_retrieve.map(|o| o.into_iter().collect()),
+            show_ranking_score: show_ranking_score.0,
+            show_ranking_score_details: show_ranking_score_details.0,
+            ranking_score_threshold: ranking_score_threshold.map(|x| x.0),
+        })
+    }
+}

meilisearch/src/routes/multi_search.rs

@@ -67,7 +67,7 @@ pub async fn multi_search_with_post(
             // Apply search rules from tenant token
             if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid)
             {
-                add_search_rules(&mut query, search_rules);
+                add_search_rules(&mut query.filter, search_rules);
             }
 
             let index = index_scheduler

meilisearch/src/search.rs

@@ -11,7 +11,7 @@ use indexmap::IndexMap;
 use meilisearch_auth::IndexSearchRules;
 use meilisearch_types::deserr::DeserrJsonError;
 use meilisearch_types::error::deserr_codes::*;
-use meilisearch_types::error::ResponseError;
+use meilisearch_types::error::{Code, ResponseError};
 use meilisearch_types::heed::RoTxn;
 use meilisearch_types::index_uid::IndexUid;
 use meilisearch_types::milli::score_details::{ScoreDetails, ScoringStrategy};
@@ -87,6 +87,44 @@ pub struct SearchQuery {
     pub matching_strategy: MatchingStrategy,
     #[deserr(default, error = DeserrJsonError<InvalidSearchAttributesToSearchOn>, default)]
     pub attributes_to_search_on: Option<Vec<String>>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchRankingScoreThreshold>, default)]
+    pub ranking_score_threshold: Option<RankingScoreThreshold>,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Deserr)]
+#[deserr(try_from(f64) = TryFrom::try_from -> InvalidSearchRankingScoreThreshold)]
+pub struct RankingScoreThreshold(f64);
+
+impl std::convert::TryFrom<f64> for RankingScoreThreshold {
+    type Error = InvalidSearchRankingScoreThreshold;
+
+    fn try_from(f: f64) -> Result<Self, Self::Error> {
+        // the suggested "fix" is: `!(0.0..=1.0).contains(&f)`` which is allegedly less readable
+        #[allow(clippy::manual_range_contains)]
+        if f > 1.0 || f < 0.0 {
+            Err(InvalidSearchRankingScoreThreshold)
+        } else {
+            Ok(RankingScoreThreshold(f))
+        }
+    }
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Deserr)]
+#[deserr(try_from(f64) = TryFrom::try_from -> InvalidSimilarRankingScoreThreshold)]
+pub struct RankingScoreThresholdSimilar(f64);
+
+impl std::convert::TryFrom<f64> for RankingScoreThresholdSimilar {
+    type Error = InvalidSimilarRankingScoreThreshold;
+
+    fn try_from(f: f64) -> Result<Self, Self::Error> {
+        // the suggested "fix" is: `!(0.0..=1.0).contains(&f)`` which is allegedly less readable
+        #[allow(clippy::manual_range_contains)]
+        if f > 1.0 || f < 0.0 {
+            Err(InvalidSimilarRankingScoreThreshold)
+        } else {
+            Ok(Self(f))
+        }
+    }
 }
 
 // Since this structure is logged A LOT we're going to reduce the number of things it logs to the bare minimum.
@@ -117,6 +155,7 @@ impl fmt::Debug for SearchQuery {
             crop_marker,
             matching_strategy,
             attributes_to_search_on,
+            ranking_score_threshold,
         } = self;
 
         let mut debug = f.debug_struct("SearchQuery");
@@ -188,6 +227,9 @@ impl fmt::Debug for SearchQuery {
         debug.field("highlight_pre_tag", &highlight_pre_tag);
         debug.field("highlight_post_tag", &highlight_post_tag);
         debug.field("crop_marker", &crop_marker);
+        if let Some(ranking_score_threshold) = ranking_score_threshold {
+            debug.field("ranking_score_threshold", &ranking_score_threshold);
+        }
 
         debug.finish()
     }
@@ -231,7 +273,7 @@ impl SearchKind {
         Ok(Self::Hybrid { embedder_name, embedder, semantic_ratio })
     }
 
-    fn embedder(
+    pub(crate) fn embedder(
         index_scheduler: &index_scheduler::IndexScheduler,
         index: &Index,
         embedder_name: Option<&str>,
@@ -356,6 +398,8 @@ pub struct SearchQueryWithIndex {
     pub matching_strategy: MatchingStrategy,
     #[deserr(default, error = DeserrJsonError<InvalidSearchAttributesToSearchOn>, default)]
     pub attributes_to_search_on: Option<Vec<String>>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchRankingScoreThreshold>, default)]
+    pub ranking_score_threshold: Option<RankingScoreThreshold>,
 }
 
 impl SearchQueryWithIndex {
@@ -384,6 +428,7 @@ impl SearchQueryWithIndex {
             matching_strategy,
             attributes_to_search_on,
             hybrid,
+            ranking_score_threshold,
         } = self;
         (
             index_uid,
@@ -410,6 +455,7 @@ impl SearchQueryWithIndex {
                 matching_strategy,
                 attributes_to_search_on,
                 hybrid,
+                ranking_score_threshold,
                 // do not use ..Default::default() here,
                 // rather add any missing field from `SearchQuery` to `SearchQueryWithIndex`
             },
@@ -417,6 +463,61 @@ impl SearchQueryWithIndex {
     }
 }
 
+#[derive(Debug, Clone, PartialEq, Deserr)]
+#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
+pub struct SimilarQuery {
+    #[deserr(error = DeserrJsonError<InvalidSimilarId>)]
+    pub id: ExternalDocumentId,
+    #[deserr(default = DEFAULT_SEARCH_OFFSET(), error = DeserrJsonError<InvalidSimilarOffset>)]
+    pub offset: usize,
+    #[deserr(default = DEFAULT_SEARCH_LIMIT(), error = DeserrJsonError<InvalidSimilarLimit>)]
+    pub limit: usize,
+    #[deserr(default, error = DeserrJsonError<InvalidSimilarFilter>)]
+    pub filter: Option<Value>,
+    #[deserr(default, error = DeserrJsonError<InvalidEmbedder>, default)]
+    pub embedder: Option<String>,
+    #[deserr(default, error = DeserrJsonError<InvalidSimilarAttributesToRetrieve>)]
+    pub attributes_to_retrieve: Option<BTreeSet<String>>,
+    #[deserr(default, error = DeserrJsonError<InvalidSimilarShowRankingScore>, default)]
+    pub show_ranking_score: bool,
+    #[deserr(default, error = DeserrJsonError<InvalidSimilarShowRankingScoreDetails>, default)]
+    pub show_ranking_score_details: bool,
+    #[deserr(default, error = DeserrJsonError<InvalidSimilarRankingScoreThreshold>, default)]
+    pub ranking_score_threshold: Option<RankingScoreThresholdSimilar>,
+}
+
+#[derive(Debug, Clone, PartialEq, Deserr)]
+#[deserr(try_from(Value) = TryFrom::try_from -> InvalidSimilarId)]
+pub struct ExternalDocumentId(String);
+
+impl AsRef<str> for ExternalDocumentId {
+    fn as_ref(&self) -> &str {
+        &self.0
+    }
+}
+
+impl ExternalDocumentId {
+    pub fn into_inner(self) -> String {
+        self.0
+    }
+}
+
+impl TryFrom<String> for ExternalDocumentId {
+    type Error = InvalidSimilarId;
+
+    fn try_from(value: String) -> Result<Self, Self::Error> {
+        serde_json::Value::String(value).try_into()
+    }
+}
+
+impl TryFrom<Value> for ExternalDocumentId {
+    type Error = InvalidSimilarId;
+
+    fn try_from(value: Value) -> Result<Self, Self::Error> {
+        Ok(Self(milli::documents::validate_document_id_value(value).map_err(|_| InvalidSimilarId)?))
+    }
+}
+
 #[derive(Debug, Copy, Clone, PartialEq, Eq, Deserr)]
 #[deserr(rename_all = camelCase)]
 pub enum MatchingStrategy {
@@ -424,6 +525,8 @@ pub enum MatchingStrategy {
     Last,
     /// All query words are mandatory
     All,
+    /// Remove query words from the most frequent to the least
+    Frequency,
 }
 
 impl Default for MatchingStrategy {
@@ -437,6 +540,7 @@ impl From<MatchingStrategy> for TermsMatchingStrategy {
         match other {
             MatchingStrategy::Last => Self::Last,
             MatchingStrategy::All => Self::All,
+            MatchingStrategy::Frequency => Self::Frequency,
         }
     }
 }
@@ -538,6 +642,16 @@ impl fmt::Debug for SearchResult {
     }
 }
 
+#[derive(Serialize, Debug, Clone, PartialEq)]
+#[serde(rename_all = "camelCase")]
+pub struct SimilarResult {
+    pub hits: Vec<SearchHit>,
+    pub id: String,
+    pub processing_time_ms: u128,
+    #[serde(flatten)]
+    pub hits_info: HitsInfo,
+}
+
 #[derive(Serialize, Debug, Clone, PartialEq)]
 #[serde(rename_all = "camelCase")]
 pub struct SearchResultWithIndex {
@@ -570,8 +684,8 @@ pub struct FacetSearchResult {
 }
 
 /// Incorporate search rules in search query
-pub fn add_search_rules(query: &mut SearchQuery, rules: IndexSearchRules) {
-    query.filter = match (query.filter.take(), rules.filter) {
+pub fn add_search_rules(filter: &mut Option<Value>, rules: IndexSearchRules) {
+    *filter = match (filter.take(), rules.filter) {
         (None, rules_filter) => rules_filter,
         (filter, None) => filter,
         (Some(filter), Some(rules_filter)) => {
@@ -598,6 +712,9 @@ fn prepare_search<'t>(
 ) -> Result<(milli::Search<'t>, bool, usize, usize), MeilisearchHttpError> {
     let mut search = index.search(rtxn);
     search.time_budget(time_budget);
+    if let Some(ranking_score_threshold) = query.ranking_score_threshold {
+        search.ranking_score_threshold(ranking_score_threshold.0);
+    }
 
     match search_kind {
         SearchKind::KeywordOnly => {
@@ -639,11 +756,16 @@ fn prepare_search<'t>(
         .unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS);
 
     search.exhaustive_number_hits(is_finite_pagination);
-    search.scoring_strategy(if query.show_ranking_score || query.show_ranking_score_details {
-        ScoringStrategy::Detailed
-    } else {
-        ScoringStrategy::Skip
-    });
+    search.scoring_strategy(
+        if query.show_ranking_score
+            || query.show_ranking_score_details
+            || query.ranking_score_threshold.is_some()
+        {
+            ScoringStrategy::Detailed
+        } else {
+            ScoringStrategy::Skip
+        },
+    );
 
     // compute the offset on the limit depending on the pagination mode.
     let (offset, limit) = if is_finite_pagination {
@@ -719,131 +841,53 @@ pub fn perform_search(
         SearchKind::Hybrid { semantic_ratio, .. } => search.execute_hybrid(*semantic_ratio)?,
     };
 
-    let fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
+    let SearchQuery {
+        q,
+        limit,
+        page,
+        hits_per_page,
+        attributes_to_retrieve,
+        attributes_to_crop,
+        crop_length,
+        attributes_to_highlight,
+        show_matches_position,
+        show_ranking_score,
+        show_ranking_score_details,
+        sort,
+        facets,
+        highlight_pre_tag,
+        highlight_post_tag,
+        crop_marker,
+        // already used in prepare_search
+        vector: _,
+        hybrid: _,
+        offset: _,
+        ranking_score_threshold: _,
+        matching_strategy: _,
+        attributes_to_search_on: _,
+        filter: _,
+    } = query;
 
-    let displayed_ids = index
-        .displayed_fields_ids(&rtxn)?
-        .map(|fields| fields.into_iter().collect::<BTreeSet<_>>())
-        .unwrap_or_else(|| fields_ids_map.iter().map(|(id, _)| id).collect());
-
-    let fids = |attrs: &BTreeSet<String>| {
-        let mut ids = BTreeSet::new();
-        for attr in attrs {
-            if attr == "*" {
-                ids.clone_from(&displayed_ids);
-                break;
-            }
-
-            if let Some(id) = fields_ids_map.id(attr) {
-                ids.insert(id);
-            }
-        }
-        ids
+    let format = AttributesFormat {
+        attributes_to_retrieve,
+        attributes_to_highlight,
+        attributes_to_crop,
+        crop_length,
+        crop_marker,
+        highlight_pre_tag,
+        highlight_post_tag,
+        show_matches_position,
+        sort,
+        show_ranking_score,
+        show_ranking_score_details,
     };
 
-    // The attributes to retrieve are the ones explicitly marked as to retrieve (all by default),
-    // but these attributes must be also be present
-    // - in the fields_ids_map
-    // - in the displayed attributes
-    let to_retrieve_ids: BTreeSet<_> = query
-        .attributes_to_retrieve
-        .as_ref()
-        .map(fids)
-        .unwrap_or_else(|| displayed_ids.clone())
-        .intersection(&displayed_ids)
-        .cloned()
-        .collect();
-
-    let attr_to_highlight = query.attributes_to_highlight.unwrap_or_default();
-
-    let attr_to_crop = query.attributes_to_crop.unwrap_or_default();
-
-    // Attributes in `formatted_options` correspond to the attributes that will be in `_formatted`
-    // These attributes are:
-    // - the attributes asked to be highlighted or cropped (with `attributesToCrop` or `attributesToHighlight`)
-    // - the attributes asked to be retrieved: these attributes will not be highlighted/cropped
-    // But these attributes must be also present in displayed attributes
-    let formatted_options = compute_formatted_options(
-        &attr_to_highlight,
-        &attr_to_crop,
-        query.crop_length,
-        &to_retrieve_ids,
-        &fields_ids_map,
-        &displayed_ids,
-    );
-
-    let mut tokenizer_builder = TokenizerBuilder::default();
-    tokenizer_builder.create_char_map(true);
-
-    let script_lang_map = index.script_language(&rtxn)?;
-    if !script_lang_map.is_empty() {
-        tokenizer_builder.allow_list(&script_lang_map);
-    }
-
-    let separators = index.allowed_separators(&rtxn)?;
-    let separators: Option<Vec<_>> =
-        separators.as_ref().map(|x| x.iter().map(String::as_str).collect());
-    if let Some(ref separators) = separators {
-        tokenizer_builder.separators(separators);
-    }
-
-    let dictionary = index.dictionary(&rtxn)?;
-    let dictionary: Option<Vec<_>> =
-        dictionary.as_ref().map(|x| x.iter().map(String::as_str).collect());
-    if let Some(ref dictionary) = dictionary {
-        tokenizer_builder.words_dict(dictionary);
-    }
-
-    let mut formatter_builder = MatcherBuilder::new(matching_words, tokenizer_builder.build());
-    formatter_builder.crop_marker(query.crop_marker);
-    formatter_builder.highlight_prefix(query.highlight_pre_tag);
-    formatter_builder.highlight_suffix(query.highlight_post_tag);
-
-    let mut documents = Vec::new();
-    let documents_iter = index.documents(&rtxn, documents_ids)?;
-
-    for ((_id, obkv), score) in documents_iter.into_iter().zip(document_scores.into_iter()) {
-        // First generate a document with all the displayed fields
-        let displayed_document = make_document(&displayed_ids, &fields_ids_map, obkv)?;
-
-        // select the attributes to retrieve
-        let attributes_to_retrieve = to_retrieve_ids
-            .iter()
-            .map(|&fid| fields_ids_map.name(fid).expect("Missing field name"));
-        let mut document =
-            permissive_json_pointer::select_values(&displayed_document, attributes_to_retrieve);
-
-        let (matches_position, formatted) = format_fields(
-            &displayed_document,
-            &fields_ids_map,
-            &formatter_builder,
-            &formatted_options,
-            query.show_matches_position,
-            &displayed_ids,
-        )?;
-
-        if let Some(sort) = query.sort.as_ref() {
-            insert_geo_distance(sort, &mut document);
-        }
-
-        let ranking_score =
-            query.show_ranking_score.then(|| ScoreDetails::global_score(score.iter()));
-        let ranking_score_details =
-            query.show_ranking_score_details.then(|| ScoreDetails::to_json_map(score.iter()));
-
-        let hit = SearchHit {
-            document,
-            formatted,
-            matches_position,
-            ranking_score_details,
-            ranking_score,
-        };
-        documents.push(hit);
-    }
+    let documents =
+        make_hits(index, &rtxn, format, matching_words, documents_ids, document_scores)?;
 
     let number_of_hits = min(candidates.len() as usize, max_total_hits);
     let hits_info = if is_finite_pagination {
-        let hits_per_page = query.hits_per_page.unwrap_or_else(DEFAULT_SEARCH_LIMIT);
+        let hits_per_page = hits_per_page.unwrap_or_else(DEFAULT_SEARCH_LIMIT);
         // If hit_per_page is 0, then pages can't be computed and so we respond 0.
         let total_pages = (number_of_hits + hits_per_page.saturating_sub(1))
             .checked_div(hits_per_page)
@@ -851,15 +895,15 @@ pub fn perform_search(
 
         HitsInfo::Pagination {
             hits_per_page,
-            page: query.page.unwrap_or(1),
+            page: page.unwrap_or(1),
             total_pages,
             total_hits: number_of_hits,
         }
     } else {
-        HitsInfo::OffsetLimit { limit: query.limit, offset, estimated_total_hits: number_of_hits }
+        HitsInfo::OffsetLimit { limit, offset, estimated_total_hits: number_of_hits }
     };
 
-    let (facet_distribution, facet_stats) = match query.facets {
+    let (facet_distribution, facet_stats) = match facets {
         Some(ref fields) => {
             let mut facet_distribution = index.facets_distribution(&rtxn);
 
@@ -896,7 +940,7 @@ pub fn perform_search(
     let result = SearchResult {
         hits: documents,
         hits_info,
-        query: query.q.unwrap_or_default(),
+        query: q.unwrap_or_default(),
         processing_time_ms: before_search.elapsed().as_millis(),
         facet_distribution,
         facet_stats,
@@ -907,6 +951,130 @@ pub fn perform_search(
     Ok(result)
 }
 
+struct AttributesFormat {
+    attributes_to_retrieve: Option<BTreeSet<String>>,
+    attributes_to_highlight: Option<HashSet<String>>,
+    attributes_to_crop: Option<Vec<String>>,
+    crop_length: usize,
+    crop_marker: String,
+    highlight_pre_tag: String,
+    highlight_post_tag: String,
+    show_matches_position: bool,
+    sort: Option<Vec<String>>,
+    show_ranking_score: bool,
+    show_ranking_score_details: bool,
+}
+
+fn make_hits(
+    index: &Index,
+    rtxn: &RoTxn<'_>,
+    format: AttributesFormat,
+    matching_words: milli::MatchingWords,
+    documents_ids: Vec<u32>,
+    document_scores: Vec<Vec<ScoreDetails>>,
+) -> Result<Vec<SearchHit>, MeilisearchHttpError> {
+    let fields_ids_map = index.fields_ids_map(rtxn).unwrap();
+    let displayed_ids = index
+        .displayed_fields_ids(rtxn)?
+        .map(|fields| fields.into_iter().collect::<BTreeSet<_>>())
+        .unwrap_or_else(|| fields_ids_map.iter().map(|(id, _)| id).collect());
+    let fids = |attrs: &BTreeSet<String>| {
+        let mut ids = BTreeSet::new();
+        for attr in attrs {
+            if attr == "*" {
+                ids.clone_from(&displayed_ids);
+                break;
+            }
+
+            if let Some(id) = fields_ids_map.id(attr) {
+                ids.insert(id);
+            }
+        }
+        ids
+    };
+    let to_retrieve_ids: BTreeSet<_> = format
+        .attributes_to_retrieve
+        .as_ref()
+        .map(fids)
+        .unwrap_or_else(|| displayed_ids.clone())
+        .intersection(&displayed_ids)
+        .cloned()
+        .collect();
+    let attr_to_highlight = format.attributes_to_highlight.unwrap_or_default();
+    let attr_to_crop = format.attributes_to_crop.unwrap_or_default();
+    let formatted_options = compute_formatted_options(
+        &attr_to_highlight,
+        &attr_to_crop,
+        format.crop_length,
+        &to_retrieve_ids,
+        &fields_ids_map,
+        &displayed_ids,
+    );
+    let mut tokenizer_builder = TokenizerBuilder::default();
+    tokenizer_builder.create_char_map(true);
+    let script_lang_map = index.script_language(rtxn)?;
+    if !script_lang_map.is_empty() {
+        tokenizer_builder.allow_list(&script_lang_map);
+    }
+    let separators = index.allowed_separators(rtxn)?;
+    let separators: Option<Vec<_>> =
+        separators.as_ref().map(|x| x.iter().map(String::as_str).collect());
+    if let Some(ref separators) = separators {
+        tokenizer_builder.separators(separators);
+    }
+    let dictionary = index.dictionary(rtxn)?;
+    let dictionary: Option<Vec<_>> =
+        dictionary.as_ref().map(|x| x.iter().map(String::as_str).collect());
+    if let Some(ref dictionary) = dictionary {
+        tokenizer_builder.words_dict(dictionary);
+    }
+    let mut formatter_builder = MatcherBuilder::new(matching_words, tokenizer_builder.build());
+    formatter_builder.crop_marker(format.crop_marker);
+    formatter_builder.highlight_prefix(format.highlight_pre_tag);
+    formatter_builder.highlight_suffix(format.highlight_post_tag);
+    let mut documents = Vec::new();
+    let documents_iter = index.documents(rtxn, documents_ids)?;
+    for ((_id, obkv), score) in documents_iter.into_iter().zip(document_scores.into_iter()) {
+        // First generate a document with all the displayed fields
+        let displayed_document = make_document(&displayed_ids, &fields_ids_map, obkv)?;
+
+        // select the attributes to retrieve
+        let attributes_to_retrieve = to_retrieve_ids
+            .iter()
+            .map(|&fid| fields_ids_map.name(fid).expect("Missing field name"));
+        let mut document =
+            permissive_json_pointer::select_values(&displayed_document, attributes_to_retrieve);
+
+        let (matches_position, formatted) = format_fields(
+            &displayed_document,
+            &fields_ids_map,
+            &formatter_builder,
+            &formatted_options,
+            format.show_matches_position,
+            &displayed_ids,
+        )?;
+
+        if let Some(sort) = format.sort.as_ref() {
+            insert_geo_distance(sort, &mut document);
+        }
+
+        let ranking_score =
+            format.show_ranking_score.then(|| ScoreDetails::global_score(score.iter()));
+        let ranking_score_details =
+            format.show_ranking_score_details.then(|| ScoreDetails::to_json_map(score.iter()));
+
+        let hit = SearchHit {
+            document,
+            formatted,
+            matches_position,
+            ranking_score_details,
+            ranking_score,
+        };
+        documents.push(hit);
+    }
+    Ok(documents)
+}
+
 pub fn perform_facet_search(
     index: &Index,
     search_query: SearchQuery,
@@ -941,6 +1109,100 @@ pub fn perform_facet_search(
     })
 }
 
+pub fn perform_similar(
+    index: &Index,
+    query: SimilarQuery,
+    embedder_name: String,
+    embedder: Arc<Embedder>,
+) -> Result<SimilarResult, ResponseError> {
+    let before_search = Instant::now();
+    let rtxn = index.read_txn()?;
+
+    let SimilarQuery {
+        id,
+        offset,
+        limit,
+        filter: _,
+        embedder: _,
+        attributes_to_retrieve,
+        show_ranking_score,
+        show_ranking_score_details,
+        ranking_score_threshold,
+    } = query;
+
+    // using let-else rather than `?` so that the borrow checker identifies we're always returning here,
+    // preventing a use-after-move
+    let Some(internal_id) = index.external_documents_ids().get(&rtxn, &id)? else {
+        return Err(ResponseError::from_msg(
+            MeilisearchHttpError::DocumentNotFound(id.into_inner()).to_string(),
+            Code::NotFoundSimilarId,
+        ));
+    };
+
+    let mut similar =
+        milli::Similar::new(internal_id, offset, limit, index, &rtxn, embedder_name, embedder);
+
+    if let Some(ref filter) = query.filter {
+        if let Some(facets) = parse_filter(filter)
+            // inject InvalidSimilarFilter code
+            .map_err(|e| ResponseError::from_msg(e.to_string(), Code::InvalidSimilarFilter))?
+        {
+            similar.filter(facets);
+        }
+    }
+
+    if let Some(ranking_score_threshold) = ranking_score_threshold {
+        similar.ranking_score_threshold(ranking_score_threshold.0);
+    }
+
+    let milli::SearchResult {
+        documents_ids,
+        matching_words: _,
+        candidates,
+        document_scores,
+        degraded: _,
+        used_negative_operator: _,
+    } = similar.execute().map_err(|err| match err {
+        milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
+            ResponseError::from_msg(err.to_string(), Code::InvalidSimilarFilter)
+        }
+        err => err.into(),
+    })?;
+
+    let format = AttributesFormat {
+        attributes_to_retrieve,
+        attributes_to_highlight: None,
+        attributes_to_crop: None,
+        crop_length: DEFAULT_CROP_LENGTH(),
+        crop_marker: DEFAULT_CROP_MARKER(),
+        highlight_pre_tag: DEFAULT_HIGHLIGHT_PRE_TAG(),
+        highlight_post_tag: DEFAULT_HIGHLIGHT_POST_TAG(),
+        show_matches_position: false,
+        sort: None,
+        show_ranking_score,
+        show_ranking_score_details,
+    };
+
+    let hits = make_hits(index, &rtxn, format, Default::default(), documents_ids, document_scores)?;
+
+    let max_total_hits = index
+        .pagination_max_total_hits(&rtxn)
+        .map_err(milli::Error::from)?
+        .map(|x| x as usize)
+        .unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS);
+
+    let number_of_hits = min(candidates.len() as usize, max_total_hits);
+    let hits_info = HitsInfo::OffsetLimit { limit, offset, estimated_total_hits: number_of_hits };
+
+    let result = SimilarResult {
+        hits,
+        hits_info,
+        id: id.into_inner(),
+        processing_time_ms: before_search.elapsed().as_millis(),
+    };
+    Ok(result)
+}
+
 fn insert_geo_distance(sorts: &[String], document: &mut Document) {
     lazy_static::lazy_static! {
         static ref GEO_REGEX: Regex =

meilisearch/src/search_queue.rs

@@ -40,8 +40,9 @@ pub struct Permit {
 
 impl Drop for Permit {
     fn drop(&mut self) {
+        let sender = self.sender.clone();
         // if the channel is closed then the whole instance is down
-        let _ = futures::executor::block_on(self.sender.send(()));
+        std::mem::drop(tokio::spawn(async move { sender.send(()).await }));
     }
 }
 

meilisearch/tests/common/index.rs

@@ -380,6 +380,43 @@ impl Index<'_> {
         self.service.get(url).await
     }
 
+    /// Performs both GET and POST similar queries
+    pub async fn similar(
+        &self,
+        query: Value,
+        test: impl Fn(Value, StatusCode) + UnwindSafe + Clone,
+    ) {
+        let post = self.similar_post(query.clone()).await;
+
+        let query = yaup::to_string(&query).unwrap();
+        let get = self.similar_get(&query).await;
+
+        insta::allow_duplicates! {
+            let (response, code) = post;
+            let t = test.clone();
+            if let Err(e) = catch_unwind(move || t(response, code)) {
+                eprintln!("Error with post search");
+                resume_unwind(e);
+            }
+
+            let (response, code) = get;
+            if let Err(e) = catch_unwind(move || test(response, code)) {
+                eprintln!("Error with get search");
+                resume_unwind(e);
+            }
+        }
+    }
+
+    pub async fn similar_post(&self, query: Value) -> (Value, StatusCode) {
+        let url = format!("/indexes/{}/similar", urlencode(self.uid.as_ref()));
+        self.service.post_encoded(url, query, self.encoder).await
+    }
+
+    pub async fn similar_get(&self, query: &str) -> (Value, StatusCode) {
+        let url = format!("/indexes/{}/similar?{}", urlencode(self.uid.as_ref()), query);
+        self.service.get(url).await
+    }
+
     pub async fn facet_search(&self, query: Value) -> (Value, StatusCode) {
         let url = format!("/indexes/{}/facet-search", urlencode(self.uid.as_ref()));
         self.service.post_encoded(url, query, self.encoder).await

meilisearch/tests/dumps/mod.rs

@@ -1859,8 +1859,7 @@ async fn import_dump_v6_containing_experimental_features() {
     {
       "vectorStore": false,
       "metrics": false,
-      "logsRoute": false,
-      "exportPuffinReports": false
+      "logsRoute": false
     }
     "###);
 

meilisearch/tests/features/mod.rs

@@ -20,8 +20,7 @@ async fn experimental_features() {
     {
       "vectorStore": false,
       "metrics": false,
-      "logsRoute": false,
-      "exportPuffinReports": false
+      "logsRoute": false
     }
     "###);
 
@@ -32,8 +31,7 @@ async fn experimental_features() {
     {
       "vectorStore": true,
       "metrics": false,
-      "logsRoute": false,
-      "exportPuffinReports": false
+      "logsRoute": false
     }
     "###);
 
@@ -44,8 +42,7 @@ async fn experimental_features() {
     {
       "vectorStore": true,
       "metrics": false,
-      "logsRoute": false,
-      "exportPuffinReports": false
+      "logsRoute": false
     }
     "###);
 
@@ -57,8 +54,7 @@ async fn experimental_features() {
     {
       "vectorStore": true,
       "metrics": false,
-      "logsRoute": false,
-      "exportPuffinReports": false
+      "logsRoute": false
     }
     "###);
 
@@ -70,8 +66,7 @@ async fn experimental_features() {
     {
       "vectorStore": true,
       "metrics": false,
-      "logsRoute": false,
-      "exportPuffinReports": false
+      "logsRoute": false
     }
     "###);
 }
@@ -90,8 +85,7 @@ async fn experimental_feature_metrics() {
     {
       "vectorStore": false,
       "metrics": true,
-      "logsRoute": false,
-      "exportPuffinReports": false
+      "logsRoute": false
     }
     "###);
 
@@ -146,7 +140,7 @@ async fn errors() {
     meili_snap::snapshot!(code, @"400 Bad Request");
     meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
     {
-      "message": "Unknown field `NotAFeature`: expected one of `vectorStore`, `metrics`, `logsRoute`, `exportPuffinReports`",
+      "message": "Unknown field `NotAFeature`: expected one of `vectorStore`, `metrics`, `logsRoute`",
       "code": "bad_request",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#bad_request"

meilisearch/tests/integration.rs

@@ -8,6 +8,7 @@ mod index;
 mod logs;
 mod search;
 mod settings;
+mod similar;
 mod snapshot;
 mod stats;
 mod swap_indexes;

meilisearch/tests/search/errors.rs

@@ -321,6 +321,40 @@ async fn search_bad_facets() {
     // Can't make the `attributes_to_highlight` fail with a get search since it'll accept anything as an array of strings.
 }
 
+#[actix_rt::test]
+async fn search_bad_threshold() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let (response, code) = index.search_post(json!({"rankingScoreThreshold": "doggo"})).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(response), @r###"
+    {
+      "message": "Invalid value type at `.rankingScoreThreshold`: expected a number, but found a string: `\"doggo\"`",
+      "code": "invalid_search_ranking_score_threshold",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_search_ranking_score_threshold"
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn search_invalid_threshold() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let (response, code) = index.search_post(json!({"rankingScoreThreshold": 42})).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(response), @r###"
+    {
+      "message": "Invalid value at `.rankingScoreThreshold`: the value of `rankingScoreThreshold` is invalid, expected a float between `0.0` and `1.0`.",
+      "code": "invalid_search_ranking_score_threshold",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_search_ranking_score_threshold"
+    }
+    "###);
+}
+
 #[actix_rt::test]
 async fn search_non_filterable_facets() {
     let server = Server::new().await;
@@ -505,7 +539,7 @@ async fn search_bad_matching_strategy() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Unknown value `doggo` at `.matchingStrategy`: expected one of `last`, `all`",
+      "message": "Unknown value `doggo` at `.matchingStrategy`: expected one of `last`, `all`, `frequency`",
       "code": "invalid_search_matching_strategy",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_matching_strategy"
@@ -527,7 +561,7 @@ async fn search_bad_matching_strategy() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Unknown value `doggo` for parameter `matchingStrategy`: expected one of `last`, `all`",
+      "message": "Unknown value `doggo` for parameter `matchingStrategy`: expected one of `last`, `all`, `frequency`",
       "code": "invalid_search_matching_strategy",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_matching_strategy"

meilisearch/tests/search/geo.rs

@@ -117,3 +117,69 @@ async fn geo_bounding_box_with_string_and_number() {
         )
         .await;
 }
+
+#[actix_rt::test]
+async fn bug_4640() {
+    // https://github.com/meilisearch/meilisearch/issues/4640
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let documents = DOCUMENTS.clone();
+    index.add_documents(documents, None).await;
+    index.update_settings_filterable_attributes(json!(["_geo"])).await;
+    let (ret, _code) = index.update_settings_sortable_attributes(json!(["_geo"])).await;
+    index.wait_task(ret.uid()).await;
+
+    // Sort the document with the second one first
+    index
+        .search(
+            json!({
+                "sort": ["_geoPoint(45.4777599, 9.1967508):asc"],
+            }),
+            |response, code| {
+                assert_eq!(code, 200, "{}", response);
+                snapshot!(json_string!(response, { ".processingTimeMs" => "[time]" }), @r###"
+                {
+                  "hits": [
+                    {
+                      "id": 2,
+                      "name": "La Bella Italia",
+                      "address": "456 Elm Street, Townsville",
+                      "type": "Italian",
+                      "rating": 9,
+                      "_geo": {
+                        "lat": "45.4777599",
+                        "lng": "9.1967508"
+                      }
+                    },
+                    {
+                      "id": 1,
+                      "name": "Taco Truck",
+                      "address": "444 Salsa Street, Burritoville",
+                      "type": "Mexican",
+                      "rating": 9,
+                      "_geo": {
+                        "lat": 34.0522,
+                        "lng": -118.2437
+                      },
+                      "_geoDistance": 9714063
+                    },
+                    {
+                      "id": 3,
+                      "name": "Crêpe Truck",
+                      "address": "2 Billig Avenue, Rouenville",
+                      "type": "French",
+                      "rating": 10
+                    }
+                  ],
+                  "query": "",
+                  "processingTimeMs": "[time]",
+                  "limit": 20,
+                  "offset": 0,
+                  "estimatedTotalHits": 3
+                }
+                "###);
+            },
+        )
+        .await;
+}

meilisearch/tests/search/hybrid.rs

@@ -5,7 +5,10 @@ use crate::common::index::Index;
 use crate::common::{Server, Value};
 use crate::json;
 
-async fn index_with_documents<'a>(server: &'a Server, documents: &Value) -> Index<'a> {
+async fn index_with_documents_user_provided<'a>(
+    server: &'a Server,
+    documents: &Value,
+) -> Index<'a> {
     let index = server.index("test");
 
     let (response, code) = server.set_features(json!({"vectorStore": true})).await;
@@ -15,8 +18,7 @@ async fn index_with_documents<'a>(server: &'a Server, documents: &Value) -> Inde
     {
       "vectorStore": true,
       "metrics": false,
-      "logsRoute": false,
-      "exportPuffinReports": false
+      "logsRoute": false
     }
     "###);
 
@@ -34,7 +36,38 @@ async fn index_with_documents<'a>(server: &'a Server, documents: &Value) -> Inde
     index
 }
 
-static SIMPLE_SEARCH_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
+async fn index_with_documents_hf<'a>(server: &'a Server, documents: &Value) -> Index<'a> {
+    let index = server.index("test");
+
+    let (response, code) = server.set_features(json!({"vectorStore": true})).await;
+
+    meili_snap::snapshot!(code, @"200 OK");
+    meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
+    {
+      "vectorStore": true,
+      "metrics": false,
+      "logsRoute": false
+    }
+    "###);
+
+    let (response, code) = index
+        .update_settings(json!({ "embedders": {"default": {
+            "source": "huggingFace",
+            "model": "sentence-transformers/all-MiniLM-L6-v2",
+            "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
+            "documentTemplate": "{{doc.title}}, {{doc.desc}}"
+        }}} ))
+        .await;
+    assert_eq!(202, code, "{:?}", response);
+    index.wait_task(response.uid()).await;
+
+    let (response, code) = index.add_documents(documents.clone(), None).await;
+    assert_eq!(202, code, "{:?}", response);
+    index.wait_task(response.uid()).await;
+    index
+}
+
+static SIMPLE_SEARCH_DOCUMENTS_VEC: Lazy<Value> = Lazy::new(|| {
     json!([
     {
         "title": "Shazam!",
@@ -56,7 +89,7 @@ static SIMPLE_SEARCH_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
     }])
 });
 
-static SINGLE_DOCUMENT: Lazy<Value> = Lazy::new(|| {
+static SINGLE_DOCUMENT_VEC: Lazy<Value> = Lazy::new(|| {
     json!([{
             "title": "Shazam!",
             "desc": "a Captain Marvel ersatz",
@@ -65,10 +98,29 @@ static SINGLE_DOCUMENT: Lazy<Value> = Lazy::new(|| {
     }])
 });
 
+static SIMPLE_SEARCH_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
+    json!([
+    {
+        "title": "Shazam!",
+        "desc": "a Captain Marvel ersatz",
+        "id": "1",
+    },
+    {
+        "title": "Captain Planet",
+        "desc": "He's not part of the Marvel Cinematic Universe",
+        "id": "2",
+    },
+    {
+        "title": "Captain Marvel",
+        "desc": "a Shazam ersatz",
+        "id": "3",
+    }])
+});
+
 #[actix_rt::test]
 async fn simple_search() {
     let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
+    let index = index_with_documents_user_provided(&server, &SIMPLE_SEARCH_DOCUMENTS_VEC).await;
 
     let (response, code) = index
         .search_post(
@@ -98,10 +150,59 @@ async fn simple_search() {
     snapshot!(response["semanticHitCount"], @"3");
 }
 
+#[actix_rt::test]
+async fn simple_search_hf() {
+    let server = Server::new().await;
+    let index = index_with_documents_hf(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
+
+    let (response, code) =
+        index.search_post(json!({"q": "Captain", "hybrid": {"semanticRatio": 0.2}})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(response["hits"], @r###"[{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2"},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1"}]"###);
+    snapshot!(response["semanticHitCount"], @"0");
+
+    let (response, code) = index
+        .search_post(
+            // disable ranking score as the vectors between architectures are not equal
+            json!({"q": "Captain", "hybrid": {"semanticRatio": 0.55}, "showRankingScore": false}),
+        )
+        .await;
+    snapshot!(code, @"200 OK");
+    snapshot!(response["hits"], @r###"[{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2"},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1"}]"###);
+    snapshot!(response["semanticHitCount"], @"1");
+
+    let (response, code) = index
+        .search_post(
+            json!({"q": "Captain", "hybrid": {"semanticRatio": 0.8}, "showRankingScore": false}),
+        )
+        .await;
+    snapshot!(code, @"200 OK");
+    snapshot!(response["hits"], @r###"[{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1"},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2"}]"###);
+    snapshot!(response["semanticHitCount"], @"3");
+
+    let (response, code) = index
+        .search_post(
+            json!({"q": "Movie World", "hybrid": {"semanticRatio": 0.2}, "showRankingScore": false}),
+        )
+        .await;
+    snapshot!(code, @"200 OK");
+    snapshot!(response["hits"], @r###"[{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2"},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1"},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"}]"###);
+    snapshot!(response["semanticHitCount"], @"3");
+
+    let (response, code) = index
+        .search_post(
+            json!({"q": "Wonder replacement", "hybrid": {"semanticRatio": 0.2}, "showRankingScore": false}),
+        )
+        .await;
+    snapshot!(code, @"200 OK");
+    snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3"},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1"},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2"}]"###);
+    snapshot!(response["semanticHitCount"], @"3");
+}
+
 #[actix_rt::test]
 async fn distribution_shift() {
     let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
+    let index = index_with_documents_user_provided(&server, &SIMPLE_SEARCH_DOCUMENTS_VEC).await;
 
     let search = json!({"q": "Captain", "vector": [1.0, 1.0], "showRankingScore": true, "hybrid": {"semanticRatio": 1.0}});
     let (response, code) = index.search_post(search.clone()).await;
@@ -133,7 +234,7 @@ async fn distribution_shift() {
 #[actix_rt::test]
 async fn highlighter() {
     let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
+    let index = index_with_documents_user_provided(&server, &SIMPLE_SEARCH_DOCUMENTS_VEC).await;
 
     let (response, code) = index
         .search_post(json!({"q": "Captain Marvel", "vector": [1.0, 1.0],
@@ -184,7 +285,7 @@ async fn highlighter() {
 #[actix_rt::test]
 async fn invalid_semantic_ratio() {
     let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
+    let index = index_with_documents_user_provided(&server, &SIMPLE_SEARCH_DOCUMENTS_VEC).await;
 
     let (response, code) = index
         .search_post(
@@ -256,7 +357,7 @@ async fn invalid_semantic_ratio() {
 #[actix_rt::test]
 async fn single_document() {
     let server = Server::new().await;
-    let index = index_with_documents(&server, &SINGLE_DOCUMENT).await;
+    let index = index_with_documents_user_provided(&server, &SINGLE_DOCUMENT_VEC).await;
 
     let (response, code) = index
     .search_post(
@@ -272,7 +373,7 @@ async fn single_document() {
 #[actix_rt::test]
 async fn query_combination() {
     let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
+    let index = index_with_documents_user_provided(&server, &SIMPLE_SEARCH_DOCUMENTS_VEC).await;
 
     // search without query and vector, but with hybrid => still placeholder
     let (response, code) = index

meilisearch/tests/search/matching_strategy.rs

@@ -0,0 +1,128 @@
+use meili_snap::snapshot;
+use once_cell::sync::Lazy;
+
+use crate::common::index::Index;
+use crate::common::{Server, Value};
+use crate::json;
+
+async fn index_with_documents<'a>(server: &'a Server, documents: &Value) -> Index<'a> {
+    let index = server.index("test");
+
+    index.add_documents(documents.clone(), None).await;
+    index.wait_task(0).await;
+    index
+}
+
+static SIMPLE_SEARCH_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
+    json!([
+    {
+        "title": "Shazam!",
+        "id": "1",
+    },
+    {
+        "title": "Captain Planet",
+        "id": "2",
+    },
+    {
+        "title": "Captain Marvel",
+        "id": "3",
+    },
+    {
+        "title": "a Captain Marvel ersatz",
+        "id": "4"
+    },
+    {
+        "title": "He's not part of the Marvel Cinematic Universe",
+        "id": "5"
+    },
+    {
+        "title": "a Shazam ersatz, but better than Captain Planet",
+        "id": "6"
+    },
+    {
+        "title": "Capitain CAAAAAVEEERNE!!!!",
+        "id": "7"
+    }
+    ])
+});
+
+#[actix_rt::test]
+async fn simple_search() {
+    let server = Server::new().await;
+    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
+
+    index
+        .search(json!({"q": "Captain Marvel", "matchingStrategy": "last", "attributesToRetrieve": ["id"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(response["hits"], @r###"[{"id":"3"},{"id":"4"},{"id":"2"},{"id":"6"},{"id":"7"}]"###);
+        })
+        .await;
+
+    index
+        .search(json!({"q": "Captain Marvel", "matchingStrategy": "all", "attributesToRetrieve": ["id"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(response["hits"], @r###"[{"id":"3"},{"id":"4"}]"###);
+        })
+        .await;
+
+    index
+        .search(json!({"q": "Captain Marvel", "matchingStrategy": "frequency", "attributesToRetrieve": ["id"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(response["hits"], @r###"[{"id":"3"},{"id":"4"},{"id":"5"}]"###);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn search_with_typo() {
+    let server = Server::new().await;
+    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
+
+    index
+        .search(json!({"q": "Capitain Marvel", "matchingStrategy": "last", "attributesToRetrieve": ["id"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(response["hits"], @r###"[{"id":"3"},{"id":"4"},{"id":"7"},{"id":"2"},{"id":"6"}]"###);
+        })
+        .await;
+
+    index
+        .search(json!({"q": "Capitain Marvel", "matchingStrategy": "all", "attributesToRetrieve": ["id"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(response["hits"], @r###"[{"id":"3"},{"id":"4"}]"###);
+        })
+        .await;
+
+    index
+        .search(json!({"q": "Capitain Marvel", "matchingStrategy": "frequency", "attributesToRetrieve": ["id"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(response["hits"], @r###"[{"id":"3"},{"id":"4"},{"id":"5"}]"###);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn search_with_unknown_word() {
+    let server = Server::new().await;
+    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
+
+    index
+        .search(json!({"q": "Captain Supercopter Marvel", "matchingStrategy": "last", "attributesToRetrieve": ["id"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(response["hits"], @r###"[{"id":"2"},{"id":"3"},{"id":"4"},{"id":"6"},{"id":"7"}]"###);
+        })
+        .await;
+
+    index
+        .search(json!({"q": "Captain Supercopter Marvel", "matchingStrategy": "all", "attributesToRetrieve": ["id"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(response["hits"], @"[]");
+        })
+        .await;
+
+    index
+        .search(json!({"q": "Captain Supercopter Marvel", "matchingStrategy": "frequency", "attributesToRetrieve": ["id"]}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(response["hits"], @r###"[{"id":"3"},{"id":"4"},{"id":"5"}]"###);
+        })
+        .await;
+}

meilisearch/tests/search/mod.rs

@@ -7,6 +7,7 @@ mod facet_search;
 mod formatted;
 mod geo;
 mod hybrid;
+mod matching_strategy;
 mod multi;
 mod pagination;
 mod restrict_searchable;
@@ -47,6 +48,31 @@ static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
     ])
 });
 
+static SCORE_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
+    json!([
+        {
+            "title": "Batman the dark knight returns: Part 1",
+            "id": "A",
+        },
+        {
+            "title": "Batman the dark knight returns: Part 2",
+            "id": "B",
+        },
+        {
+            "title": "Batman Returns",
+            "id": "C",
+        },
+        {
+            "title": "Batman",
+            "id": "D",
+        },
+        {
+            "title": "Badman",
+            "id": "E",
+        }
+    ])
+});
+
 static NESTED_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
     json!([
         {
@@ -680,6 +706,26 @@ async fn search_facet_distribution() {
             },
         )
         .await;
+
+    index.update_settings(json!({"filterableAttributes": ["doggos.name"]})).await;
+    index.wait_task(5).await;
+
+    index
+        .search(
+            json!({
+                "facets": ["doggos.name"]
+            }),
+            |response, code| {
+                assert_eq!(code, 200, "{}", response);
+                let dist = response["facetDistribution"].as_object().unwrap();
+                assert_eq!(dist.len(), 1);
+                assert_eq!(
+                    dist["doggos.name"],
+                    json!({ "bobby": 1, "buddy": 1, "gros bill": 1, "turbo": 1, "fast": 1})
+                );
+            },
+        )
+        .await;
 }
 
 #[actix_rt::test]
@@ -895,9 +941,9 @@ async fn test_score_details() {
                     "id": "166428",
                     "_vectors": {
                       "manual": [
-                        -100,
-                        231,
-                        32
+                        -100.0,
+                        231.0,
+                        32.0
                       ]
                     },
                     "_rankingScoreDetails": {
@@ -939,6 +985,213 @@ async fn test_score_details() {
         .await;
 }
 
+#[actix_rt::test]
+async fn test_score() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let documents = SCORE_DOCUMENTS.clone();
+
+    let res = index.add_documents(json!(documents), None).await;
+    index.wait_task(res.0.uid()).await;
+
+    index
+        .search(
+            json!({
+                "q": "Badman the dark knight returns 1",
+                "showRankingScore": true,
+            }),
+            |response, code| {
+                meili_snap::snapshot!(code, @"200 OK");
+                meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
+                [
+                  {
+                    "title": "Batman the dark knight returns: Part 1",
+                    "id": "A",
+                    "_rankingScore": 0.9746605609456898
+                  },
+                  {
+                    "title": "Batman the dark knight returns: Part 2",
+                    "id": "B",
+                    "_rankingScore": 0.8055252965383685
+                  },
+                  {
+                    "title": "Badman",
+                    "id": "E",
+                    "_rankingScore": 0.16666666666666666
+                  },
+                  {
+                    "title": "Batman Returns",
+                    "id": "C",
+                    "_rankingScore": 0.07702020202020202
+                  },
+                  {
+                    "title": "Batman",
+                    "id": "D",
+                    "_rankingScore": 0.07702020202020202
+                  }
+                ]
+                "###);
+            },
+        )
+        .await;
+}
+
+#[actix_rt::test]
+async fn test_score_threshold() {
+    let query = "Badman dark returns 1";
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let documents = SCORE_DOCUMENTS.clone();
+
+    let res = index.add_documents(json!(documents), None).await;
+    index.wait_task(res.0.uid()).await;
+
+    index
+        .search(
+            json!({
+                "q": query,
+                "showRankingScore": true,
+                "rankingScoreThreshold": 0.0
+            }),
+            |response, code| {
+                meili_snap::snapshot!(code, @"200 OK");
+                meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"5");
+                meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
+                [
+                  {
+                    "title": "Batman the dark knight returns: Part 1",
+                    "id": "A",
+                    "_rankingScore": 0.93430081300813
+                  },
+                  {
+                    "title": "Batman the dark knight returns: Part 2",
+                    "id": "B",
+                    "_rankingScore": 0.6685627880184332
+                  },
+                  {
+                    "title": "Badman",
+                    "id": "E",
+                    "_rankingScore": 0.25
+                  },
+                  {
+                    "title": "Batman Returns",
+                    "id": "C",
+                    "_rankingScore": 0.11553030303030302
+                  },
+                  {
+                    "title": "Batman",
+                    "id": "D",
+                    "_rankingScore": 0.11553030303030302
+                  }
+                ]
+                "###);
+            },
+        )
+        .await;
+
+    index
+        .search(
+            json!({
+                "q": query,
+                "showRankingScore": true,
+                "rankingScoreThreshold": 0.2
+            }),
+            |response, code| {
+                meili_snap::snapshot!(code, @"200 OK");
+                meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @r###"3"###);
+                meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
+                [
+                  {
+                    "title": "Batman the dark knight returns: Part 1",
+                    "id": "A",
+                    "_rankingScore": 0.93430081300813
+                  },
+                  {
+                    "title": "Batman the dark knight returns: Part 2",
+                    "id": "B",
+                    "_rankingScore": 0.6685627880184332
+                  },
+                  {
+                    "title": "Badman",
+                    "id": "E",
+                    "_rankingScore": 0.25
+                  }
+                ]
+                "###);
+            },
+        )
+        .await;
+
+    index
+        .search(
+            json!({
+                "q": query,
+                "showRankingScore": true,
+                "rankingScoreThreshold": 0.5
+            }),
+            |response, code| {
+                meili_snap::snapshot!(code, @"200 OK");
+                meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @r###"2"###);
+                meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
+                [
+                  {
+                    "title": "Batman the dark knight returns: Part 1",
+                    "id": "A",
+                    "_rankingScore": 0.93430081300813
+                  },
+                  {
+                    "title": "Batman the dark knight returns: Part 2",
+                    "id": "B",
+                    "_rankingScore": 0.6685627880184332
+                  }
+                ]
+                "###);
+            },
+        )
+        .await;
+
+    index
+        .search(
+            json!({
+                "q": query,
+                "showRankingScore": true,
+                "rankingScoreThreshold": 0.8
+            }),
+            |response, code| {
+                meili_snap::snapshot!(code, @"200 OK");
+                meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @r###"1"###);
+                meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
+                [
+                  {
+                    "title": "Batman the dark knight returns: Part 1",
+                    "id": "A",
+                    "_rankingScore": 0.93430081300813
+                  }
+                ]
+                "###);
+            },
+        )
+        .await;
+
+    index
+        .search(
+            json!({
+                "q": query,
+                "showRankingScore": true,
+                "rankingScoreThreshold": 1.0
+            }),
+            |response, code| {
+                meili_snap::snapshot!(code, @"200 OK");
+                meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @r###"0"###);
+                // nobody is perfect
+                meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @"[]");
+            },
+        )
+        .await;
+}
+
 #[actix_rt::test]
 async fn test_degraded_score_details() {
     let server = Server::new().await;
@@ -1096,9 +1349,9 @@ async fn experimental_feature_vector_store() {
         "id": "287947",
         "_vectors": {
           "manual": [
-            1,
-            2,
-            3
+            1.0,
+            2.0,
+            3.0
           ]
         },
         "_rankingScore": 1.0
@@ -1108,9 +1361,9 @@ async fn experimental_feature_vector_store() {
         "id": "299537",
         "_vectors": {
           "manual": [
-            1,
-            2,
-            54
+            1.0,
+            2.0,
+            54.0
           ]
         },
         "_rankingScore": 0.9129111766815186
@@ -1120,9 +1373,9 @@ async fn experimental_feature_vector_store() {
         "id": "450465",
         "_vectors": {
           "manual": [
-            -100,
-            340,
-            90
+            -100.0,
+            340.0,
+            90.0
           ]
         },
         "_rankingScore": 0.8106412887573242
@@ -1132,9 +1385,9 @@ async fn experimental_feature_vector_store() {
         "id": "166428",
         "_vectors": {
           "manual": [
-            -100,
-            231,
-            32
+            -100.0,
+            231.0,
+            32.0
           ]
         },
         "_rankingScore": 0.7412010431289673
@@ -1144,9 +1397,9 @@ async fn experimental_feature_vector_store() {
         "id": "522681",
         "_vectors": {
           "manual": [
-            10,
-            -23,
-            32
+            10.0,
+            -23.0,
+            32.0
           ]
         },
         "_rankingScore": 0.6972063183784485
@@ -1405,9 +1658,9 @@ async fn simple_search_with_strange_synonyms() {
                 "id": "166428",
                 "_vectors": {
                   "manual": [
-                    -100,
-                    231,
-                    32
+                    -100.0,
+                    231.0,
+                    32.0
                   ]
                 }
               }
@@ -1426,9 +1679,9 @@ async fn simple_search_with_strange_synonyms() {
                 "id": "166428",
                 "_vectors": {
                   "manual": [
-                    -100,
-                    231,
-                    32
+                    -100.0,
+                    231.0,
+                    32.0
                   ]
                 }
               }
@@ -1447,9 +1700,9 @@ async fn simple_search_with_strange_synonyms() {
                 "id": "166428",
                 "_vectors": {
                   "manual": [
-                    -100,
-                    231,
-                    32
+                    -100.0,
+                    231.0,
+                    32.0
                   ]
                 }
               }

meilisearch/tests/search/multi.rs

@@ -75,9 +75,9 @@ async fn simple_search_single_index() {
             "id": "450465",
             "_vectors": {
               "manual": [
-                -100,
-                340,
-                90
+                -100.0,
+                340.0,
+                90.0
               ]
             }
           }
@@ -96,9 +96,9 @@ async fn simple_search_single_index() {
             "id": "299537",
             "_vectors": {
               "manual": [
-                1,
-                2,
-                54
+                1.0,
+                2.0,
+                54.0
               ]
             }
           }
@@ -194,9 +194,9 @@ async fn simple_search_two_indexes() {
             "id": "450465",
             "_vectors": {
               "manual": [
-                -100,
-                340,
-                90
+                -100.0,
+                340.0,
+                90.0
               ]
             }
           }
@@ -227,9 +227,9 @@ async fn simple_search_two_indexes() {
             "cattos": "pésti",
             "_vectors": {
               "manual": [
-                1,
-                2,
-                3
+                1.0,
+                2.0,
+                3.0
               ]
             }
           },
@@ -249,9 +249,9 @@ async fn simple_search_two_indexes() {
             ],
             "_vectors": {
               "manual": [
-                1,
-                2,
-                54
+                1.0,
+                2.0,
+                54.0
               ]
             }
           }

meilisearch/tests/settings/get_settings.rs

@@ -98,8 +98,7 @@ async fn secrets_are_hidden_in_settings() {
     {
       "vectorStore": true,
       "metrics": false,
-      "logsRoute": false,
-      "exportPuffinReports": false
+      "logsRoute": false
     }
     "###);
 

meilisearch/tests/similar/errors.rs

@@ -0,0 +1,758 @@
+use meili_snap::*;
+
+use super::DOCUMENTS;
+use crate::common::Server;
+use crate::json;
+
+#[actix_rt::test]
+async fn similar_unexisting_index() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let expected_response = json!({
+        "message": "Index `test` not found.",
+        "code": "index_not_found",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#index_not_found"
+    });
+
+    index
+        .similar(json!({"id": 287947}), |response, code| {
+            assert_eq!(code, 404);
+            assert_eq!(response, expected_response);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn similar_unexisting_parameter() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    index
+        .similar(json!({"id": 287947, "marin": "hello"}), |response, code| {
+            assert_eq!(code, 400, "{}", response);
+            assert_eq!(response["code"], "bad_request");
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn similar_feature_not_enabled() {
+    let server = Server::new().await;
+    let index = server.index("test");
+
+    let (response, code) = index.similar_post(json!({"id": 287947})).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(response), @r###"
+    {
+      "message": "Using the similar API requires enabling the `vector store` experimental feature. See https://github.com/meilisearch/product/discussions/677",
+      "code": "feature_not_enabled",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn similar_bad_id() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let (response, code) = index.similar_post(json!({"id": ["doggo"]})).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(response), @r###"
+    {
+      "message": "Invalid value at `.id`: the value of `id` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_).",
+      "code": "invalid_similar_id",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_similar_id"
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn similar_bad_ranking_score_threshold() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let (response, code) = index.similar_post(json!({"rankingScoreThreshold": ["doggo"]})).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(response), @r###"
+    {
+      "message": "Invalid value type at `.rankingScoreThreshold`: expected a number, but found an array: `[\"doggo\"]`",
+      "code": "invalid_similar_ranking_score_threshold",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_similar_ranking_score_threshold"
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn similar_invalid_ranking_score_threshold() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let (response, code) = index.similar_post(json!({"rankingScoreThreshold": 42})).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(response), @r###"
+    {
+      "message": "Invalid value at `.rankingScoreThreshold`: the value of `rankingScoreThreshold` is invalid, expected a float between `0.0` and `1.0`.",
+      "code": "invalid_similar_ranking_score_threshold",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_similar_ranking_score_threshold"
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn similar_invalid_id() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let (response, code) = index.similar_post(json!({"id": "http://invalid-docid/"})).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(response), @r###"
+    {
+      "message": "Invalid value at `.id`: the value of `id` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_).",
+      "code": "invalid_similar_id",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_similar_id"
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn similar_not_found_id() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let (response, code) = index.similar_post(json!({"id": "definitely-doesnt-exist"})).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(response), @r###"
+    {
+      "message": "Document `definitely-doesnt-exist` not found.",
+      "code": "not_found_similar_id",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#not_found_similar_id"
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn similar_bad_offset() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let (response, code) = index.similar_post(json!({"id": 287947, "offset": "doggo"})).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(response), @r###"
+    {
+      "message": "Invalid value type at `.offset`: expected a positive integer, but found a string: `\"doggo\"`",
+      "code": "invalid_similar_offset",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_similar_offset"
+    }
+    "###);
+
+    let (response, code) = index.similar_get("id=287947&offset=doggo").await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(response), @r###"
+    {
+      "message": "Invalid value in parameter `offset`: could not parse `doggo` as a positive integer",
+      "code": "invalid_similar_offset",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_similar_offset"
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn similar_bad_limit() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let (response, code) = index.similar_post(json!({"id": 287947, "limit": "doggo"})).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(response), @r###"
+    {
+      "message": "Invalid value type at `.limit`: expected a positive integer, but found a string: `\"doggo\"`",
+      "code": "invalid_similar_limit",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_similar_limit"
+    }
+    "###);
+
+    let (response, code) = index.similar_get("id=287946&limit=doggo").await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(response), @r###"
+    {
+      "message": "Invalid value in parameter `limit`: could not parse `doggo` as a positive integer",
+      "code": "invalid_similar_limit",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_similar_limit"
+    }
+    "###);
+}
+
+#[actix_rt::test]
+async fn similar_bad_filter() {
+    // Since a filter is deserialized as a json Value it will never fail to deserialize.
+    // Thus the error message is not generated by deserr but written by us.
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    snapshot!(code, @"202 Accepted");
+
+    let documents = DOCUMENTS.clone();
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await;
+
+    let (response, code) = index.similar_post(json!({ "id": 287947, "filter": true })).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(response), @r###"
+    {
+      "message": "Invalid syntax for the filter parameter: `expected String, Array, found: true`.",
+      "code": "invalid_similar_filter",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
+    }
+    "###);
+    // Can't make the `filter` fail with a get search since it'll accept anything as a strings.
+}
+
+#[actix_rt::test]
+async fn filter_invalid_syntax_object() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let documents = DOCUMENTS.clone();
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await;
+
+    let expected_response = json!({
+        "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
+        "code": "invalid_similar_filter",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
+    });
+    index
+        .similar(json!({"id": 287947, "filter": "title & Glass"}), |response, code| {
+            assert_eq!(response, expected_response);
+            assert_eq!(code, 400);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn filter_invalid_syntax_array() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let documents = DOCUMENTS.clone();
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await;
+
+    let expected_response = json!({
+        "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
+        "code": "invalid_similar_filter",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
+    });
+    index
+        .similar(json!({"id": 287947, "filter": ["title & Glass"]}), |response, code| {
+            assert_eq!(response, expected_response);
+            assert_eq!(code, 400);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn filter_invalid_syntax_string() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let documents = DOCUMENTS.clone();
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await;
+
+    let expected_response = json!({
+        "message": "Found unexpected characters at the end of the filter: `XOR title = Glass`. You probably forgot an `OR` or an `AND` rule.\n15:32 title = Glass XOR title = Glass",
+        "code": "invalid_similar_filter",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
+    });
+    index
+        .similar(
+            json!({"id": 287947, "filter": "title = Glass XOR title = Glass"}),
+            |response, code| {
+                assert_eq!(response, expected_response);
+                assert_eq!(code, 400);
+            },
+        )
+        .await;
+}
+
+#[actix_rt::test]
+async fn filter_invalid_attribute_array() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let documents = DOCUMENTS.clone();
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await;
+
+    let expected_response = json!({
+        "message": "Attribute `many` is not filterable. Available filterable attributes are: `title`.\n1:5 many = Glass",
+        "code": "invalid_similar_filter",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
+    });
+    index
+        .similar(json!({"id": 287947, "filter": ["many = Glass"]}), |response, code| {
+            assert_eq!(response, expected_response);
+            assert_eq!(code, 400);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn filter_invalid_attribute_string() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let documents = DOCUMENTS.clone();
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await;
+
+    let expected_response = json!({
+        "message": "Attribute `many` is not filterable. Available filterable attributes are: `title`.\n1:5 many = Glass",
+        "code": "invalid_similar_filter",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
+    });
+    index
+        .similar(json!({"id": 287947, "filter": "many = Glass"}), |response, code| {
+            assert_eq!(response, expected_response);
+            assert_eq!(code, 400);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn filter_reserved_geo_attribute_array() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let documents = DOCUMENTS.clone();
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await;
+
+    let expected_response = json!({
+        "message": "`_geo` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:13 _geo = Glass",
+        "code": "invalid_similar_filter",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
+    });
+    index
+        .similar(json!({"id": 287947, "filter": ["_geo = Glass"]}), |response, code| {
+            assert_eq!(response, expected_response);
+            assert_eq!(code, 400);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn filter_reserved_geo_attribute_string() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let documents = DOCUMENTS.clone();
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await;
+
+    let expected_response = json!({
+        "message": "`_geo` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:13 _geo = Glass",
+        "code": "invalid_similar_filter",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
+    });
+    index
+        .similar(json!({"id": 287947, "filter": "_geo = Glass"}), |response, code| {
+            assert_eq!(response, expected_response);
+            assert_eq!(code, 400);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn filter_reserved_attribute_array() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let documents = DOCUMENTS.clone();
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await;
+
+    let expected_response = json!({
+        "message": "`_geoDistance` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:21 _geoDistance = Glass",
+        "code": "invalid_similar_filter",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
+    });
+    index
+        .similar(json!({"id": 287947, "filter": ["_geoDistance = Glass"]}), |response, code| {
+            assert_eq!(response, expected_response);
+            assert_eq!(code, 400);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn filter_reserved_attribute_string() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let documents = DOCUMENTS.clone();
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await;
+
+    let expected_response = json!({
+       "message": "`_geoDistance` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:21 _geoDistance = Glass",
+        "code": "invalid_similar_filter",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
+    });
+    index
+        .similar(json!({"id": 287947, "filter": "_geoDistance = Glass"}), |response, code| {
+            assert_eq!(response, expected_response);
+            assert_eq!(code, 400);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn filter_reserved_geo_point_array() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let documents = DOCUMENTS.clone();
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await;
+
+    let expected_response = json!({
+        "message": "`_geoPoint` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:18 _geoPoint = Glass",
+        "code": "invalid_similar_filter",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
+    });
+    index
+        .similar(json!({"id": 287947, "filter": ["_geoPoint = Glass"]}), |response, code| {
+            assert_eq!(response, expected_response);
+            assert_eq!(code, 400);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn filter_reserved_geo_point_string() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    server.set_features(json!({"vectorStore": true})).await;
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let documents = DOCUMENTS.clone();
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await;
+
+    let expected_response = json!({
+       "message": "`_geoPoint` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance)` or `_geoBoundingBox([latitude, longitude], [latitude, longitude])` built-in rules to filter on `_geo` coordinates.\n1:18 _geoPoint = Glass",
+        "code": "invalid_similar_filter",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
+    });
+    index
+        .similar(json!({"id": 287947, "filter": "_geoPoint = Glass"}), |response, code| {
+            assert_eq!(response, expected_response);
+            assert_eq!(code, 400);
+        })
+        .await;
+}

meilisearch/tests/similar/mod.rs

@@ -0,0 +1,602 @@
+mod errors;
+
+use meili_snap::{json_string, snapshot};
+use once_cell::sync::Lazy;
+
+use crate::common::{Server, Value};
+use crate::json;
+
+static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
+    json!([
+        {
+            "title": "Shazam!",
+            "release_year": 2019,
+            "id": "287947",
+            // Three semantic properties:
+            // 1. magic, anything that reminds you of magic
+            // 2. authority, anything that inspires command
+            // 3. horror, anything that inspires fear or dread
+            "_vectors": { "manual": [0.8, 0.4, -0.5]},
+        },
+        {
+            "title": "Captain Marvel",
+            "release_year": 2019,
+            "id": "299537",
+            "_vectors": { "manual": [0.6, 0.8, -0.2] },
+        },
+        {
+            "title": "Escape Room",
+            "release_year": 2019,
+            "id": "522681",
+            "_vectors": { "manual": [0.1, 0.6, 0.8] },
+        },
+        {
+            "title": "How to Train Your Dragon: The Hidden World",
+            "release_year": 2019,
+            "id": "166428",
+            "_vectors": { "manual": [0.7, 0.7, -0.4] },
+        },
+        {
+            "title": "All Quiet on the Western Front",
+            "release_year": 1930,
+            "id": "143",
+            "_vectors": { "manual": [-0.5, 0.3, 0.85] },
+        }
+    ])
+});
+
+#[actix_rt::test]
+async fn basic() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(value, @r###"
+    {
+      "vectorStore": true,
+      "metrics": false,
+      "logsRoute": false
+    }
+    "###);
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let documents = DOCUMENTS.clone();
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await;
+
+    index
+        .similar(json!({"id": 143}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "title": "Escape Room",
+                "release_year": 2019,
+                "id": "522681",
+                "_vectors": {
+                  "manual": [
+                    0.1,
+                    0.6,
+                    0.8
+                  ]
+                }
+              },
+              {
+                "title": "Captain Marvel",
+                "release_year": 2019,
+                "id": "299537",
+                "_vectors": {
+                  "manual": [
+                    0.6,
+                    0.8,
+                    -0.2
+                  ]
+                }
+              },
+              {
+                "title": "How to Train Your Dragon: The Hidden World",
+                "release_year": 2019,
+                "id": "166428",
+                "_vectors": {
+                  "manual": [
+                    0.7,
+                    0.7,
+                    -0.4
+                  ]
+                }
+              },
+              {
+                "title": "Shazam!",
+                "release_year": 2019,
+                "id": "287947",
+                "_vectors": {
+                  "manual": [
+                    0.8,
+                    0.4,
+                    -0.5
+                  ]
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+
+    index
+        .similar(json!({"id": "299537"}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "title": "How to Train Your Dragon: The Hidden World",
+                "release_year": 2019,
+                "id": "166428",
+                "_vectors": {
+                  "manual": [
+                    0.7,
+                    0.7,
+                    -0.4
+                  ]
+                }
+              },
+              {
+                "title": "Shazam!",
+                "release_year": 2019,
+                "id": "287947",
+                "_vectors": {
+                  "manual": [
+                    0.8,
+                    0.4,
+                    -0.5
+                  ]
+                }
+              },
+              {
+                "title": "Escape Room",
+                "release_year": 2019,
+                "id": "522681",
+                "_vectors": {
+                  "manual": [
+                    0.1,
+                    0.6,
+                    0.8
+                  ]
+                }
+              },
+              {
+                "title": "All Quiet on the Western Front",
+                "release_year": 1930,
+                "id": "143",
+                "_vectors": {
+                  "manual": [
+                    -0.5,
+                    0.3,
+                    0.85
+                  ]
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn ranking_score_threshold() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(value, @r###"
+    {
+      "vectorStore": true,
+      "metrics": false,
+      "logsRoute": false
+    }
+    "###);
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let documents = DOCUMENTS.clone();
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await;
+
+    index
+        .similar(
+            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0}),
+            |response, code| {
+                snapshot!(code, @"200 OK");
+                meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"4");
+                snapshot!(json_string!(response["hits"]), @r###"
+                [
+                  {
+                    "title": "Escape Room",
+                    "release_year": 2019,
+                    "id": "522681",
+                    "_vectors": {
+                      "manual": [
+                        0.1,
+                        0.6,
+                        0.8
+                      ]
+                    },
+                    "_rankingScore": 0.890957772731781
+                  },
+                  {
+                    "title": "Captain Marvel",
+                    "release_year": 2019,
+                    "id": "299537",
+                    "_vectors": {
+                      "manual": [
+                        0.6,
+                        0.8,
+                        -0.2
+                      ]
+                    },
+                    "_rankingScore": 0.39060014486312866
+                  },
+                  {
+                    "title": "How to Train Your Dragon: The Hidden World",
+                    "release_year": 2019,
+                    "id": "166428",
+                    "_vectors": {
+                      "manual": [
+                        0.7,
+                        0.7,
+                        -0.4
+                      ]
+                    },
+                    "_rankingScore": 0.2819308042526245
+                  },
+                  {
+                    "title": "Shazam!",
+                    "release_year": 2019,
+                    "id": "287947",
+                    "_vectors": {
+                      "manual": [
+                        0.8,
+                        0.4,
+                        -0.5
+                      ]
+                    },
+                    "_rankingScore": 0.1662663221359253
+                  }
+                ]
+                "###);
+            },
+        )
+        .await;
+
+    index
+        .similar(
+            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.2}),
+            |response, code| {
+                snapshot!(code, @"200 OK");
+                meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"3");
+                snapshot!(json_string!(response["hits"]), @r###"
+                [
+                  {
+                    "title": "Escape Room",
+                    "release_year": 2019,
+                    "id": "522681",
+                    "_vectors": {
+                      "manual": [
+                        0.1,
+                        0.6,
+                        0.8
+                      ]
+                    },
+                    "_rankingScore": 0.890957772731781
+                  },
+                  {
+                    "title": "Captain Marvel",
+                    "release_year": 2019,
+                    "id": "299537",
+                    "_vectors": {
+                      "manual": [
+                        0.6,
+                        0.8,
+                        -0.2
+                      ]
+                    },
+                    "_rankingScore": 0.39060014486312866
+                  },
+                  {
+                    "title": "How to Train Your Dragon: The Hidden World",
+                    "release_year": 2019,
+                    "id": "166428",
+                    "_vectors": {
+                      "manual": [
+                        0.7,
+                        0.7,
+                        -0.4
+                      ]
+                    },
+                    "_rankingScore": 0.2819308042526245
+                  }
+                ]
+                "###);
+            },
+        )
+        .await;
+
+    index
+        .similar(
+            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.3}),
+            |response, code| {
+                snapshot!(code, @"200 OK");
+                meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"2");
+                snapshot!(json_string!(response["hits"]), @r###"
+                [
+                  {
+                    "title": "Escape Room",
+                    "release_year": 2019,
+                    "id": "522681",
+                    "_vectors": {
+                      "manual": [
+                        0.1,
+                        0.6,
+                        0.8
+                      ]
+                    },
+                    "_rankingScore": 0.890957772731781
+                  },
+                  {
+                    "title": "Captain Marvel",
+                    "release_year": 2019,
+                    "id": "299537",
+                    "_vectors": {
+                      "manual": [
+                        0.6,
+                        0.8,
+                        -0.2
+                      ]
+                    },
+                    "_rankingScore": 0.39060014486312866
+                  }
+                ]
+                "###);
+            },
+        )
+        .await;
+
+    index
+        .similar(
+            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.6}),
+            |response, code| {
+                snapshot!(code, @"200 OK");
+                meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"1");
+                snapshot!(json_string!(response["hits"]), @r###"
+                [
+                  {
+                    "title": "Escape Room",
+                    "release_year": 2019,
+                    "id": "522681",
+                    "_vectors": {
+                      "manual": [
+                        0.1,
+                        0.6,
+                        0.8
+                      ]
+                    },
+                    "_rankingScore": 0.890957772731781
+                  }
+                ]
+                "###);
+            },
+        )
+        .await;
+
+    index
+        .similar(
+            json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.9}),
+            |response, code| {
+                snapshot!(code, @"200 OK");
+                snapshot!(json_string!(response["hits"]), @"[]");
+            },
+        )
+        .await;
+}
+
+#[actix_rt::test]
+async fn filter() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(value, @r###"
+    {
+      "vectorStore": true,
+      "metrics": false,
+      "logsRoute": false
+    }
+    "###);
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title", "release_year"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let documents = DOCUMENTS.clone();
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await;
+
+    index
+        .similar(json!({"id": 522681, "filter": "release_year = 2019"}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "title": "Captain Marvel",
+                "release_year": 2019,
+                "id": "299537",
+                "_vectors": {
+                  "manual": [
+                    0.6,
+                    0.8,
+                    -0.2
+                  ]
+                }
+              },
+              {
+                "title": "How to Train Your Dragon: The Hidden World",
+                "release_year": 2019,
+                "id": "166428",
+                "_vectors": {
+                  "manual": [
+                    0.7,
+                    0.7,
+                    -0.4
+                  ]
+                }
+              },
+              {
+                "title": "Shazam!",
+                "release_year": 2019,
+                "id": "287947",
+                "_vectors": {
+                  "manual": [
+                    0.8,
+                    0.4,
+                    -0.5
+                  ]
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+
+    index
+        .similar(json!({"id": 522681, "filter": "release_year < 2000"}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "title": "All Quiet on the Western Front",
+                "release_year": 1930,
+                "id": "143",
+                "_vectors": {
+                  "manual": [
+                    -0.5,
+                    0.3,
+                    0.85
+                  ]
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+}
+
+#[actix_rt::test]
+async fn limit_and_offset() {
+    let server = Server::new().await;
+    let index = server.index("test");
+    let (value, code) = server.set_features(json!({"vectorStore": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(value, @r###"
+    {
+      "vectorStore": true,
+      "metrics": false,
+      "logsRoute": false
+    }
+    "###);
+
+    let (response, code) = index
+        .update_settings(json!({
+        "embedders": {
+            "manual": {
+                "source": "userProvided",
+                "dimensions": 3,
+            }
+        },
+        "filterableAttributes": ["title"]}))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await;
+
+    let documents = DOCUMENTS.clone();
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    index.wait_task(value.uid()).await;
+
+    index
+        .similar(json!({"id": 143, "limit": 1}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "title": "Escape Room",
+                "release_year": 2019,
+                "id": "522681",
+                "_vectors": {
+                  "manual": [
+                    0.1,
+                    0.6,
+                    0.8
+                  ]
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+
+    index
+        .similar(json!({"id": 143, "limit": 1, "offset": 1}), |response, code| {
+            snapshot!(code, @"200 OK");
+            snapshot!(json_string!(response["hits"]), @r###"
+            [
+              {
+                "title": "Captain Marvel",
+                "release_year": 2019,
+                "id": "299537",
+                "_vectors": {
+                  "manual": [
+                    0.6,
+                    0.8,
+                    -0.2
+                  ]
+                }
+              }
+            ]
+            "###);
+        })
+        .await;
+}

meilisearch/tests/snapshot/mod.rs

@@ -31,6 +31,7 @@ macro_rules! verify_snapshot {
 }
 
 #[actix_rt::test]
+#[cfg_attr(target_os = "windows", ignore)]
 async fn perform_snapshot() {
     let temp = tempfile::tempdir().unwrap();
     let snapshot_dir = tempfile::tempdir().unwrap();

milli/Cargo.toml

@@ -17,7 +17,7 @@ bincode = "1.3.3"
 bstr = "1.9.0"
 bytemuck = { version = "1.14.0", features = ["extern_crate_alloc"] }
 byteorder = "1.5.0"
-charabia = { version = "0.8.10", default-features = false }
+charabia = { version = "0.8.11", default-features = false }
 concat-arrays = "0.1.2"
 crossbeam-channel = "0.5.11"
 deserr = "0.6.1"
@@ -67,9 +67,6 @@ filter-parser = { path = "../filter-parser" }
 # documents words self-join
 itertools = "0.11.0"
 
-# profiling
-puffin = "0.16.0"
-
 csv = "1.3.0"
 candle-core = { version = "0.4.1" }
 candle-transformers = { version = "0.4.1" }

milli/examples/search.rs

@@ -49,7 +49,7 @@ fn main() -> Result<(), Box<dyn Error>> {
             let start = Instant::now();
 
             let mut ctx = SearchContext::new(&index, &txn)?;
-            let universe = filtered_universe(&ctx, &None)?;
+            let universe = filtered_universe(ctx.index, ctx.txn, &None)?;
 
             let docs = execute_search(
                 &mut ctx,
@@ -66,6 +66,7 @@ fn main() -> Result<(), Box<dyn Error>> {
                 &mut DefaultSearchLogger,
                 logger,
                 TimeBudget::max(),
+                None,
             )?;
             if let Some((logger, dir)) = detailed_logger {
                 logger.finish(&mut ctx, Path::new(dir))?;

milli/src/documents/mod.rs

@@ -12,7 +12,10 @@ use bimap::BiHashMap;
 pub use builder::DocumentsBatchBuilder;
 pub use enriched::{EnrichedDocument, EnrichedDocumentsBatchCursor, EnrichedDocumentsBatchReader};
 use obkv::KvReader;
-pub use primary_key::{DocumentIdExtractionError, FieldIdMapper, PrimaryKey, DEFAULT_PRIMARY_KEY};
+pub use primary_key::{
+    validate_document_id_value, DocumentIdExtractionError, FieldIdMapper, PrimaryKey,
+    DEFAULT_PRIMARY_KEY,
+};
 pub use reader::{DocumentsBatchCursor, DocumentsBatchCursorError, DocumentsBatchReader};
 use serde::{Deserialize, Serialize};
 

milli/src/documents/primary_key.rs

@@ -60,7 +60,7 @@ impl<'a> PrimaryKey<'a> {
                 Some(document_id_bytes) => {
                     let document_id = serde_json::from_slice(document_id_bytes)
                         .map_err(InternalError::SerdeJson)?;
-                    match validate_document_id_value(document_id)? {
+                    match validate_document_id_value(document_id) {
                         Ok(document_id) => Ok(Ok(document_id)),
                         Err(user_error) => {
                             Ok(Err(DocumentIdExtractionError::InvalidDocumentId(user_error)))
@@ -88,7 +88,7 @@ impl<'a> PrimaryKey<'a> {
                 }
 
                 match matching_documents_ids.pop() {
-                    Some(document_id) => match validate_document_id_value(document_id)? {
+                    Some(document_id) => match validate_document_id_value(document_id) {
                         Ok(document_id) => Ok(Ok(document_id)),
                         Err(user_error) => {
                             Ok(Err(DocumentIdExtractionError::InvalidDocumentId(user_error)))
@@ -159,14 +159,14 @@ fn validate_document_id(document_id: &str) -> Option<&str> {
     }
 }
 
-pub fn validate_document_id_value(document_id: Value) -> Result<StdResult<String, UserError>> {
+pub fn validate_document_id_value(document_id: Value) -> StdResult<String, UserError> {
     match document_id {
         Value::String(string) => match validate_document_id(&string) {
-            Some(s) if s.len() == string.len() => Ok(Ok(string)),
-            Some(s) => Ok(Ok(s.to_string())),
-            None => Ok(Err(UserError::InvalidDocumentId { document_id: Value::String(string) })),
+            Some(s) if s.len() == string.len() => Ok(string),
+            Some(s) => Ok(s.to_string()),
+            None => Err(UserError::InvalidDocumentId { document_id: Value::String(string) }),
         },
-        Value::Number(number) if number.is_i64() => Ok(Ok(number.to_string())),
-        content => Ok(Err(UserError::InvalidDocumentId { document_id: content })),
+        Value::Number(number) if number.is_i64() => Ok(number.to_string()),
+        content => Err(UserError::InvalidDocumentId { document_id: content }),
     }
 }

milli/src/error.rs

@@ -117,10 +117,8 @@ only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and undersco
     InvalidGeoField(#[from] GeoError),
     #[error("Invalid vector dimensions: expected: `{}`, found: `{}`.", .expected, .found)]
     InvalidVectorDimensions { expected: usize, found: usize },
-    #[error("The `_vectors.{subfield}` field in the document with id: `{document_id}` is not an array. Was expecting an array of floats or an array of arrays of floats but instead got `{value}`.")]
-    InvalidVectorsType { document_id: Value, value: Value, subfield: String },
     #[error("The `_vectors` field in the document with id: `{document_id}` is not an object. Was expecting an object with a key for each embedder with manually provided vectors, but instead got `{value}`")]
-    InvalidVectorsMapType { document_id: Value, value: Value },
+    InvalidVectorsMapType { document_id: String, value: Value },
     #[error("{0}")]
     InvalidFilter(String),
     #[error("Invalid type for filter subexpression: expected: {}, found: {1}.", .0.join(", "))]

milli/src/heed_codec/facet/mod.rs

@@ -47,6 +47,12 @@ pub struct FacetGroupValue {
     pub bitmap: RoaringBitmap,
 }
 
+#[derive(Debug)]
+pub struct FacetGroupLazyValue<'b> {
+    pub size: u8,
+    pub bitmap_bytes: &'b [u8],
+}
+
 pub struct FacetGroupKeyCodec<T> {
     _phantom: PhantomData<T>,
 }
@@ -69,6 +75,7 @@ where
         Ok(Cow::Owned(v))
     }
 }
+
 impl<'a, T> heed::BytesDecode<'a> for FacetGroupKeyCodec<T>
 where
     T: BytesDecode<'a>,
@@ -84,6 +91,7 @@ where
 }
 
 pub struct FacetGroupValueCodec;
+
 impl<'a> heed::BytesEncode<'a> for FacetGroupValueCodec {
     type EItem = FacetGroupValue;
 
@@ -93,11 +101,23 @@ impl<'a> heed::BytesEncode<'a> for FacetGroupValueCodec {
         Ok(Cow::Owned(v))
     }
 }
+
 impl<'a> heed::BytesDecode<'a> for FacetGroupValueCodec {
     type DItem = FacetGroupValue;
+
     fn bytes_decode(bytes: &'a [u8]) -> Result<Self::DItem, BoxedError> {
         let size = bytes[0];
         let bitmap = CboRoaringBitmapCodec::deserialize_from(&bytes[1..])?;
         Ok(FacetGroupValue { size, bitmap })
     }
 }
+
+pub struct FacetGroupLazyValueCodec;
+
+impl<'a> heed::BytesDecode<'a> for FacetGroupLazyValueCodec {
+    type DItem = FacetGroupLazyValue<'a>;
+
+    fn bytes_decode(bytes: &'a [u8]) -> Result<Self::DItem, BoxedError> {
+        Ok(FacetGroupLazyValue { size: bytes[0], bitmap_bytes: &bytes[1..] })
+    }
+}

milli/src/heed_codec/roaring_bitmap/cbo_roaring_bitmap_codec.rs

@@ -1,5 +1,5 @@
 use std::borrow::Cow;
-use std::io;
+use std::io::{self, Cursor};
 use std::mem::size_of;
 
 use byteorder::{NativeEndian, ReadBytesExt, WriteBytesExt};
@@ -57,6 +57,24 @@ impl CboRoaringBitmapCodec {
         }
     }
 
+    pub fn intersection_with_serialized(
+        mut bytes: &[u8],
+        other: &RoaringBitmap,
+    ) -> io::Result<RoaringBitmap> {
+        // See above `deserialize_from` method for implementation details.
+        if bytes.len() <= THRESHOLD * size_of::<u32>() {
+            let mut bitmap = RoaringBitmap::new();
+            while let Ok(integer) = bytes.read_u32::<NativeEndian>() {
+                if other.contains(integer) {
+                    bitmap.insert(integer);
+                }
+            }
+            Ok(bitmap)
+        } else {
+            other.intersection_with_serialized_unchecked(Cursor::new(bytes))
+        }
+    }
+
     /// Merge serialized CboRoaringBitmaps in a buffer.
     ///
     /// if the merged values length is under the threshold, values are directly
@@ -195,7 +213,7 @@ mod tests {
     fn merge_cbo_roaring_bitmaps() {
         let mut buffer = Vec::new();
 
-        let small_data = vec![
+        let small_data = [
             RoaringBitmap::from_sorted_iter(1..4).unwrap(),
             RoaringBitmap::from_sorted_iter(2..5).unwrap(),
             RoaringBitmap::from_sorted_iter(4..6).unwrap(),
@@ -209,7 +227,7 @@ mod tests {
         let expected = RoaringBitmap::from_sorted_iter(1..6).unwrap();
         assert_eq!(bitmap, expected);
 
-        let medium_data = vec![
+        let medium_data = [
             RoaringBitmap::from_sorted_iter(1..4).unwrap(),
             RoaringBitmap::from_sorted_iter(2..5).unwrap(),
             RoaringBitmap::from_sorted_iter(4..8).unwrap(),

milli/src/index.rs

@@ -23,7 +23,7 @@ use crate::heed_codec::{
 };
 use crate::order_by_map::OrderByMap;
 use crate::proximity::ProximityPrecision;
-use crate::vector::EmbeddingConfig;
+use crate::vector::{Embedding, EmbeddingConfig};
 use crate::{
     default_criteria, CboRoaringBitmapCodec, Criterion, DocumentId, ExternalDocumentsIds,
     FacetDistribution, FieldDistribution, FieldId, FieldIdMapMissingEntry, FieldIdWordCountCodec,
@@ -1595,6 +1595,22 @@ impl Index {
             .unwrap_or_default())
     }
 
+    pub fn arroy_readers<'a>(
+        &'a self,
+        rtxn: &'a RoTxn<'a>,
+        embedder_id: u8,
+    ) -> impl Iterator<Item = Result<arroy::Reader<arroy::distances::Angular>>> + 'a {
+        crate::vector::arroy_db_range_for_embedder(embedder_id).map_while(move |k| {
+            arroy::Reader::open(rtxn, k, self.vector_arroy)
+                .map(Some)
+                .or_else(|e| match e {
+                    arroy::Error::MissingMetadata => Ok(None),
+                    e => Err(e.into()),
+                })
+                .transpose()
+        })
+    }
+
     pub(crate) fn put_search_cutoff(&self, wtxn: &mut RwTxn<'_>, cutoff: u64) -> heed::Result<()> {
         self.main.remap_types::<Str, BEU64>().put(wtxn, main_key::SEARCH_CUTOFF, &cutoff)
     }
@@ -1606,6 +1622,44 @@ impl Index {
     pub(crate) fn delete_search_cutoff(&self, wtxn: &mut RwTxn<'_>) -> heed::Result<bool> {
         self.main.remap_key_type::<Str>().delete(wtxn, main_key::SEARCH_CUTOFF)
     }
+
+    pub fn embeddings(
+        &self,
+        rtxn: &RoTxn<'_>,
+        docid: DocumentId,
+    ) -> Result<BTreeMap<String, Vec<Embedding>>> {
+        let mut res = BTreeMap::new();
+        for row in self.embedder_category_id.iter(rtxn)? {
+            let (embedder_name, embedder_id) = row?;
+            let embedder_id = (embedder_id as u16) << 8;
+            let mut embeddings = Vec::new();
+            'vectors: for i in 0..=u8::MAX {
+                let reader = arroy::Reader::open(rtxn, embedder_id | (i as u16), self.vector_arroy)
+                    .map(Some)
+                    .or_else(|e| match e {
+                        arroy::Error::MissingMetadata => Ok(None),
+                        e => Err(e),
+                    })
+                    .transpose();
+
+                let Some(reader) = reader else {
+                    break 'vectors;
+                };
+
+                let embedding = reader?.item_vector(rtxn, docid)?;
+                if let Some(embedding) = embedding {
+                    embeddings.push(embedding)
+                } else {
+                    break 'vectors;
+                }
+            }
+
+            if !embeddings.is_empty() {
+                res.insert(embedder_name.to_owned(), embeddings);
+            }
+        }
+        Ok(res)
+    }
 }
 
 #[cfg(test)]

milli/src/lib.rs

@@ -63,6 +63,7 @@ pub use self::heed_codec::{
 };
 pub use self::index::Index;
 pub use self::search::facet::{FacetValueHit, SearchForFacetValues};
+pub use self::search::similar::Similar;
 pub use self::search::{
     FacetDistribution, Filter, FormatOptions, MatchBounds, MatcherBuilder, MatchingWords, OrderBy,
     Search, SearchResult, SemanticSearch, TermsMatchingStrategy, DEFAULT_VALUES_PER_FACET,
@@ -354,43 +355,13 @@ pub fn is_faceted(field: &str, faceted_fields: impl IntoIterator<Item = impl AsR
 /// assert!(!is_faceted_by("animaux.chien", "animaux.chie"));
 /// ```
 pub fn is_faceted_by(field: &str, facet: &str) -> bool {
-    field.starts_with(facet)
-        && field[facet.len()..].chars().next().map(|c| c == '.').unwrap_or(true)
+    field.starts_with(facet) && field[facet.len()..].chars().next().map_or(true, |c| c == '.')
 }
 
 pub fn normalize_facet(original: &str) -> String {
     CompatibilityDecompositionNormalizer.normalize_str(original.trim()).to_lowercase()
 }
 
-/// Represents either a vector or an array of multiple vectors.
-#[derive(serde::Serialize, serde::Deserialize, Debug)]
-#[serde(transparent)]
-pub struct VectorOrArrayOfVectors {
-    #[serde(with = "either::serde_untagged_optional")]
-    inner: Option<either::Either<Vec<f32>, Vec<Vec<f32>>>>,
-}
-
-impl VectorOrArrayOfVectors {
-    pub fn into_array_of_vectors(self) -> Option<Vec<Vec<f32>>> {
-        match self.inner? {
-            either::Either::Left(vector) => Some(vec![vector]),
-            either::Either::Right(vectors) => Some(vectors),
-        }
-    }
-}
-
-/// Normalize a vector by dividing the dimensions by the length of it.
-pub fn normalize_vector(mut vector: Vec<f32>) -> Vec<f32> {
-    let squared: f32 = vector.iter().map(|x| x * x).sum();
-    let length = squared.sqrt();
-    if length <= f32::EPSILON {
-        vector
-    } else {
-        vector.iter_mut().for_each(|x| *x /= length);
-        vector
-    }
-}
-
 #[cfg(test)]
 mod tests {
     use serde_json::json;

milli/src/search/facet/facet_distribution_iter.rs

@@ -38,7 +38,7 @@ where
         field_id,
     )?;
 
-    if let Some(first_bound) = get_first_facet_value::<BytesRefCodec>(rtxn, db, field_id)? {
+    if let Some(first_bound) = get_first_facet_value::<BytesRefCodec, _>(rtxn, db, field_id)? {
         fd.iterate(candidates, highest_level, first_bound, usize::MAX)?;
         Ok(())
     } else {
@@ -81,7 +81,7 @@ where
         field_id,
     )?;
 
-    if let Some(first_bound) = get_first_facet_value::<BytesRefCodec>(rtxn, db, field_id)? {
+    if let Some(first_bound) = get_first_facet_value::<BytesRefCodec, _>(rtxn, db, field_id)? {
         // We first fill the heap with values from the highest level
         let starting_key =
             FacetGroupKey { field_id, level: highest_level, left_bound: first_bound };

milli/src/search/facet/facet_range_search.rs

@@ -4,9 +4,11 @@ use heed::BytesEncode;
 use roaring::RoaringBitmap;
 
 use super::{get_first_facet_value, get_highest_level, get_last_facet_value};
-use crate::heed_codec::facet::{FacetGroupKey, FacetGroupKeyCodec, FacetGroupValueCodec};
+use crate::heed_codec::facet::{
+    FacetGroupKey, FacetGroupKeyCodec, FacetGroupLazyValueCodec, FacetGroupValueCodec,
+};
 use crate::heed_codec::BytesRefCodec;
-use crate::Result;
+use crate::{CboRoaringBitmapCodec, Result};
 
 /// Find all the document ids for which the given field contains a value contained within
 /// the two bounds.
@@ -16,6 +18,7 @@ pub fn find_docids_of_facet_within_bounds<'t, BoundCodec>(
     field_id: u16,
     left: &'t Bound<<BoundCodec as BytesEncode<'t>>::EItem>,
     right: &'t Bound<<BoundCodec as BytesEncode<'t>>::EItem>,
+    universe: Option<&RoaringBitmap>,
     docids: &mut RoaringBitmap,
 ) -> Result<()>
 where
@@ -46,13 +49,15 @@ where
         }
         Bound::Unbounded => Bound::Unbounded,
     };
-    let db = db.remap_key_type::<FacetGroupKeyCodec<BytesRefCodec>>();
-    let mut f = FacetRangeSearch { rtxn, db, field_id, left, right, docids };
+    let db = db.remap_types::<FacetGroupKeyCodec<BytesRefCodec>, FacetGroupLazyValueCodec>();
+    let mut f = FacetRangeSearch { rtxn, db, field_id, left, right, universe, docids };
     let highest_level = get_highest_level(rtxn, db, field_id)?;
 
-    if let Some(starting_left_bound) = get_first_facet_value::<BytesRefCodec>(rtxn, db, field_id)? {
+    if let Some(starting_left_bound) =
+        get_first_facet_value::<BytesRefCodec, _>(rtxn, db, field_id)?
+    {
         let rightmost_bound =
-            Bound::Included(get_last_facet_value::<BytesRefCodec>(rtxn, db, field_id)?.unwrap()); // will not fail because get_first_facet_value succeeded
+            Bound::Included(get_last_facet_value::<BytesRefCodec, _>(rtxn, db, field_id)?.unwrap()); // will not fail because get_first_facet_value succeeded
         let group_size = usize::MAX;
         f.run(highest_level, starting_left_bound, rightmost_bound, group_size)?;
         Ok(())
@@ -64,12 +69,16 @@ where
 /// Fetch the document ids that have a facet with a value between the two given bounds
 struct FacetRangeSearch<'t, 'b, 'bitmap> {
     rtxn: &'t heed::RoTxn<'t>,
-    db: heed::Database<FacetGroupKeyCodec<BytesRefCodec>, FacetGroupValueCodec>,
+    db: heed::Database<FacetGroupKeyCodec<BytesRefCodec>, FacetGroupLazyValueCodec>,
     field_id: u16,
     left: Bound<&'b [u8]>,
     right: Bound<&'b [u8]>,
+    /// The subset of documents ids that are useful for this search.
+    /// Great performance optimizations can be achieved by only fetching values matching this subset.
+    universe: Option<&'bitmap RoaringBitmap>,
     docids: &'bitmap mut RoaringBitmap,
 }
+
 impl<'t, 'b, 'bitmap> FacetRangeSearch<'t, 'b, 'bitmap> {
     fn run_level_0(&mut self, starting_left_bound: &'t [u8], group_size: usize) -> Result<()> {
         let left_key =
@@ -104,7 +113,13 @@ impl<'t, 'b, 'bitmap> FacetRangeSearch<'t, 'b, 'bitmap> {
             }
 
             if RangeBounds::<&[u8]>::contains(&(self.left, self.right), &key.left_bound) {
-                *self.docids |= value.bitmap;
+                *self.docids |= match self.universe {
+                    Some(universe) => CboRoaringBitmapCodec::intersection_with_serialized(
+                        value.bitmap_bytes,
+                        universe,
+                    )?,
+                    None => CboRoaringBitmapCodec::deserialize_from(value.bitmap_bytes)?,
+                };
             }
         }
         Ok(())
@@ -195,7 +210,13 @@ impl<'t, 'b, 'bitmap> FacetRangeSearch<'t, 'b, 'bitmap> {
                 left_condition && right_condition
             };
             if should_take_whole_group {
-                *self.docids |= &previous_value.bitmap;
+                *self.docids |= match self.universe {
+                    Some(universe) => CboRoaringBitmapCodec::intersection_with_serialized(
+                        previous_value.bitmap_bytes,
+                        universe,
+                    )?,
+                    None => CboRoaringBitmapCodec::deserialize_from(previous_value.bitmap_bytes)?,
+                };
                 previous_key = next_key;
                 previous_value = next_value;
                 continue;
@@ -291,7 +312,13 @@ impl<'t, 'b, 'bitmap> FacetRangeSearch<'t, 'b, 'bitmap> {
             left_condition && right_condition
         };
         if should_take_whole_group {
-            *self.docids |= &previous_value.bitmap;
+            *self.docids |= match self.universe {
+                Some(universe) => CboRoaringBitmapCodec::intersection_with_serialized(
+                    previous_value.bitmap_bytes,
+                    universe,
+                )?,
+                None => CboRoaringBitmapCodec::deserialize_from(previous_value.bitmap_bytes)?,
+            };
         } else {
             let level = level - 1;
             let starting_left_bound = previous_key.left_bound;
@@ -365,6 +392,7 @@ mod tests {
                     0,
                     &start,
                     &end,
+                    None,
                     &mut docids,
                 )
                 .unwrap();
@@ -384,6 +412,7 @@ mod tests {
                     0,
                     &start,
                     &end,
+                    None,
                     &mut docids,
                 )
                 .unwrap();
@@ -418,6 +447,7 @@ mod tests {
                     0,
                     &start,
                     &end,
+                    None,
                     &mut docids,
                 )
                 .unwrap();
@@ -439,6 +469,7 @@ mod tests {
                     0,
                     &start,
                     &end,
+                    None,
                     &mut docids,
                 )
                 .unwrap();
@@ -474,6 +505,7 @@ mod tests {
                     0,
                     &start,
                     &end,
+                    None,
                     &mut docids,
                 )
                 .unwrap();
@@ -499,6 +531,7 @@ mod tests {
                     0,
                     &start,
                     &end,
+                    None,
                     &mut docids,
                 )
                 .unwrap();
@@ -537,6 +570,7 @@ mod tests {
                     0,
                     &start,
                     &end,
+                    None,
                     &mut docids,
                 )
                 .unwrap();
@@ -556,6 +590,7 @@ mod tests {
                     0,
                     &start,
                     &end,
+                    None,
                     &mut docids,
                 )
                 .unwrap();
@@ -571,6 +606,7 @@ mod tests {
                 0,
                 &Bound::Unbounded,
                 &Bound::Unbounded,
+                None,
                 &mut docids,
             )
             .unwrap();
@@ -586,6 +622,7 @@ mod tests {
                 1,
                 &Bound::Unbounded,
                 &Bound::Unbounded,
+                None,
                 &mut docids,
             )
             .unwrap();
@@ -621,6 +658,7 @@ mod tests {
                     0,
                     &start,
                     &end,
+                    None,
                     &mut docids,
                 )
                 .unwrap();
@@ -634,6 +672,7 @@ mod tests {
                     1,
                     &start,
                     &end,
+                    None,
                     &mut docids,
                 )
                 .unwrap();

milli/src/search/facet/facet_sort_ascending.rs

@@ -36,7 +36,7 @@ pub fn ascending_facet_sort<'t>(
     candidates: RoaringBitmap,
 ) -> Result<impl Iterator<Item = Result<(RoaringBitmap, &'t [u8])>> + 't> {
     let highest_level = get_highest_level(rtxn, db, field_id)?;
-    if let Some(first_bound) = get_first_facet_value::<BytesRefCodec>(rtxn, db, field_id)? {
+    if let Some(first_bound) = get_first_facet_value::<BytesRefCodec, _>(rtxn, db, field_id)? {
         let first_key = FacetGroupKey { field_id, level: highest_level, left_bound: first_bound };
         let iter = db.range(rtxn, &(first_key..)).unwrap().take(usize::MAX);
 

milli/src/search/facet/facet_sort_descending.rs

@@ -19,9 +19,9 @@ pub fn descending_facet_sort<'t>(
     candidates: RoaringBitmap,
 ) -> Result<impl Iterator<Item = Result<(RoaringBitmap, &'t [u8])>> + 't> {
     let highest_level = get_highest_level(rtxn, db, field_id)?;
-    if let Some(first_bound) = get_first_facet_value::<BytesRefCodec>(rtxn, db, field_id)? {
+    if let Some(first_bound) = get_first_facet_value::<BytesRefCodec, _>(rtxn, db, field_id)? {
         let first_key = FacetGroupKey { field_id, level: highest_level, left_bound: first_bound };
-        let last_bound = get_last_facet_value::<BytesRefCodec>(rtxn, db, field_id)?.unwrap();
+        let last_bound = get_last_facet_value::<BytesRefCodec, _>(rtxn, db, field_id)?.unwrap();
         let last_key = FacetGroupKey { field_id, level: highest_level, left_bound: last_bound };
         let iter = db.rev_range(rtxn, &(first_key..=last_key))?.take(usize::MAX);
         Ok(itertools::Either::Left(DescendingFacetSort {

milli/src/search/facet/filter.rs

@@ -4,7 +4,7 @@ use std::ops::Bound::{self, Excluded, Included};
 
 use either::Either;
 pub use filter_parser::{Condition, Error as FPError, FilterCondition, Token};
-use roaring::RoaringBitmap;
+use roaring::{MultiOps, RoaringBitmap};
 use serde_json::Value;
 
 use super::facet_range_search;
@@ -224,14 +224,14 @@ impl<'a> Filter<'a> {
     pub fn evaluate(&self, rtxn: &heed::RoTxn, index: &Index) -> Result<RoaringBitmap> {
         // to avoid doing this for each recursive call we're going to do it ONCE ahead of time
         let filterable_fields = index.filterable_fields(rtxn)?;
-
-        self.inner_evaluate(rtxn, index, &filterable_fields)
+        self.inner_evaluate(rtxn, index, &filterable_fields, None)
     }
 
     fn evaluate_operator(
         rtxn: &heed::RoTxn,
         index: &Index,
         field_id: FieldId,
+        universe: Option<&RoaringBitmap>,
         operator: &Condition<'a>,
     ) -> Result<RoaringBitmap> {
         let numbers_db = index.facet_id_f64_docids;
@@ -291,14 +291,22 @@ impl<'a> Filter<'a> {
             }
             Condition::NotEqual(val) => {
                 let operator = Condition::Equal(val.clone());
-                let docids = Self::evaluate_operator(rtxn, index, field_id, &operator)?;
+                let docids = Self::evaluate_operator(rtxn, index, field_id, None, &operator)?;
                 let all_ids = index.documents_ids(rtxn)?;
                 return Ok(all_ids - docids);
             }
         };
 
         let mut output = RoaringBitmap::new();
-        Self::explore_facet_number_levels(rtxn, numbers_db, field_id, left, right, &mut output)?;
+        Self::explore_facet_number_levels(
+            rtxn,
+            numbers_db,
+            field_id,
+            left,
+            right,
+            universe,
+            &mut output,
+        )?;
         Ok(output)
     }
 
@@ -310,6 +318,7 @@ impl<'a> Filter<'a> {
         field_id: FieldId,
         left: Bound<f64>,
         right: Bound<f64>,
+        universe: Option<&RoaringBitmap>,
         output: &mut RoaringBitmap,
     ) -> Result<()> {
         match (left, right) {
@@ -321,7 +330,7 @@ impl<'a> Filter<'a> {
             (_, _) => (),
         }
         facet_range_search::find_docids_of_facet_within_bounds::<OrderedF64Codec>(
-            rtxn, db, field_id, &left, &right, output,
+            rtxn, db, field_id, &left, &right, universe, output,
         )?;
 
         Ok(())
@@ -332,31 +341,37 @@ impl<'a> Filter<'a> {
         rtxn: &heed::RoTxn,
         index: &Index,
         filterable_fields: &HashSet<String>,
+        universe: Option<&RoaringBitmap>,
     ) -> Result<RoaringBitmap> {
+        if universe.map_or(false, |u| u.is_empty()) {
+            return Ok(RoaringBitmap::new());
+        }
+
         match &self.condition {
             FilterCondition::Not(f) => {
-                let all_ids = index.documents_ids(rtxn)?;
                 let selected = Self::inner_evaluate(
                     &(f.as_ref().clone()).into(),
                     rtxn,
                     index,
                     filterable_fields,
+                    universe,
                 )?;
-                Ok(all_ids - selected)
+                match universe {
+                    Some(universe) => Ok(universe - selected),
+                    None => {
+                        let all_ids = index.documents_ids(rtxn)?;
+                        Ok(all_ids - selected)
+                    }
+                }
             }
             FilterCondition::In { fid, els } => {
                 if crate::is_faceted(fid.value(), filterable_fields) {
                     let field_ids_map = index.fields_ids_map(rtxn)?;
-
                     if let Some(fid) = field_ids_map.id(fid.value()) {
-                        let mut bitmap = RoaringBitmap::new();
-
-                        for el in els {
-                            let op = Condition::Equal(el.clone());
-                            let el_bitmap = Self::evaluate_operator(rtxn, index, fid, &op)?;
-                            bitmap |= el_bitmap;
-                        }
-                        Ok(bitmap)
+                        els.iter()
+                            .map(|el| Condition::Equal(el.clone()))
+                            .map(|op| Self::evaluate_operator(rtxn, index, fid, universe, &op))
+                            .union()
                     } else {
                         Ok(RoaringBitmap::new())
                     }
@@ -371,7 +386,7 @@ impl<'a> Filter<'a> {
                 if crate::is_faceted(fid.value(), filterable_fields) {
                     let field_ids_map = index.fields_ids_map(rtxn)?;
                     if let Some(fid) = field_ids_map.id(fid.value()) {
-                        Self::evaluate_operator(rtxn, index, fid, op)
+                        Self::evaluate_operator(rtxn, index, fid, universe, op)
                     } else {
                         Ok(RoaringBitmap::new())
                     }
@@ -382,14 +397,11 @@ impl<'a> Filter<'a> {
                     }))?
                 }
             }
-            FilterCondition::Or(subfilters) => {
-                let mut bitmap = RoaringBitmap::new();
-                for f in subfilters {
-                    bitmap |=
-                        Self::inner_evaluate(&(f.clone()).into(), rtxn, index, filterable_fields)?;
-                }
-                Ok(bitmap)
-            }
+            FilterCondition::Or(subfilters) => subfilters
+                .iter()
+                .cloned()
+                .map(|f| Self::inner_evaluate(&f.into(), rtxn, index, filterable_fields, universe))
+                .union(),
             FilterCondition::And(subfilters) => {
                 let mut subfilters_iter = subfilters.iter();
                 if let Some(first_subfilter) = subfilters_iter.next() {
@@ -398,16 +410,21 @@ impl<'a> Filter<'a> {
                         rtxn,
                         index,
                         filterable_fields,
+                        universe,
                     )?;
                     for f in subfilters_iter {
                         if bitmap.is_empty() {
                             return Ok(bitmap);
                         }
+                        // TODO We are doing the intersections two times,
+                        //      it could be more efficient
+                        //      Can't I just replace this `&=` by an `=`?
                         bitmap &= Self::inner_evaluate(
                             &(f.clone()).into(),
                             rtxn,
                             index,
                             filterable_fields,
+                            Some(&bitmap),
                         )?;
                     }
                     Ok(bitmap)
@@ -507,6 +524,7 @@ impl<'a> Filter<'a> {
                         rtxn,
                         index,
                         filterable_fields,
+                        universe,
                     )?;
 
                     let geo_lng_token = Token::new(
@@ -539,6 +557,7 @@ impl<'a> Filter<'a> {
                             rtxn,
                             index,
                             filterable_fields,
+                            universe,
                         )?;
 
                         let condition_right = FilterCondition::Condition {
@@ -552,6 +571,7 @@ impl<'a> Filter<'a> {
                             rtxn,
                             index,
                             filterable_fields,
+                            universe,
                         )?;
 
                         left | right
@@ -567,6 +587,7 @@ impl<'a> Filter<'a> {
                             rtxn,
                             index,
                             filterable_fields,
+                            universe,
                         )?
                     };
 

milli/src/search/facet/mod.rs

@@ -7,7 +7,7 @@ use roaring::RoaringBitmap;
 pub use self::facet_distribution::{FacetDistribution, OrderBy, DEFAULT_VALUES_PER_FACET};
 pub use self::filter::{BadGeoError, Filter};
 pub use self::search::{FacetValueHit, SearchForFacetValues};
-use crate::heed_codec::facet::{FacetGroupKeyCodec, FacetGroupValueCodec, OrderedF64Codec};
+use crate::heed_codec::facet::{FacetGroupKeyCodec, OrderedF64Codec};
 use crate::heed_codec::BytesRefCodec;
 use crate::{Index, Result};
 
@@ -54,9 +54,9 @@ pub fn facet_max_value<'t>(
 }
 
 /// Get the first facet value in the facet database
-pub(crate) fn get_first_facet_value<'t, BoundCodec>(
+pub(crate) fn get_first_facet_value<'t, BoundCodec, DC>(
     txn: &'t RoTxn,
-    db: heed::Database<FacetGroupKeyCodec<BytesRefCodec>, FacetGroupValueCodec>,
+    db: heed::Database<FacetGroupKeyCodec<BytesRefCodec>, DC>,
     field_id: u16,
 ) -> heed::Result<Option<BoundCodec::DItem>>
 where
@@ -78,9 +78,9 @@ where
 }
 
 /// Get the last facet value in the facet database
-pub(crate) fn get_last_facet_value<'t, BoundCodec>(
+pub(crate) fn get_last_facet_value<'t, BoundCodec, DC>(
     txn: &'t RoTxn,
-    db: heed::Database<FacetGroupKeyCodec<BytesRefCodec>, FacetGroupValueCodec>,
+    db: heed::Database<FacetGroupKeyCodec<BytesRefCodec>, DC>,
     field_id: u16,
 ) -> heed::Result<Option<BoundCodec::DItem>>
 where
@@ -102,9 +102,9 @@ where
 }
 
 /// Get the height of the highest level in the facet database
-pub(crate) fn get_highest_level<'t>(
+pub(crate) fn get_highest_level<'t, DC>(
     txn: &'t RoTxn<'t>,
-    db: heed::Database<FacetGroupKeyCodec<BytesRefCodec>, FacetGroupValueCodec>,
+    db: heed::Database<FacetGroupKeyCodec<BytesRefCodec>, DC>,
     field_id: u16,
 ) -> heed::Result<u8> {
     let field_id_prefix = &field_id.to_be_bytes();

milli/src/search/hybrid.rs

@@ -169,6 +169,7 @@ impl<'a> Search<'a> {
             index: self.index,
             semantic: self.semantic.clone(),
             time_budget: self.time_budget.clone(),
+            ranking_score_threshold: self.ranking_score_threshold,
         };
 
         let semantic = search.semantic.take();

milli/src/search/mod.rs

@@ -24,6 +24,7 @@ pub mod facet;
 mod fst_utils;
 pub mod hybrid;
 pub mod new;
+pub mod similar;
 
 #[derive(Debug, Clone)]
 pub struct SemanticSearch {
@@ -49,6 +50,7 @@ pub struct Search<'a> {
     index: &'a Index,
     semantic: Option<SemanticSearch>,
     time_budget: TimeBudget,
+    ranking_score_threshold: Option<f64>,
 }
 
 impl<'a> Search<'a> {
@@ -69,6 +71,7 @@ impl<'a> Search<'a> {
             index,
             semantic: None,
             time_budget: TimeBudget::max(),
+            ranking_score_threshold: None,
         }
     }
 
@@ -145,10 +148,15 @@ impl<'a> Search<'a> {
         self
     }
 
+    pub fn ranking_score_threshold(&mut self, ranking_score_threshold: f64) -> &mut Search<'a> {
+        self.ranking_score_threshold = Some(ranking_score_threshold);
+        self
+    }
+
     pub fn execute_for_candidates(&self, has_vector_search: bool) -> Result<RoaringBitmap> {
         if has_vector_search {
             let ctx = SearchContext::new(self.index, self.rtxn)?;
-            filtered_universe(&ctx, &self.filter)
+            filtered_universe(ctx.index, ctx.txn, &self.filter)
         } else {
             Ok(self.execute()?.candidates)
         }
@@ -161,7 +169,7 @@ impl<'a> Search<'a> {
             ctx.attributes_to_search_on(searchable_attributes)?;
         }
 
-        let universe = filtered_universe(&ctx, &self.filter)?;
+        let universe = filtered_universe(ctx.index, ctx.txn, &self.filter)?;
         let PartialSearchResult {
             located_query_terms,
             candidates,
@@ -183,6 +191,7 @@ impl<'a> Search<'a> {
                     embedder_name,
                     embedder,
                     self.time_budget.clone(),
+                    self.ranking_score_threshold,
                 )?
             }
             _ => execute_search(
@@ -200,6 +209,7 @@ impl<'a> Search<'a> {
                 &mut DefaultSearchLogger,
                 &mut DefaultSearchLogger,
                 self.time_budget.clone(),
+                self.ranking_score_threshold,
             )?,
         };
 
@@ -238,6 +248,7 @@ impl fmt::Debug for Search<'_> {
             index: _,
             semantic,
             time_budget,
+            ranking_score_threshold,
         } = self;
         f.debug_struct("Search")
             .field("query", query)
@@ -256,6 +267,7 @@ impl fmt::Debug for Search<'_> {
                 &semantic.as_ref().map(|semantic| &semantic.embedder_name),
             )
             .field("time_budget", time_budget)
+            .field("ranking_score_threshold", ranking_score_threshold)
             .finish()
     }
 }
@@ -276,6 +288,8 @@ pub enum TermsMatchingStrategy {
     Last,
     // all words are mandatory
     All,
+    // remove more frequent word first
+    Frequency,
 }
 
 impl Default for TermsMatchingStrategy {

milli/src/search/new/bucket_sort.rs

@@ -28,6 +28,7 @@ pub fn bucket_sort<'ctx, Q: RankingRuleQueryTrait>(
     scoring_strategy: ScoringStrategy,
     logger: &mut dyn SearchLogger<Q>,
     time_budget: TimeBudget,
+    ranking_score_threshold: Option<f64>,
 ) -> Result<BucketSortOutput> {
     logger.initial_query(query);
     logger.ranking_rules(&ranking_rules);
@@ -164,7 +165,19 @@ pub fn bucket_sort<'ctx, Q: RankingRuleQueryTrait>(
             loop {
                 let bucket = std::mem::take(&mut ranking_rule_universes[cur_ranking_rule_index]);
                 ranking_rule_scores.push(ScoreDetails::Skipped);
+
+                // remove candidates from the universe without adding them to result if their score is below the threshold
+                if let Some(ranking_score_threshold) = ranking_score_threshold {
+                    let current_score = ScoreDetails::global_score(ranking_rule_scores.iter());
+                    if current_score < ranking_score_threshold {
+                        all_candidates -= bucket | &ranking_rule_universes[cur_ranking_rule_index];
+                        back!();
+                        continue;
+                    }
+                }
+
                 maybe_add_to_results!(bucket);
+
                 ranking_rule_scores.pop();
 
                 if cur_ranking_rule_index == 0 {
@@ -220,6 +233,18 @@ pub fn bucket_sort<'ctx, Q: RankingRuleQueryTrait>(
         debug_assert!(
             ranking_rule_universes[cur_ranking_rule_index].is_superset(&next_bucket.candidates)
         );
+
+        // remove candidates from the universe without adding them to result if their score is below the threshold
+        if let Some(ranking_score_threshold) = ranking_score_threshold {
+            let current_score = ScoreDetails::global_score(ranking_rule_scores.iter());
+            if current_score < ranking_score_threshold {
+                all_candidates -=
+                    next_bucket.candidates | &ranking_rule_universes[cur_ranking_rule_index];
+                back!();
+                continue;
+            }
+        }
+
         ranking_rule_universes[cur_ranking_rule_index] -= &next_bucket.candidates;
 
         if cur_ranking_rule_index == ranking_rules_len - 1

milli/src/search/new/graph_based_ranking_rule.rs

@@ -164,6 +164,21 @@ impl<'ctx, G: RankingRuleGraphTrait> RankingRule<'ctx, QueryGraph> for GraphBase
                     }
                     costs
                 }
+                TermsMatchingStrategy::Frequency => {
+                    let removal_order =
+                        query_graph.removal_order_for_terms_matching_strategy_frequency(ctx)?;
+                    let mut forbidden_nodes =
+                        SmallBitmap::for_interned_values_in(&query_graph.nodes);
+                    let mut costs = query_graph.nodes.map(|_| None);
+                    // FIXME: this works because only words uses termsmatchingstrategy at the moment.
+                    for ns in removal_order {
+                        for n in ns.iter() {
+                            *costs.get_mut(n) = Some((1, forbidden_nodes.clone()));
+                        }
+                        forbidden_nodes.union(&ns);
+                    }
+                    costs
+                }
                 TermsMatchingStrategy::All => query_graph.nodes.map(|_| None),
             }
         } else {

milli/src/search/new/matches/mod.rs

@@ -507,7 +507,7 @@ mod tests {
     impl<'a> MatcherBuilder<'a> {
         fn new_test(rtxn: &'a heed::RoTxn, index: &'a TempIndex, query: &str) -> Self {
             let mut ctx = SearchContext::new(index, rtxn).unwrap();
-            let universe = filtered_universe(&ctx, &None).unwrap();
+            let universe = filtered_universe(ctx.index, ctx.txn, &None).unwrap();
             let crate::search::PartialSearchResult { located_query_terms, .. } = execute_search(
                 &mut ctx,
                 Some(query),
@@ -523,6 +523,7 @@ mod tests {
                 &mut crate::DefaultSearchLogger,
                 &mut crate::DefaultSearchLogger,
                 TimeBudget::max(),
+                None,
             )
             .unwrap();
 

milli/src/search/new/mod.rs

@@ -197,6 +197,11 @@ fn resolve_maximally_reduced_query_graph(
             .iter()
             .flat_map(|x| x.iter())
             .collect(),
+        TermsMatchingStrategy::Frequency => query_graph
+            .removal_order_for_terms_matching_strategy_frequency(ctx)?
+            .iter()
+            .flat_map(|x| x.iter())
+            .collect(),
         TermsMatchingStrategy::All => vec![],
     };
     graph.remove_nodes_keep_edges(&nodes_to_remove);
@@ -543,11 +548,16 @@ fn resolve_sort_criteria<'ctx, Query: RankingRuleQueryTrait>(
     Ok(())
 }
 
-pub fn filtered_universe(ctx: &SearchContext, filters: &Option<Filter>) -> Result<RoaringBitmap> {
+#[tracing::instrument(level = "trace", skip_all, target = "search")]
+pub fn filtered_universe(
+    index: &Index,
+    txn: &RoTxn<'_>,
+    filters: &Option<Filter>,
+) -> Result<RoaringBitmap> {
     Ok(if let Some(filters) = filters {
-        filters.evaluate(ctx.txn, ctx.index)?
+        filters.evaluate(txn, index)?
     } else {
-        ctx.index.documents_ids(ctx.txn)?
+        index.documents_ids(txn)?
     })
 }
 
@@ -564,6 +574,7 @@ pub fn execute_vector_search(
     embedder_name: &str,
     embedder: &Embedder,
     time_budget: TimeBudget,
+    ranking_score_threshold: Option<f64>,
 ) -> Result<PartialSearchResult> {
     check_sort_criteria(ctx, sort_criteria.as_ref())?;
 
@@ -593,6 +604,7 @@ pub fn execute_vector_search(
         scoring_strategy,
         placeholder_search_logger,
         time_budget,
+        ranking_score_threshold,
     )?;
 
     Ok(PartialSearchResult {
@@ -622,6 +634,7 @@ pub fn execute_search(
     placeholder_search_logger: &mut dyn SearchLogger<PlaceholderQuery>,
     query_graph_logger: &mut dyn SearchLogger<QueryGraph>,
     time_budget: TimeBudget,
+    ranking_score_threshold: Option<f64>,
 ) -> Result<PartialSearchResult> {
     check_sort_criteria(ctx, sort_criteria.as_ref())?;
 
@@ -710,6 +723,7 @@ pub fn execute_search(
             scoring_strategy,
             query_graph_logger,
             time_budget,
+            ranking_score_threshold,
         )?
     } else {
         let ranking_rules =
@@ -724,6 +738,7 @@ pub fn execute_search(
             scoring_strategy,
             placeholder_search_logger,
             time_budget,
+            ranking_score_threshold,
         )?
     };
 

milli/src/search/new/query_graph.rs

@@ -1,8 +1,9 @@
-use std::cmp::Ordering;
+use std::cmp::{Ordering, Reverse};
 use std::collections::BTreeMap;
 use std::hash::{Hash, Hasher};
 
 use fxhash::{FxHashMap, FxHasher};
+use roaring::RoaringBitmap;
 
 use super::interner::{FixedSizeInterner, Interned};
 use super::query_term::{
@@ -11,6 +12,7 @@ use super::query_term::{
 use super::small_bitmap::SmallBitmap;
 use super::SearchContext;
 use crate::search::new::interner::Interner;
+use crate::search::new::resolve_query_graph::compute_query_term_subset_docids;
 use crate::Result;
 
 /// A node of the [`QueryGraph`].
@@ -290,6 +292,49 @@ impl QueryGraph {
         }
     }
 
+    pub fn removal_order_for_terms_matching_strategy_frequency(
+        &self,
+        ctx: &mut SearchContext,
+    ) -> Result<Vec<SmallBitmap<QueryNode>>> {
+        // lookup frequency for each term
+        let mut term_with_frequency: Vec<(u8, u64)> = {
+            let mut term_docids: BTreeMap<u8, RoaringBitmap> = Default::default();
+            for (_, node) in self.nodes.iter() {
+                match &node.data {
+                    QueryNodeData::Term(t) => {
+                        let docids = compute_query_term_subset_docids(ctx, &t.term_subset)?;
+                        for id in t.term_ids.clone() {
+                            term_docids
+                                .entry(id)
+                                .and_modify(|curr| *curr |= &docids)
+                                .or_insert_with(|| docids.clone());
+                        }
+                    }
+                    QueryNodeData::Deleted | QueryNodeData::Start | QueryNodeData::End => continue,
+                }
+            }
+            term_docids
+                .into_iter()
+                .map(|(idx, docids)| match docids.len() {
+                    0 => (idx, u64::max_value()),
+                    frequency => (idx, frequency),
+                })
+                .collect()
+        };
+        term_with_frequency.sort_by_key(|(_, frequency)| Reverse(*frequency));
+        let mut term_weight = BTreeMap::new();
+        let mut weight: u16 = 1;
+        let mut peekable = term_with_frequency.into_iter().peekable();
+        while let Some((idx, frequency)) = peekable.next() {
+            term_weight.insert(idx, weight);
+            if peekable.peek().map_or(false, |(_, f)| frequency != *f) {
+                weight += 1;
+            }
+        }
+        let cost_of_term_idx = move |term_idx: u8| *term_weight.get(&term_idx).unwrap();
+        Ok(self.removal_order_for_terms_matching_strategy(ctx, cost_of_term_idx))
+    }
+
     pub fn removal_order_for_terms_matching_strategy_last(
         &self,
         ctx: &SearchContext,
@@ -315,10 +360,19 @@ impl QueryGraph {
         if first_term_idx >= last_term_idx {
             return vec![];
         }
+
         let cost_of_term_idx = |term_idx: u8| {
             let rank = 1 + last_term_idx - term_idx;
             rank as u16
         };
+        self.removal_order_for_terms_matching_strategy(ctx, cost_of_term_idx)
+    }
+
+    pub fn removal_order_for_terms_matching_strategy(
+        &self,
+        ctx: &SearchContext,
+        order: impl Fn(u8) -> u16,
+    ) -> Vec<SmallBitmap<QueryNode>> {
         let mut nodes_to_remove = BTreeMap::<u16, SmallBitmap<QueryNode>>::new();
         let mut at_least_one_mandatory_term = false;
         for (node_id, node) in self.nodes.iter() {
@@ -329,7 +383,7 @@ impl QueryGraph {
             }
             let mut cost = 0;
             for id in t.term_ids.clone() {
-                cost = std::cmp::max(cost, cost_of_term_idx(id));
+                cost = std::cmp::max(cost, order(id));
             }
             nodes_to_remove
                 .entry(cost)

milli/src/search/new/vector_sort.rs

@@ -49,19 +49,8 @@ impl<Q: RankingRuleQueryTrait> VectorSort<Q> {
         ctx: &mut SearchContext<'_>,
         vector_candidates: &RoaringBitmap,
     ) -> Result<()> {
-        let writer_index = (self.embedder_index as u16) << 8;
-        let readers: std::result::Result<Vec<_>, _> = (0..=u8::MAX)
-            .map_while(|k| {
-                arroy::Reader::open(ctx.txn, writer_index | (k as u16), ctx.index.vector_arroy)
-                    .map(Some)
-                    .or_else(|e| match e {
-                        arroy::Error::MissingMetadata => Ok(None),
-                        e => Err(e),
-                    })
-                    .transpose()
-            })
-            .collect();
-
+        let readers: std::result::Result<Vec<_>, _> =
+            ctx.index.arroy_readers(ctx.txn, self.embedder_index).collect();
         let readers = readers?;
 
         let target = &self.target;

milli/src/search/similar.rs

@@ -0,0 +1,146 @@
+use std::sync::Arc;
+
+use ordered_float::OrderedFloat;
+use roaring::RoaringBitmap;
+
+use crate::score_details::{self, ScoreDetails};
+use crate::vector::Embedder;
+use crate::{filtered_universe, DocumentId, Filter, Index, Result, SearchResult};
+
+pub struct Similar<'a> {
+    id: DocumentId,
+    // this should be linked to the String in the query
+    filter: Option<Filter<'a>>,
+    offset: usize,
+    limit: usize,
+    rtxn: &'a heed::RoTxn<'a>,
+    index: &'a Index,
+    embedder_name: String,
+    embedder: Arc<Embedder>,
+    ranking_score_threshold: Option<f64>,
+}
+
+impl<'a> Similar<'a> {
+    pub fn new(
+        id: DocumentId,
+        offset: usize,
+        limit: usize,
+        index: &'a Index,
+        rtxn: &'a heed::RoTxn<'a>,
+        embedder_name: String,
+        embedder: Arc<Embedder>,
+    ) -> Self {
+        Self {
+            id,
+            filter: None,
+            offset,
+            limit,
+            rtxn,
+            index,
+            embedder_name,
+            embedder,
+            ranking_score_threshold: None,
+        }
+    }
+
+    pub fn filter(&mut self, filter: Filter<'a>) -> &mut Self {
+        self.filter = Some(filter);
+        self
+    }
+
+    pub fn ranking_score_threshold(&mut self, ranking_score_threshold: f64) -> &mut Self {
+        self.ranking_score_threshold = Some(ranking_score_threshold);
+        self
+    }
+
+    pub fn execute(&self) -> Result<SearchResult> {
+        let mut universe = filtered_universe(self.index, self.rtxn, &self.filter)?;
+
+        // we never want to receive the docid
+        universe.remove(self.id);
+
+        let universe = universe;
+
+        let embedder_index =
+            self.index
+                .embedder_category_id
+                .get(self.rtxn, &self.embedder_name)?
+                .ok_or_else(|| crate::UserError::InvalidEmbedder(self.embedder_name.to_owned()))?;
+
+        let readers: std::result::Result<Vec<_>, _> =
+            self.index.arroy_readers(self.rtxn, embedder_index).collect();
+
+        let readers = readers?;
+
+        let mut results = Vec::new();
+
+        for reader in readers.iter() {
+            let nns_by_item = reader.nns_by_item(
+                self.rtxn,
+                self.id,
+                self.limit + self.offset + 1,
+                None,
+                Some(&universe),
+            )?;
+            if let Some(mut nns_by_item) = nns_by_item {
+                results.append(&mut nns_by_item);
+            } else {
+                break;
+            }
+        }
+
+        results.sort_unstable_by_key(|(_, distance)| OrderedFloat(*distance));
+
+        let mut documents_ids = Vec::with_capacity(self.limit);
+        let mut document_scores = Vec::with_capacity(self.limit);
+        // list of documents we've already seen, so that we don't return the same document multiple times.
+        // initialized to the target document, that we never want to return.
+        let mut documents_seen = RoaringBitmap::new();
+        documents_seen.insert(self.id);
+
+        let mut candidates = universe;
+
+        for (docid, distance) in results
+            .into_iter()
+            // skip documents we've already seen & mark that we saw the current document
+            .filter(|(docid, _)| documents_seen.insert(*docid))
+            .skip(self.offset)
+            // take **after** filter and skip so that we get exactly limit elements if available
+            .take(self.limit)
+        {
+            let score = 1.0 - distance;
+            let score = self
+                .embedder
+                .distribution()
+                .map(|distribution| distribution.shift(score))
+                .unwrap_or(score);
+
+            let score_details =
+                vec![ScoreDetails::Vector(score_details::Vector { similarity: Some(score) })];
+
+            let score = ScoreDetails::global_score(score_details.iter());
+
+            if let Some(ranking_score_threshold) = &self.ranking_score_threshold {
+                if score < *ranking_score_threshold {
+                    // this document is no longer a candidate
+                    candidates.remove(docid);
+                    // any document after this one is no longer a candidate either, so restrict the set to documents already seen.
+                    candidates &= documents_seen;
+                    break;
+                }
+            }
+
+            documents_ids.push(docid);
+            document_scores.push(score_details);
+        }
+
+        Ok(SearchResult {
+            matching_words: Default::default(),
+            candidates,
+            documents_ids,
+            document_scores,
+            degraded: false,
+            used_negative_operator: false,
+        })
+    }
+}

milli/src/update/clear_documents.rs

@@ -21,8 +21,6 @@ impl<'t, 'i> ClearDocuments<'t, 'i> {
         name = "clear_documents"
     )]
     pub fn execute(self) -> Result<u64> {
-        puffin::profile_function!();
-
         self.index.set_updated_at(self.wtxn, &OffsetDateTime::now_utc())?;
         let Index {
             env: _env,

milli/src/update/del_add.rs

@@ -40,11 +40,26 @@ pub fn into_del_add_obkv<K: obkv::Key + PartialOrd>(
     operation: DelAddOperation,
     buffer: &mut Vec<u8>,
 ) -> Result<(), std::io::Error> {
+    into_del_add_obkv_conditional_operation(reader, buffer, |_| operation)
+}
+
+/// Akin to the [into_del_add_obkv] function but lets you
+/// conditionally define the `DelAdd` variant based on the obkv key.
+pub fn into_del_add_obkv_conditional_operation<K, F>(
+    reader: obkv::KvReader<K>,
+    buffer: &mut Vec<u8>,
+    operation: F,
+) -> std::io::Result<()>
+where
+    K: obkv::Key + PartialOrd,
+    F: Fn(K) -> DelAddOperation,
+{
     let mut writer = obkv::KvWriter::new(buffer);
     let mut value_buffer = Vec::new();
     for (key, value) in reader.iter() {
         value_buffer.clear();
         let mut value_writer = KvWriterDelAdd::new(&mut value_buffer);
+        let operation = operation(key);
         if matches!(operation, DelAddOperation::Deletion | DelAddOperation::DeletionAndAddition) {
             value_writer.insert(DelAdd::Deletion, value)?;
         }

milli/src/update/index_documents/enrich.rs

@@ -29,8 +29,6 @@ pub fn enrich_documents_batch<R: Read + Seek>(
     autogenerate_docids: bool,
     reader: DocumentsBatchReader<R>,
 ) -> Result<StdResult<EnrichedDocumentsBatchReader<R>, UserError>> {
-    puffin::profile_function!();
-
     let (mut cursor, mut documents_batch_index) = reader.into_cursor_and_fields_index();
 
     let mut external_ids = tempfile::tempfile().map(BufWriter::new).map(grenad::Writer::new)?;

milli/src/update/index_documents/extract/extract_docid_word_positions.rs

@@ -29,8 +29,6 @@ pub fn extract_docid_word_positions<R: io::Read + io::Seek>(
     settings_diff: &InnerIndexSettingsDiff,
     max_positions_per_attributes: Option<u32>,
 ) -> Result<(grenad::Reader<BufReader<File>>, ScriptLanguageDocidsMap)> {
-    puffin::profile_function!();
-
     let max_positions_per_attributes = max_positions_per_attributes
         .map_or(MAX_POSITION_PER_ATTRIBUTE, |max| max.min(MAX_POSITION_PER_ATTRIBUTE));
     let max_memory = indexer.max_memory_by_thread();

milli/src/update/index_documents/extract/extract_facet_number_docids.rs

@@ -23,8 +23,6 @@ pub fn extract_facet_number_docids<R: io::Read + io::Seek>(
     indexer: GrenadParameters,
     _settings_diff: &InnerIndexSettingsDiff,
 ) -> Result<grenad::Reader<BufReader<File>>> {
-    puffin::profile_function!();
-
     let max_memory = indexer.max_memory_by_thread();
 
     let mut facet_number_docids_sorter = create_sorter(

milli/src/update/index_documents/extract/extract_facet_string_docids.rs

@@ -28,8 +28,6 @@ pub fn extract_facet_string_docids<R: io::Read + io::Seek>(
     indexer: GrenadParameters,
     _settings_diff: &InnerIndexSettingsDiff,
 ) -> Result<(grenad::Reader<BufReader<File>>, grenad::Reader<BufReader<File>>)> {
-    puffin::profile_function!();
-
     let max_memory = indexer.max_memory_by_thread();
     let options = NormalizerOption { lossy: true, ..Default::default() };
 

milli/src/update/index_documents/extract/extract_fid_docid_facet_values.rs

@@ -1,5 +1,5 @@
 use std::borrow::Cow;
-use std::collections::BTreeMap;
+use std::collections::{BTreeMap, BTreeSet};
 use std::convert::TryInto;
 use std::fs::File;
 use std::io::{self, BufReader};
@@ -9,7 +9,7 @@ use std::result::Result as StdResult;
 use bytemuck::bytes_of;
 use grenad::Sorter;
 use heed::BytesEncode;
-use itertools::EitherOrBoth;
+use itertools::{merge_join_by, EitherOrBoth};
 use ordered_float::OrderedFloat;
 use roaring::RoaringBitmap;
 use serde_json::{from_slice, Value};
@@ -18,7 +18,7 @@ use FilterableValues::{Empty, Null, Values};
 use super::helpers::{create_sorter, keep_first, sorter_into_reader, GrenadParameters};
 use crate::error::InternalError;
 use crate::facet::value_encoding::f64_into_bytes;
-use crate::update::del_add::{DelAdd, KvWriterDelAdd};
+use crate::update::del_add::{DelAdd, KvReaderDelAdd, KvWriterDelAdd};
 use crate::update::index_documents::{create_writer, writer_into_reader};
 use crate::update::settings::InnerIndexSettingsDiff;
 use crate::{CboRoaringBitmapCodec, DocumentId, Error, FieldId, Result, MAX_FACET_VALUE_LENGTH};
@@ -45,10 +45,7 @@ pub fn extract_fid_docid_facet_values<R: io::Read + io::Seek>(
     obkv_documents: grenad::Reader<R>,
     indexer: GrenadParameters,
     settings_diff: &InnerIndexSettingsDiff,
-    geo_fields_ids: Option<(FieldId, FieldId)>,
 ) -> Result<ExtractedFacetValues> {
-    puffin::profile_function!();
-
     let max_memory = indexer.max_memory_by_thread();
 
     let mut fid_docid_facet_numbers_sorter = create_sorter(
@@ -78,143 +75,181 @@ pub fn extract_fid_docid_facet_values<R: io::Read + io::Seek>(
     let mut numbers_key_buffer = Vec::new();
     let mut strings_key_buffer = Vec::new();
 
-    let mut cursor = obkv_documents.into_cursor()?;
-    while let Some((docid_bytes, value)) = cursor.move_on_next()? {
-        let obkv = obkv::KvReader::new(value);
+    let old_faceted_fids: BTreeSet<_> =
+        settings_diff.old.faceted_fields_ids.iter().copied().collect();
+    let new_faceted_fids: BTreeSet<_> =
+        settings_diff.new.faceted_fields_ids.iter().copied().collect();
 
-        for (field_id, field_bytes) in obkv.iter() {
-            let delete_faceted = settings_diff.old.faceted_fields_ids.contains(&field_id);
-            let add_faceted = settings_diff.new.faceted_fields_ids.contains(&field_id);
-            if delete_faceted || add_faceted {
-                numbers_key_buffer.clear();
-                strings_key_buffer.clear();
+    if !settings_diff.settings_update_only || old_faceted_fids != new_faceted_fids {
+        let mut cursor = obkv_documents.into_cursor()?;
+        while let Some((docid_bytes, value)) = cursor.move_on_next()? {
+            let obkv = obkv::KvReader::new(value);
+            let get_document_json_value = move |field_id, side| {
+                obkv.get(field_id)
+                    .map(KvReaderDelAdd::new)
+                    .and_then(|kv| kv.get(side))
+                    .map(from_slice)
+                    .transpose()
+                    .map_err(InternalError::SerdeJson)
+            };
+            // iterate over the faceted fields instead of over the whole document.
+            for eob in
+                merge_join_by(old_faceted_fids.iter(), new_faceted_fids.iter(), |old, new| {
+                    old.cmp(new)
+                })
+            {
+                let (field_id, del_value, add_value) = match eob {
+                    EitherOrBoth::Left(&field_id) => {
+                        let del_value = get_document_json_value(field_id, DelAdd::Deletion)?;
 
-                // Set key to the field_id
-                // Note: this encoding is consistent with FieldIdCodec
-                numbers_key_buffer.extend_from_slice(&field_id.to_be_bytes());
-                strings_key_buffer.extend_from_slice(&field_id.to_be_bytes());
+                        // deletion only
+                        (field_id, del_value, None)
+                    }
+                    EitherOrBoth::Right(&field_id) => {
+                        let add_value = get_document_json_value(field_id, DelAdd::Addition)?;
 
-                let document: [u8; 4] = docid_bytes[..4].try_into().ok().unwrap();
-                let document = DocumentId::from_be_bytes(document);
+                        // addition only
+                        (field_id, None, add_value)
+                    }
+                    EitherOrBoth::Both(&field_id, _) => {
+                        // during settings update, recompute the changing settings only.
+                        if settings_diff.settings_update_only {
+                            continue;
+                        }
 
-                // For the other extraction tasks, prefix the key with the field_id and the document_id
-                numbers_key_buffer.extend_from_slice(docid_bytes);
-                strings_key_buffer.extend_from_slice(docid_bytes);
+                        let del_value = get_document_json_value(field_id, DelAdd::Deletion)?;
+                        let add_value = get_document_json_value(field_id, DelAdd::Addition)?;
 
-                let del_add_obkv = obkv::KvReader::new(field_bytes);
-                let del_value = match del_add_obkv.get(DelAdd::Deletion).filter(|_| delete_faceted)
-                {
-                    Some(bytes) => Some(from_slice(bytes).map_err(InternalError::SerdeJson)?),
-                    None => None,
-                };
-                let add_value = match del_add_obkv.get(DelAdd::Addition).filter(|_| add_faceted) {
-                    Some(bytes) => Some(from_slice(bytes).map_err(InternalError::SerdeJson)?),
-                    None => None,
+                        (field_id, del_value, add_value)
+                    }
                 };
 
-                // We insert the document id on the Del and the Add side if the field exists.
-                let (ref mut del_exists, ref mut add_exists) =
-                    facet_exists_docids.entry(field_id).or_default();
-                let (ref mut del_is_null, ref mut add_is_null) =
-                    facet_is_null_docids.entry(field_id).or_default();
-                let (ref mut del_is_empty, ref mut add_is_empty) =
-                    facet_is_empty_docids.entry(field_id).or_default();
+                if del_value.is_some() || add_value.is_some() {
+                    numbers_key_buffer.clear();
+                    strings_key_buffer.clear();
 
-                if del_value.is_some() {
-                    del_exists.insert(document);
-                }
-                if add_value.is_some() {
-                    add_exists.insert(document);
-                }
+                    // Set key to the field_id
+                    // Note: this encoding is consistent with FieldIdCodec
+                    numbers_key_buffer.extend_from_slice(&field_id.to_be_bytes());
+                    strings_key_buffer.extend_from_slice(&field_id.to_be_bytes());
 
-                let geo_support =
-                    geo_fields_ids.map_or(false, |(lat, lng)| field_id == lat || field_id == lng);
-                let del_filterable_values =
-                    del_value.map(|value| extract_facet_values(&value, geo_support));
-                let add_filterable_values =
-                    add_value.map(|value| extract_facet_values(&value, geo_support));
+                    let document: [u8; 4] = docid_bytes[..4].try_into().ok().unwrap();
+                    let document = DocumentId::from_be_bytes(document);
 
-                // Those closures are just here to simplify things a bit.
-                let mut insert_numbers_diff = |del_numbers, add_numbers| {
-                    insert_numbers_diff(
-                        &mut fid_docid_facet_numbers_sorter,
-                        &mut numbers_key_buffer,
-                        del_numbers,
-                        add_numbers,
-                    )
-                };
-                let mut insert_strings_diff = |del_strings, add_strings| {
-                    insert_strings_diff(
-                        &mut fid_docid_facet_strings_sorter,
-                        &mut strings_key_buffer,
-                        del_strings,
-                        add_strings,
-                    )
-                };
+                    // For the other extraction tasks, prefix the key with the field_id and the document_id
+                    numbers_key_buffer.extend_from_slice(docid_bytes);
+                    strings_key_buffer.extend_from_slice(docid_bytes);
 
-                match (del_filterable_values, add_filterable_values) {
-                    (None, None) => (),
-                    (Some(del_filterable_values), None) => match del_filterable_values {
-                        Null => {
-                            del_is_null.insert(document);
-                        }
-                        Empty => {
-                            del_is_empty.insert(document);
-                        }
-                        Values { numbers, strings } => {
-                            insert_numbers_diff(numbers, vec![])?;
-                            insert_strings_diff(strings, vec![])?;
-                        }
-                    },
-                    (None, Some(add_filterable_values)) => match add_filterable_values {
-                        Null => {
-                            add_is_null.insert(document);
-                        }
-                        Empty => {
-                            add_is_empty.insert(document);
-                        }
-                        Values { numbers, strings } => {
-                            insert_numbers_diff(vec![], numbers)?;
-                            insert_strings_diff(vec![], strings)?;
-                        }
-                    },
-                    (Some(del_filterable_values), Some(add_filterable_values)) => {
-                        match (del_filterable_values, add_filterable_values) {
-                            (Null, Null) | (Empty, Empty) => (),
-                            (Null, Empty) => {
-                                del_is_null.insert(document);
-                                add_is_empty.insert(document);
-                            }
-                            (Empty, Null) => {
-                                del_is_empty.insert(document);
-                                add_is_null.insert(document);
-                            }
-                            (Null, Values { numbers, strings }) => {
-                                insert_numbers_diff(vec![], numbers)?;
-                                insert_strings_diff(vec![], strings)?;
+                    // We insert the document id on the Del and the Add side if the field exists.
+                    let (ref mut del_exists, ref mut add_exists) =
+                        facet_exists_docids.entry(field_id).or_default();
+                    let (ref mut del_is_null, ref mut add_is_null) =
+                        facet_is_null_docids.entry(field_id).or_default();
+                    let (ref mut del_is_empty, ref mut add_is_empty) =
+                        facet_is_empty_docids.entry(field_id).or_default();
+
+                    if del_value.is_some() {
+                        del_exists.insert(document);
+                    }
+                    if add_value.is_some() {
+                        add_exists.insert(document);
+                    }
+
+                    let del_geo_support = settings_diff
+                        .old
+                        .geo_fields_ids
+                        .map_or(false, |(lat, lng)| field_id == lat || field_id == lng);
+                    let add_geo_support = settings_diff
+                        .new
+                        .geo_fields_ids
+                        .map_or(false, |(lat, lng)| field_id == lat || field_id == lng);
+                    let del_filterable_values =
+                        del_value.map(|value| extract_facet_values(&value, del_geo_support));
+                    let add_filterable_values =
+                        add_value.map(|value| extract_facet_values(&value, add_geo_support));
+
+                    // Those closures are just here to simplify things a bit.
+                    let mut insert_numbers_diff = |del_numbers, add_numbers| {
+                        insert_numbers_diff(
+                            &mut fid_docid_facet_numbers_sorter,
+                            &mut numbers_key_buffer,
+                            del_numbers,
+                            add_numbers,
+                        )
+                    };
+                    let mut insert_strings_diff = |del_strings, add_strings| {
+                        insert_strings_diff(
+                            &mut fid_docid_facet_strings_sorter,
+                            &mut strings_key_buffer,
+                            del_strings,
+                            add_strings,
+                        )
+                    };
+
+                    match (del_filterable_values, add_filterable_values) {
+                        (None, None) => (),
+                        (Some(del_filterable_values), None) => match del_filterable_values {
+                            Null => {
                                 del_is_null.insert(document);
                             }
-                            (Empty, Values { numbers, strings }) => {
-                                insert_numbers_diff(vec![], numbers)?;
-                                insert_strings_diff(vec![], strings)?;
+                            Empty => {
                                 del_is_empty.insert(document);
                             }
-                            (Values { numbers, strings }, Null) => {
-                                add_is_null.insert(document);
+                            Values { numbers, strings } => {
                                 insert_numbers_diff(numbers, vec![])?;
                                 insert_strings_diff(strings, vec![])?;
                             }
-                            (Values { numbers, strings }, Empty) => {
-                                add_is_empty.insert(document);
-                                insert_numbers_diff(numbers, vec![])?;
-                                insert_strings_diff(strings, vec![])?;
+                        },
+                        (None, Some(add_filterable_values)) => match add_filterable_values {
+                            Null => {
+                                add_is_null.insert(document);
                             }
-                            (
-                                Values { numbers: del_numbers, strings: del_strings },
-                                Values { numbers: add_numbers, strings: add_strings },
-                            ) => {
-                                insert_numbers_diff(del_numbers, add_numbers)?;
-                                insert_strings_diff(del_strings, add_strings)?;
+                            Empty => {
+                                add_is_empty.insert(document);
+                            }
+                            Values { numbers, strings } => {
+                                insert_numbers_diff(vec![], numbers)?;
+                                insert_strings_diff(vec![], strings)?;
+                            }
+                        },
+                        (Some(del_filterable_values), Some(add_filterable_values)) => {
+                            match (del_filterable_values, add_filterable_values) {
+                                (Null, Null) | (Empty, Empty) => (),
+                                (Null, Empty) => {
+                                    del_is_null.insert(document);
+                                    add_is_empty.insert(document);
+                                }
+                                (Empty, Null) => {
+                                    del_is_empty.insert(document);
+                                    add_is_null.insert(document);
+                                }
+                                (Null, Values { numbers, strings }) => {
+                                    insert_numbers_diff(vec![], numbers)?;
+                                    insert_strings_diff(vec![], strings)?;
+                                    del_is_null.insert(document);
+                                }
+                                (Empty, Values { numbers, strings }) => {
+                                    insert_numbers_diff(vec![], numbers)?;
+                                    insert_strings_diff(vec![], strings)?;
+                                    del_is_empty.insert(document);
+                                }
+                                (Values { numbers, strings }, Null) => {
+                                    add_is_null.insert(document);
+                                    insert_numbers_diff(numbers, vec![])?;
+                                    insert_strings_diff(strings, vec![])?;
+                                }
+                                (Values { numbers, strings }, Empty) => {
+                                    add_is_empty.insert(document);
+                                    insert_numbers_diff(numbers, vec![])?;
+                                    insert_strings_diff(strings, vec![])?;
+                                }
+                                (
+                                    Values { numbers: del_numbers, strings: del_strings },
+                                    Values { numbers: add_numbers, strings: add_strings },
+                                ) => {
+                                    insert_numbers_diff(del_numbers, add_numbers)?;
+                                    insert_strings_diff(del_strings, add_strings)?;
+                                }
                             }
                         }
                     }

milli/src/update/index_documents/extract/extract_fid_word_count_docids.rs

@@ -26,8 +26,6 @@ pub fn extract_fid_word_count_docids<R: io::Read + io::Seek>(
     indexer: GrenadParameters,
     _settings_diff: &InnerIndexSettingsDiff,
 ) -> Result<grenad::Reader<BufReader<File>>> {
-    puffin::profile_function!();
-
     let max_memory = indexer.max_memory_by_thread();
 
     let mut fid_word_count_docids_sorter = create_sorter(

milli/src/update/index_documents/extract/extract_geo_points.rs

@@ -8,6 +8,7 @@ use super::helpers::{create_writer, writer_into_reader, GrenadParameters};
 use crate::error::GeoError;
 use crate::update::del_add::{DelAdd, KvReaderDelAdd, KvWriterDelAdd};
 use crate::update::index_documents::extract_finite_float_from_value;
+use crate::update::settings::{InnerIndexSettings, InnerIndexSettingsDiff};
 use crate::{FieldId, InternalError, Result};
 
 /// Extracts the geographical coordinates contained in each document under the `_geo` field.
@@ -18,10 +19,8 @@ pub fn extract_geo_points<R: io::Read + io::Seek>(
     obkv_documents: grenad::Reader<R>,
     indexer: GrenadParameters,
     primary_key_id: FieldId,
-    (lat_fid, lng_fid): (FieldId, FieldId),
+    settings_diff: &InnerIndexSettingsDiff,
 ) -> Result<grenad::Reader<BufReader<File>>> {
-    puffin::profile_function!();
-
     let mut writer = create_writer(
         indexer.chunk_compression_type,
         indexer.chunk_compression_level,
@@ -40,47 +39,27 @@ pub fn extract_geo_points<R: io::Read + io::Seek>(
             serde_json::from_slice(document_id).unwrap()
         };
 
-        // first we get the two fields
-        match (obkv.get(lat_fid), obkv.get(lng_fid)) {
-            (Some(lat), Some(lng)) => {
-                let deladd_lat_obkv = KvReaderDelAdd::new(lat);
-                let deladd_lng_obkv = KvReaderDelAdd::new(lng);
+        // extract old version
+        let del_lat_lng =
+            extract_lat_lng(&obkv, &settings_diff.old, DelAdd::Deletion, document_id)?;
+        // extract new version
+        let add_lat_lng =
+            extract_lat_lng(&obkv, &settings_diff.new, DelAdd::Addition, document_id)?;
 
-                // then we extract the values
-                let del_lat_lng = deladd_lat_obkv
-                    .get(DelAdd::Deletion)
-                    .zip(deladd_lng_obkv.get(DelAdd::Deletion))
-                    .map(|(lat, lng)| extract_lat_lng(lat, lng, document_id))
-                    .transpose()?;
-                let add_lat_lng = deladd_lat_obkv
-                    .get(DelAdd::Addition)
-                    .zip(deladd_lng_obkv.get(DelAdd::Addition))
-                    .map(|(lat, lng)| extract_lat_lng(lat, lng, document_id))
-                    .transpose()?;
-
-                if del_lat_lng != add_lat_lng {
-                    let mut obkv = KvWriterDelAdd::memory();
-                    if let Some([lat, lng]) = del_lat_lng {
-                        #[allow(clippy::drop_non_drop)]
-                        let bytes: [u8; 16] = concat_arrays![lat.to_ne_bytes(), lng.to_ne_bytes()];
-                        obkv.insert(DelAdd::Deletion, bytes)?;
-                    }
-                    if let Some([lat, lng]) = add_lat_lng {
-                        #[allow(clippy::drop_non_drop)]
-                        let bytes: [u8; 16] = concat_arrays![lat.to_ne_bytes(), lng.to_ne_bytes()];
-                        obkv.insert(DelAdd::Addition, bytes)?;
-                    }
-                    let bytes = obkv.into_inner()?;
-                    writer.insert(docid_bytes, bytes)?;
-                }
+        if del_lat_lng != add_lat_lng {
+            let mut obkv = KvWriterDelAdd::memory();
+            if let Some([lat, lng]) = del_lat_lng {
+                #[allow(clippy::drop_non_drop)]
+                let bytes: [u8; 16] = concat_arrays![lat.to_ne_bytes(), lng.to_ne_bytes()];
+                obkv.insert(DelAdd::Deletion, bytes)?;
             }
-            (None, Some(_)) => {
-                return Err(GeoError::MissingLatitude { document_id: document_id() }.into())
+            if let Some([lat, lng]) = add_lat_lng {
+                #[allow(clippy::drop_non_drop)]
+                let bytes: [u8; 16] = concat_arrays![lat.to_ne_bytes(), lng.to_ne_bytes()];
+                obkv.insert(DelAdd::Addition, bytes)?;
             }
-            (Some(_), None) => {
-                return Err(GeoError::MissingLongitude { document_id: document_id() }.into())
-            }
-            (None, None) => (),
+            let bytes = obkv.into_inner()?;
+            writer.insert(docid_bytes, bytes)?;
         }
     }
 
@@ -88,16 +67,37 @@ pub fn extract_geo_points<R: io::Read + io::Seek>(
 }
 
 /// Extract the finite floats lat and lng from two bytes slices.
-fn extract_lat_lng(lat: &[u8], lng: &[u8], document_id: impl Fn() -> Value) -> Result<[f64; 2]> {
-    let lat = extract_finite_float_from_value(
-        serde_json::from_slice(lat).map_err(InternalError::SerdeJson)?,
-    )
-    .map_err(|lat| GeoError::BadLatitude { document_id: document_id(), value: lat })?;
+fn extract_lat_lng(
+    document: &obkv::KvReader<FieldId>,
+    settings: &InnerIndexSettings,
+    deladd: DelAdd,
+    document_id: impl Fn() -> Value,
+) -> Result<Option<[f64; 2]>> {
+    match settings.geo_fields_ids {
+        Some((lat_fid, lng_fid)) => {
+            let lat = document.get(lat_fid).map(KvReaderDelAdd::new).and_then(|r| r.get(deladd));
+            let lng = document.get(lng_fid).map(KvReaderDelAdd::new).and_then(|r| r.get(deladd));
+            let (lat, lng) = match (lat, lng) {
+                (Some(lat), Some(lng)) => (lat, lng),
+                (Some(_), None) => {
+                    return Err(GeoError::MissingLatitude { document_id: document_id() }.into())
+                }
+                (None, Some(_)) => {
+                    return Err(GeoError::MissingLongitude { document_id: document_id() }.into())
+                }
+                (None, None) => return Ok(None),
+            };
+            let lat = extract_finite_float_from_value(
+                serde_json::from_slice(lat).map_err(InternalError::SerdeJson)?,
+            )
+            .map_err(|lat| GeoError::BadLatitude { document_id: document_id(), value: lat })?;
 
-    let lng = extract_finite_float_from_value(
-        serde_json::from_slice(lng).map_err(InternalError::SerdeJson)?,
-    )
-    .map_err(|lng| GeoError::BadLongitude { document_id: document_id(), value: lng })?;
-
-    Ok([lat, lng])
+            let lng = extract_finite_float_from_value(
+                serde_json::from_slice(lng).map_err(InternalError::SerdeJson)?,
+            )
+            .map_err(|lng| GeoError::BadLongitude { document_id: document_id(), value: lng })?;
+            Ok(Some([lat, lng]))
+        }
+        None => Ok(None),
+    }
 }

milli/src/update/index_documents/extract/extract_vector_points.rs

@@ -10,16 +10,16 @@ use bytemuck::cast_slice;
 use grenad::Writer;
 use itertools::EitherOrBoth;
 use ordered_float::OrderedFloat;
-use serde_json::{from_slice, Value};
+use serde_json::Value;
 
 use super::helpers::{create_writer, writer_into_reader, GrenadParameters};
-use crate::error::UserError;
 use crate::prompt::Prompt;
 use crate::update::del_add::{DelAdd, KvReaderDelAdd, KvWriterDelAdd};
 use crate::update::index_documents::helpers::try_split_at;
 use crate::update::settings::InnerIndexSettingsDiff;
+use crate::vector::parsed_vectors::{ParsedVectorsDiff, RESERVED_VECTORS_FIELD_NAME};
 use crate::vector::Embedder;
-use crate::{DocumentId, InternalError, Result, ThreadPoolNoAbort, VectorOrArrayOfVectors};
+use crate::{DocumentId, Result, ThreadPoolNoAbort};
 
 /// The length of the elements that are always in the buffer when inserting new values.
 const TRUNCATE_SIZE: usize = size_of::<DocumentId>();
@@ -31,6 +31,10 @@ pub struct ExtractedVectorPoints {
     pub remove_vectors: grenad::Reader<BufReader<File>>,
     // docid -> prompt
     pub prompts: grenad::Reader<BufReader<File>>,
+
+    // embedder
+    pub embedder_name: String,
+    pub embedder: Arc<Embedder>,
 }
 
 enum VectorStateDelta {
@@ -65,6 +69,19 @@ impl VectorStateDelta {
     }
 }
 
+struct EmbedderVectorExtractor {
+    embedder_name: String,
+    embedder: Arc<Embedder>,
+    prompt: Arc<Prompt>,
+
+    // (docid, _index) -> KvWriterDelAdd -> Vector
+    manual_vectors_writer: Writer<BufWriter<File>>,
+    // (docid) -> (prompt)
+    prompts_writer: Writer<BufWriter<File>>,
+    // (docid) -> ()
+    remove_vectors_writer: Writer<BufWriter<File>>,
+}
+
 /// Extracts the embedding vector contained in each document under the `_vectors` field.
 ///
 /// Returns the generated grenad reader containing the docid as key associated to the Vec<f32>
@@ -73,34 +90,52 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
     obkv_documents: grenad::Reader<R>,
     indexer: GrenadParameters,
     settings_diff: &InnerIndexSettingsDiff,
-    prompt: &Prompt,
-    embedder_name: &str,
-) -> Result<ExtractedVectorPoints> {
-    puffin::profile_function!();
+) -> Result<Vec<ExtractedVectorPoints>> {
+    let reindex_vectors = settings_diff.reindex_vectors();
 
     let old_fields_ids_map = &settings_diff.old.fields_ids_map;
     let new_fields_ids_map = &settings_diff.new.fields_ids_map;
+    // the vector field id may have changed
+    let old_vectors_fid = old_fields_ids_map.id(RESERVED_VECTORS_FIELD_NAME);
+    // filter the old vector fid if the settings has been changed forcing reindexing.
+    let old_vectors_fid = old_vectors_fid.filter(|_| !reindex_vectors);
 
-    // (docid, _index) -> KvWriterDelAdd -> Vector
-    let mut manual_vectors_writer = create_writer(
-        indexer.chunk_compression_type,
-        indexer.chunk_compression_level,
-        tempfile::tempfile()?,
-    );
+    let new_vectors_fid = new_fields_ids_map.id(RESERVED_VECTORS_FIELD_NAME);
 
-    // (docid) -> (prompt)
-    let mut prompts_writer = create_writer(
-        indexer.chunk_compression_type,
-        indexer.chunk_compression_level,
-        tempfile::tempfile()?,
-    );
+    let mut extractors = Vec::new();
+    for (embedder_name, (embedder, prompt)) in
+        settings_diff.new.embedding_configs.clone().into_iter()
+    {
+        // (docid, _index) -> KvWriterDelAdd -> Vector
+        let manual_vectors_writer = create_writer(
+            indexer.chunk_compression_type,
+            indexer.chunk_compression_level,
+            tempfile::tempfile()?,
+        );
 
-    // (docid) -> ()
-    let mut remove_vectors_writer = create_writer(
-        indexer.chunk_compression_type,
-        indexer.chunk_compression_level,
-        tempfile::tempfile()?,
-    );
+        // (docid) -> (prompt)
+        let prompts_writer = create_writer(
+            indexer.chunk_compression_type,
+            indexer.chunk_compression_level,
+            tempfile::tempfile()?,
+        );
+
+        // (docid) -> ()
+        let remove_vectors_writer = create_writer(
+            indexer.chunk_compression_type,
+            indexer.chunk_compression_level,
+            tempfile::tempfile()?,
+        );
+
+        extractors.push(EmbedderVectorExtractor {
+            embedder_name,
+            embedder,
+            prompt,
+            manual_vectors_writer,
+            prompts_writer,
+            remove_vectors_writer,
+        });
+    }
 
     let mut key_buffer = Vec::new();
     let mut cursor = obkv_documents.into_cursor()?;
@@ -114,152 +149,138 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
         key_buffer.clear();
         key_buffer.extend_from_slice(docid_bytes);
 
-        // since we only needs the primary key when we throw an error we create this getter to
+        // since we only need the primary key when we throw an error we create this getter to
         // lazily get it when needed
         let document_id = || -> Value { from_utf8(external_id_bytes).unwrap().into() };
 
-        // the vector field id may have changed
-        let old_vectors_fid = old_fields_ids_map.id("_vectors");
-        // filter the old vector fid if the settings has been changed forcing reindexing.
-        let old_vectors_fid = old_vectors_fid.filter(|_| !settings_diff.reindex_vectors());
+        let mut parsed_vectors = ParsedVectorsDiff::new(obkv, old_vectors_fid, new_vectors_fid)
+            .map_err(|error| error.to_crate_error(document_id().to_string()))?;
 
-        let new_vectors_fid = new_fields_ids_map.id("_vectors");
-        let vectors_field = {
-            let del = old_vectors_fid
-                .and_then(|vectors_fid| obkv.get(vectors_fid))
-                .map(KvReaderDelAdd::new)
-                .map(|obkv| to_vector_map(obkv, DelAdd::Deletion, &document_id))
-                .transpose()?
-                .flatten();
-            let add = new_vectors_fid
-                .and_then(|vectors_fid| obkv.get(vectors_fid))
-                .map(KvReaderDelAdd::new)
-                .map(|obkv| to_vector_map(obkv, DelAdd::Addition, &document_id))
-                .transpose()?
-                .flatten();
-            (del, add)
-        };
+        for EmbedderVectorExtractor {
+            embedder_name,
+            embedder: _,
+            prompt,
+            manual_vectors_writer,
+            prompts_writer,
+            remove_vectors_writer,
+        } in extractors.iter_mut()
+        {
+            let delta = match parsed_vectors.remove(embedder_name) {
+                (Some(old), Some(new)) => {
+                    // no autogeneration
+                    let del_vectors = old.into_array_of_vectors();
+                    let add_vectors = new.into_array_of_vectors();
 
-        let (del_map, add_map) = vectors_field;
-
-        let del_value = del_map.and_then(|mut map| map.remove(embedder_name));
-        let add_value = add_map.and_then(|mut map| map.remove(embedder_name));
-
-        let delta = match (del_value, add_value) {
-            (Some(old), Some(new)) => {
-                // no autogeneration
-                let del_vectors = extract_vectors(old, document_id, embedder_name)?;
-                let add_vectors = extract_vectors(new, document_id, embedder_name)?;
-
-                if add_vectors.len() > usize::from(u8::MAX) {
-                    return Err(crate::Error::UserError(crate::UserError::TooManyVectors(
-                        document_id().to_string(),
-                        add_vectors.len(),
-                    )));
-                }
-
-                VectorStateDelta::ManualDelta(del_vectors, add_vectors)
-            }
-            (Some(_old), None) => {
-                // Do we keep this document?
-                let document_is_kept = obkv
-                    .iter()
-                    .map(|(_, deladd)| KvReaderDelAdd::new(deladd))
-                    .any(|deladd| deladd.get(DelAdd::Addition).is_some());
-                if document_is_kept {
-                    // becomes autogenerated
-                    VectorStateDelta::NowGenerated(prompt.render(
-                        obkv,
-                        DelAdd::Addition,
-                        new_fields_ids_map,
-                    )?)
-                } else {
-                    VectorStateDelta::NowRemoved
-                }
-            }
-            (None, Some(new)) => {
-                // was possibly autogenerated, remove all vectors for that document
-                let add_vectors = extract_vectors(new, document_id, embedder_name)?;
-                if add_vectors.len() > usize::from(u8::MAX) {
-                    return Err(crate::Error::UserError(crate::UserError::TooManyVectors(
-                        document_id().to_string(),
-                        add_vectors.len(),
-                    )));
-                }
-
-                VectorStateDelta::WasGeneratedNowManual(add_vectors)
-            }
-            (None, None) => {
-                // Do we keep this document?
-                let document_is_kept = obkv
-                    .iter()
-                    .map(|(_, deladd)| KvReaderDelAdd::new(deladd))
-                    .any(|deladd| deladd.get(DelAdd::Addition).is_some());
-
-                if document_is_kept {
-                    // Don't give up if the old prompt was failing
-                    let old_prompt = Some(prompt)
-                        // TODO: this filter works because we erase the vec database when a embedding setting changes.
-                        // When vector pipeline will be optimized, this should be removed.
-                        .filter(|_| !settings_diff.reindex_vectors())
-                        .map(|p| {
-                            p.render(obkv, DelAdd::Deletion, old_fields_ids_map).unwrap_or_default()
-                        });
-                    let new_prompt = prompt.render(obkv, DelAdd::Addition, new_fields_ids_map)?;
-                    if old_prompt.as_ref() != Some(&new_prompt) {
-                        let old_prompt = old_prompt.unwrap_or_default();
-                        tracing::trace!(
-                            "🚀 Changing prompt from\n{old_prompt}\n===to===\n{new_prompt}"
-                        );
-                        VectorStateDelta::NowGenerated(new_prompt)
-                    } else {
-                        tracing::trace!("⏭️ Prompt unmodified, skipping");
-                        VectorStateDelta::NoChange
+                    if add_vectors.len() > usize::from(u8::MAX) {
+                        return Err(crate::Error::UserError(crate::UserError::TooManyVectors(
+                            document_id().to_string(),
+                            add_vectors.len(),
+                        )));
                     }
-                } else {
-                    VectorStateDelta::NowRemoved
-                }
-            }
-        };
 
-        // and we finally push the unique vectors into the writer
-        push_vectors_diff(
-            &mut remove_vectors_writer,
-            &mut prompts_writer,
-            &mut manual_vectors_writer,
-            &mut key_buffer,
-            delta,
-            settings_diff,
-        )?;
+                    VectorStateDelta::ManualDelta(del_vectors, add_vectors)
+                }
+                (Some(_old), None) => {
+                    // Do we keep this document?
+                    let document_is_kept = obkv
+                        .iter()
+                        .map(|(_, deladd)| KvReaderDelAdd::new(deladd))
+                        .any(|deladd| deladd.get(DelAdd::Addition).is_some());
+                    if document_is_kept {
+                        // becomes autogenerated
+                        VectorStateDelta::NowGenerated(prompt.render(
+                            obkv,
+                            DelAdd::Addition,
+                            new_fields_ids_map,
+                        )?)
+                    } else {
+                        VectorStateDelta::NowRemoved
+                    }
+                }
+                (None, Some(new)) => {
+                    // was possibly autogenerated, remove all vectors for that document
+                    let add_vectors = new.into_array_of_vectors();
+                    if add_vectors.len() > usize::from(u8::MAX) {
+                        return Err(crate::Error::UserError(crate::UserError::TooManyVectors(
+                            document_id().to_string(),
+                            add_vectors.len(),
+                        )));
+                    }
+
+                    VectorStateDelta::WasGeneratedNowManual(add_vectors)
+                }
+                (None, None) => {
+                    // Do we keep this document?
+                    let document_is_kept = obkv
+                        .iter()
+                        .map(|(_, deladd)| KvReaderDelAdd::new(deladd))
+                        .any(|deladd| deladd.get(DelAdd::Addition).is_some());
+
+                    if document_is_kept {
+                        // Don't give up if the old prompt was failing
+                        let old_prompt = Some(&prompt)
+                            // TODO: this filter works because we erase the vec database when a embedding setting changes.
+                            // When vector pipeline will be optimized, this should be removed.
+                            .filter(|_| !settings_diff.reindex_vectors())
+                            .map(|p| {
+                                p.render(obkv, DelAdd::Deletion, old_fields_ids_map)
+                                    .unwrap_or_default()
+                            });
+                        let new_prompt =
+                            prompt.render(obkv, DelAdd::Addition, new_fields_ids_map)?;
+                        if old_prompt.as_ref() != Some(&new_prompt) {
+                            let old_prompt = old_prompt.unwrap_or_default();
+                            tracing::trace!(
+                                "🚀 Changing prompt from\n{old_prompt}\n===to===\n{new_prompt}"
+                            );
+                            VectorStateDelta::NowGenerated(new_prompt)
+                        } else {
+                            tracing::trace!("⏭️ Prompt unmodified, skipping");
+                            VectorStateDelta::NoChange
+                        }
+                    } else {
+                        VectorStateDelta::NowRemoved
+                    }
+                }
+            };
+
+            // and we finally push the unique vectors into the writer
+            push_vectors_diff(
+                remove_vectors_writer,
+                prompts_writer,
+                manual_vectors_writer,
+                &mut key_buffer,
+                delta,
+                reindex_vectors,
+            )?;
+        }
     }
 
-    Ok(ExtractedVectorPoints {
-        // docid, _index -> KvWriterDelAdd -> Vector
-        manual_vectors: writer_into_reader(manual_vectors_writer)?,
-        // docid -> ()
-        remove_vectors: writer_into_reader(remove_vectors_writer)?,
-        // docid -> prompt
-        prompts: writer_into_reader(prompts_writer)?,
-    })
-}
+    let mut results = Vec::new();
 
-fn to_vector_map(
-    obkv: KvReaderDelAdd,
-    side: DelAdd,
-    document_id: &impl Fn() -> Value,
-) -> Result<Option<serde_json::Map<String, Value>>> {
-    Ok(if let Some(value) = obkv.get(side) {
-        let Ok(value) = from_slice(value) else {
-            let value = from_slice(value).map_err(InternalError::SerdeJson)?;
-            return Err(crate::Error::UserError(UserError::InvalidVectorsMapType {
-                document_id: document_id(),
-                value,
-            }));
-        };
-        Some(value)
-    } else {
-        None
-    })
+    for EmbedderVectorExtractor {
+        embedder_name,
+        embedder,
+        prompt: _,
+        manual_vectors_writer,
+        prompts_writer,
+        remove_vectors_writer,
+    } in extractors
+    {
+        results.push(ExtractedVectorPoints {
+            // docid, _index -> KvWriterDelAdd -> Vector
+            manual_vectors: writer_into_reader(manual_vectors_writer)?,
+            // docid -> ()
+            remove_vectors: writer_into_reader(remove_vectors_writer)?,
+            // docid -> prompt
+            prompts: writer_into_reader(prompts_writer)?,
+
+            embedder,
+            embedder_name,
+        })
+    }
+
+    Ok(results)
 }
 
 /// Computes the diff between both Del and Add numbers and
@@ -270,14 +291,13 @@ fn push_vectors_diff(
     manual_vectors_writer: &mut Writer<BufWriter<File>>,
     key_buffer: &mut Vec<u8>,
     delta: VectorStateDelta,
-    settings_diff: &InnerIndexSettingsDiff,
+    reindex_vectors: bool,
 ) -> Result<()> {
-    puffin::profile_function!();
     let (must_remove, prompt, (mut del_vectors, mut add_vectors)) = delta.into_values();
     if must_remove
     // TODO: the below condition works because we erase the vec database when a embedding setting changes.
     // When vector pipeline will be optimized, this should be removed.
-    && !settings_diff.reindex_vectors()
+    && !reindex_vectors
     {
         key_buffer.truncate(TRUNCATE_SIZE);
         remove_vectors_writer.insert(&key_buffer, [])?;
@@ -308,7 +328,7 @@ fn push_vectors_diff(
             EitherOrBoth::Left(vector) => {
                 // TODO: the below condition works because we erase the vec database when a embedding setting changes.
                 // When vector pipeline will be optimized, this should be removed.
-                if !settings_diff.reindex_vectors() {
+                if !reindex_vectors {
                     // We insert only the Del part of the Obkv to inform
                     // that we only want to remove all those vectors.
                     let mut obkv = KvWriterDelAdd::memory();
@@ -336,26 +356,6 @@ fn compare_vectors(a: &[f32], b: &[f32]) -> Ordering {
     a.iter().copied().map(OrderedFloat).cmp(b.iter().copied().map(OrderedFloat))
 }
 
-/// Extracts the vectors from a JSON value.
-fn extract_vectors(
-    value: Value,
-    document_id: impl Fn() -> Value,
-    name: &str,
-) -> Result<Vec<Vec<f32>>> {
-    // FIXME: ugly clone of the vectors here
-    match serde_json::from_value(value.clone()) {
-        Ok(vectors) => {
-            Ok(VectorOrArrayOfVectors::into_array_of_vectors(vectors).unwrap_or_default())
-        }
-        Err(_) => Err(UserError::InvalidVectorsType {
-            document_id: document_id(),
-            value,
-            subfield: name.to_owned(),
-        }
-        .into()),
-    }
-}
-
 #[tracing::instrument(level = "trace", skip_all, target = "indexing::extract")]
 pub fn extract_embeddings<R: io::Read + io::Seek>(
     // docid, prompt
@@ -364,7 +364,6 @@ pub fn extract_embeddings<R: io::Read + io::Seek>(
     embedder: Arc<Embedder>,
     request_threads: &ThreadPoolNoAbort,
 ) -> Result<grenad::Reader<BufReader<File>>> {
-    puffin::profile_function!();
     let n_chunks = embedder.chunk_count_hint(); // chunk level parallelism
     let n_vectors_per_chunk = embedder.prompt_count_in_chunk_hint(); // number of vectors in a single chunk
 

milli/src/update/index_documents/extract/extract_word_docids.rs

@@ -36,8 +36,6 @@ pub fn extract_word_docids<R: io::Read + io::Seek>(
     grenad::Reader<BufReader<File>>,
     grenad::Reader<BufReader<File>>,
 )> {
-    puffin::profile_function!();
-
     let max_memory = indexer.max_memory_by_thread();
 
     let mut word_fid_docids_sorter = create_sorter(
@@ -167,8 +165,6 @@ fn words_into_sorter(
     add_words: &BTreeSet<Vec<u8>>,
     word_fid_docids_sorter: &mut grenad::Sorter<MergeFn>,
 ) -> Result<()> {
-    puffin::profile_function!();
-
     use itertools::merge_join_by;
     use itertools::EitherOrBoth::{Both, Left, Right};
 

milli/src/update/index_documents/extract/extract_word_pair_proximity_docids.rs

@@ -26,12 +26,8 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
     indexer: GrenadParameters,
     settings_diff: &InnerIndexSettingsDiff,
 ) -> Result<grenad::Reader<BufReader<File>>> {
-    puffin::profile_function!();
-    let any_deletion = settings_diff.old.proximity_precision == ProximityPrecision::ByWord;
-    let any_addition = settings_diff.new.proximity_precision == ProximityPrecision::ByWord;
-
     // early return if the data shouldn't be deleted nor created.
-    if !any_deletion && !any_addition {
+    if settings_diff.settings_update_only && !settings_diff.reindex_proximities() {
         let writer = create_writer(
             indexer.chunk_compression_type,
             indexer.chunk_compression_level,
@@ -40,8 +36,10 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
         return writer_into_reader(writer);
     }
 
-    let max_memory = indexer.max_memory_by_thread();
+    let any_deletion = settings_diff.old.proximity_precision == ProximityPrecision::ByWord;
+    let any_addition = settings_diff.new.proximity_precision == ProximityPrecision::ByWord;
 
+    let max_memory = indexer.max_memory_by_thread();
     let mut word_pair_proximity_docids_sorters: Vec<_> = (1..MAX_DISTANCE)
         .map(|_| {
             create_sorter(
@@ -71,8 +69,6 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
 
         // if we change document, we fill the sorter
         if current_document_id.map_or(false, |id| id != document_id) {
-            puffin::profile_scope!("Document into sorter");
-
             // FIXME: span inside of a hot loop might degrade performance and create big reports
             let span = tracing::trace_span!(target: "indexing::details", "document_into_sorter");
             let _entered = span.enter();
@@ -163,7 +159,6 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
     }
 
     if let Some(document_id) = current_document_id {
-        puffin::profile_scope!("Final document into sorter");
         // FIXME: span inside of a hot loop might degrade performance and create big reports
         let span = tracing::trace_span!(target: "indexing::details", "final_document_into_sorter");
         let _entered = span.enter();
@@ -176,7 +171,6 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
         )?;
     }
     {
-        puffin::profile_scope!("sorter_into_reader");
         // FIXME: span inside of a hot loop might degrade performance and create big reports
         let span = tracing::trace_span!(target: "indexing::details", "sorter_into_reader");
         let _entered = span.enter();

milli/src/update/index_documents/extract/extract_word_position_docids.rs

@@ -25,8 +25,6 @@ pub fn extract_word_position_docids<R: io::Read + io::Seek>(
     indexer: GrenadParameters,
     _settings_diff: &InnerIndexSettingsDiff,
 ) -> Result<grenad::Reader<BufReader<File>>> {
-    puffin::profile_function!();
-
     let max_memory = indexer.max_memory_by_thread();
 
     let mut word_position_docids_sorter = create_sorter(
@@ -104,8 +102,6 @@ fn words_position_into_sorter(
     add_word_positions: &BTreeSet<(u16, Vec<u8>)>,
     word_position_docids_sorter: &mut grenad::Sorter<MergeFn>,
 ) -> Result<()> {
-    puffin::profile_function!();
-
     use itertools::merge_join_by;
     use itertools::EitherOrBoth::{Both, Left, Right};
 

milli/src/update/index_documents/extract/mod.rs

@@ -8,6 +8,7 @@ mod extract_vector_points;
 mod extract_word_docids;
 mod extract_word_pair_proximity_docids;
 mod extract_word_position_docids;
+// mod searchable;
 
 use std::fs::File;
 use std::io::BufReader;
@@ -43,12 +44,9 @@ pub(crate) fn data_from_obkv_documents(
     indexer: GrenadParameters,
     lmdb_writer_sx: Sender<Result<TypedChunk>>,
     primary_key_id: FieldId,
-    geo_fields_ids: Option<(FieldId, FieldId)>,
     settings_diff: Arc<InnerIndexSettingsDiff>,
     max_positions_per_attributes: Option<u32>,
 ) -> Result<()> {
-    puffin::profile_function!();
-
     let (original_pipeline_result, flattened_pipeline_result): (Result<_>, Result<_>) = rayon::join(
         || {
             original_obkv_chunks
@@ -72,7 +70,6 @@ pub(crate) fn data_from_obkv_documents(
                         indexer,
                         lmdb_writer_sx.clone(),
                         primary_key_id,
-                        geo_fields_ids,
                         settings_diff.clone(),
                         max_positions_per_attributes,
                     )
@@ -90,7 +87,6 @@ pub(crate) fn data_from_obkv_documents(
                             lmdb_writer_sx.clone(),
                             extract_fid_word_count_docids,
                             TypedChunk::FieldIdWordCountDocids,
-                            "field-id-wordcount-docids",
                         );
                         run_extraction_task::<
                             _,
@@ -117,7 +113,6 @@ pub(crate) fn data_from_obkv_documents(
                                     word_fid_docids_reader,
                                 }
                             },
-                            "word-docids",
                         );
 
                         run_extraction_task::<_, _, grenad::Reader<BufReader<File>>>(
@@ -127,7 +122,6 @@ pub(crate) fn data_from_obkv_documents(
                             lmdb_writer_sx.clone(),
                             extract_word_position_docids,
                             TypedChunk::WordPositionDocids,
-                            "word-position-docids",
                         );
 
                         run_extraction_task::<
@@ -141,7 +135,6 @@ pub(crate) fn data_from_obkv_documents(
                             lmdb_writer_sx.clone(),
                             extract_facet_string_docids,
                             TypedChunk::FieldIdFacetStringDocids,
-                            "field-id-facet-string-docids",
                         );
 
                         run_extraction_task::<_, _, grenad::Reader<BufReader<File>>>(
@@ -151,7 +144,6 @@ pub(crate) fn data_from_obkv_documents(
                             lmdb_writer_sx.clone(),
                             extract_facet_number_docids,
                             TypedChunk::FieldIdFacetNumberDocids,
-                            "field-id-facet-number-docids",
                         );
 
                         run_extraction_task::<_, _, grenad::Reader<BufReader<File>>>(
@@ -161,7 +153,6 @@ pub(crate) fn data_from_obkv_documents(
                             lmdb_writer_sx.clone(),
                             extract_word_pair_proximity_docids,
                             TypedChunk::WordPairProximityDocids,
-                            "word-pair-proximity-docids",
                         );
                     }
 
@@ -185,7 +176,6 @@ fn run_extraction_task<FE, FS, M>(
     lmdb_writer_sx: Sender<Result<TypedChunk>>,
     extract_fn: FE,
     serialize_fn: FS,
-    name: &'static str,
 ) where
     FE: Fn(
             grenad::Reader<CursorClonableMmap>,
@@ -203,7 +193,7 @@ fn run_extraction_task<FE, FS, M>(
     rayon::spawn(move || {
         let child_span = tracing::trace_span!(target: "indexing::extract::details", parent: &current_span, "extract_multiple_chunks");
         let _entered = child_span.enter();
-        puffin::profile_scope!("extract_multiple_chunks", name);
+
         match extract_fn(chunk, indexer, &settings_diff) {
             Ok(chunk) => {
                 let _ = lmdb_writer_sx.send(Ok(serialize_fn(chunk)));
@@ -226,27 +216,31 @@ fn send_original_documents_data(
     let original_documents_chunk =
         original_documents_chunk.and_then(|c| unsafe { as_cloneable_grenad(&c) })?;
 
-    let documents_chunk_cloned = original_documents_chunk.clone();
-    let lmdb_writer_sx_cloned = lmdb_writer_sx.clone();
-
     let request_threads = ThreadPoolNoAbortBuilder::new()
         .num_threads(crate::vector::REQUEST_PARALLELISM)
         .thread_name(|index| format!("embedding-request-{index}"))
         .build()?;
 
-    if settings_diff.reindex_vectors() || !settings_diff.settings_update_only() {
+    let index_vectors = (settings_diff.reindex_vectors() || !settings_diff.settings_update_only())
+        // no point in indexing vectors without embedders
+        && (!settings_diff.new.embedding_configs.inner_as_ref().is_empty());
+
+    if index_vectors {
         let settings_diff = settings_diff.clone();
+
+        let original_documents_chunk = original_documents_chunk.clone();
+        let lmdb_writer_sx = lmdb_writer_sx.clone();
         rayon::spawn(move || {
-            for (name, (embedder, prompt)) in settings_diff.new.embedding_configs.clone() {
-                let result = extract_vector_points(
-                    documents_chunk_cloned.clone(),
-                    indexer,
-                    &settings_diff,
-                    &prompt,
-                    &name,
-                );
-                match result {
-                    Ok(ExtractedVectorPoints { manual_vectors, remove_vectors, prompts }) => {
+            match extract_vector_points(original_documents_chunk.clone(), indexer, &settings_diff) {
+                Ok(extracted_vectors) => {
+                    for ExtractedVectorPoints {
+                        manual_vectors,
+                        remove_vectors,
+                        prompts,
+                        embedder_name,
+                        embedder,
+                    } in extracted_vectors
+                    {
                         let embeddings = match extract_embeddings(
                             prompts,
                             indexer,
@@ -255,28 +249,26 @@ fn send_original_documents_data(
                         ) {
                             Ok(results) => Some(results),
                             Err(error) => {
-                                let _ = lmdb_writer_sx_cloned.send(Err(error));
+                                let _ = lmdb_writer_sx.send(Err(error));
                                 None
                             }
                         };
-
                         if !(remove_vectors.is_empty()
                             && manual_vectors.is_empty()
                             && embeddings.as_ref().map_or(true, |e| e.is_empty()))
                         {
-                            let _ = lmdb_writer_sx_cloned.send(Ok(TypedChunk::VectorPoints {
+                            let _ = lmdb_writer_sx.send(Ok(TypedChunk::VectorPoints {
                                 remove_vectors,
                                 embeddings,
                                 expected_dimension: embedder.dimensions(),
                                 manual_vectors,
-                                embedder_name: name,
+                                embedder_name,
                             }));
                         }
                     }
-
-                    Err(error) => {
-                        let _ = lmdb_writer_sx_cloned.send(Err(error));
-                    }
+                }
+                Err(error) => {
+                    let _ = lmdb_writer_sx.send(Err(error));
                 }
             }
         });
@@ -300,7 +292,6 @@ fn send_and_extract_flattened_documents_data(
     indexer: GrenadParameters,
     lmdb_writer_sx: Sender<Result<TypedChunk>>,
     primary_key_id: FieldId,
-    geo_fields_ids: Option<(FieldId, FieldId)>,
     settings_diff: Arc<InnerIndexSettingsDiff>,
     max_positions_per_attributes: Option<u32>,
 ) -> Result<(
@@ -310,12 +301,13 @@ fn send_and_extract_flattened_documents_data(
     let flattened_documents_chunk =
         flattened_documents_chunk.and_then(|c| unsafe { as_cloneable_grenad(&c) })?;
 
-    if let Some(geo_fields_ids) = geo_fields_ids {
+    if settings_diff.run_geo_indexing() {
         let documents_chunk_cloned = flattened_documents_chunk.clone();
         let lmdb_writer_sx_cloned = lmdb_writer_sx.clone();
+        let settings_diff = settings_diff.clone();
         rayon::spawn(move || {
             let result =
-                extract_geo_points(documents_chunk_cloned, indexer, primary_key_id, geo_fields_ids);
+                extract_geo_points(documents_chunk_cloned, indexer, primary_key_id, &settings_diff);
             let _ = match result {
                 Ok(geo_points) => lmdb_writer_sx_cloned.send(Ok(TypedChunk::GeoPoints(geo_points))),
                 Err(error) => lmdb_writer_sx_cloned.send(Err(error)),
@@ -354,7 +346,6 @@ fn send_and_extract_flattened_documents_data(
                     flattened_documents_chunk.clone(),
                     indexer,
                     &settings_diff,
-                    geo_fields_ids,
                 )?;
 
                 // send fid_docid_facet_numbers_chunk to DB writer

milli/src/update/index_documents/extract/searchable/field_word_position.rs

@@ -0,0 +1,211 @@
+use std::collections::HashMap;
+
+use charabia::normalizer::NormalizedTokenIter;
+use charabia::{Language, Script, SeparatorKind, Token, TokenKind, Tokenizer, TokenizerBuilder};
+use roaring::RoaringBitmap;
+use serde_json::Value;
+
+use crate::update::settings::InnerIndexSettings;
+use crate::{InternalError, Result, MAX_POSITION_PER_ATTRIBUTE, MAX_WORD_LENGTH};
+
+pub type ScriptLanguageDocidsMap = HashMap<(Script, Language), (RoaringBitmap, RoaringBitmap)>;
+
+pub struct FieldWordPositionExtractorBuilder<'a> {
+    max_positions_per_attributes: u16,
+    stop_words: Option<&'a fst::Set<Vec<u8>>>,
+    separators: Option<Vec<&'a str>>,
+    dictionary: Option<Vec<&'a str>>,
+}
+
+impl<'a> FieldWordPositionExtractorBuilder<'a> {
+    pub fn new(
+        max_positions_per_attributes: Option<u32>,
+        settings: &'a InnerIndexSettings,
+    ) -> Result<Self> {
+        let stop_words = settings.stop_words.as_ref();
+        let separators: Option<Vec<_>> =
+            settings.allowed_separators.as_ref().map(|s| s.iter().map(String::as_str).collect());
+        let dictionary: Option<Vec<_>> =
+            settings.dictionary.as_ref().map(|s| s.iter().map(String::as_str).collect());
+        Ok(Self {
+            max_positions_per_attributes: max_positions_per_attributes
+                .map_or(MAX_POSITION_PER_ATTRIBUTE as u16, |max| {
+                    max.min(MAX_POSITION_PER_ATTRIBUTE) as u16
+                }),
+            stop_words,
+            separators,
+            dictionary,
+        })
+    }
+
+    pub fn build(&'a self) -> FieldWordPositionExtractor<'a> {
+        let builder = tokenizer_builder(
+            self.stop_words,
+            self.separators.as_deref(),
+            self.dictionary.as_deref(),
+            None,
+        );
+
+        FieldWordPositionExtractor {
+            tokenizer: builder.into_tokenizer(),
+            max_positions_per_attributes: self.max_positions_per_attributes,
+        }
+    }
+}
+
+pub struct FieldWordPositionExtractor<'a> {
+    tokenizer: Tokenizer<'a>,
+    max_positions_per_attributes: u16,
+}
+
+impl<'a> FieldWordPositionExtractor<'a> {
+    pub fn extract<'b>(
+        &'a self,
+        field_bytes: &[u8],
+        buffer: &'b mut String,
+    ) -> Result<ExtractedFieldWordPosition<'a, 'b>> {
+        let field_value = serde_json::from_slice(field_bytes).map_err(InternalError::SerdeJson)?;
+        Ok(ExtractedFieldWordPosition {
+            tokenizer: &self.tokenizer,
+            max_positions_per_attributes: self.max_positions_per_attributes,
+            field_value,
+            buffer: buffer,
+        })
+    }
+}
+
+pub struct ExtractedFieldWordPosition<'a, 'b> {
+    tokenizer: &'a Tokenizer<'a>,
+    max_positions_per_attributes: u16,
+    field_value: Value,
+    buffer: &'b mut String,
+}
+
+impl<'a> ExtractedFieldWordPosition<'a, '_> {
+    pub fn iter<'o>(&'o mut self) -> FieldWordPositionIter<'o> {
+        self.buffer.clear();
+        let inner = match json_to_string(&self.field_value, &mut self.buffer) {
+            Some(field) => Some(self.tokenizer.tokenize(field)),
+            None => None,
+        };
+
+        // create an iterator of token with their positions.
+        FieldWordPositionIter {
+            inner,
+            max_positions_per_attributes: self.max_positions_per_attributes,
+            position: 0,
+            prev_kind: None,
+        }
+    }
+}
+
+pub struct FieldWordPositionIter<'a> {
+    inner: Option<NormalizedTokenIter<'a, 'a>>,
+    max_positions_per_attributes: u16,
+    position: u16,
+    prev_kind: Option<TokenKind>,
+}
+
+impl<'a> Iterator for FieldWordPositionIter<'a> {
+    type Item = (u16, Token<'a>);
+
+    fn next(&mut self) -> Option<Self::Item> {
+        if self.position >= self.max_positions_per_attributes {
+            return None;
+        }
+
+        let token = self.inner.as_mut().map(|i| i.next()).flatten()?;
+
+        match token.kind {
+            TokenKind::Word | TokenKind::StopWord if !token.lemma().is_empty() => {
+                self.position += match self.prev_kind {
+                    Some(TokenKind::Separator(SeparatorKind::Hard)) => 8,
+                    Some(_) => 1,
+                    None => 0,
+                };
+                self.prev_kind = Some(token.kind)
+            }
+            TokenKind::Separator(_) if self.position == 0 => {
+                return self.next();
+            }
+            TokenKind::Separator(SeparatorKind::Hard) => {
+                self.prev_kind = Some(token.kind);
+            }
+            TokenKind::Separator(SeparatorKind::Soft)
+                if self.prev_kind != Some(TokenKind::Separator(SeparatorKind::Hard)) =>
+            {
+                self.prev_kind = Some(token.kind);
+            }
+            _ => return self.next(),
+        }
+
+        if !token.is_word() {
+            return self.next();
+        }
+
+        // keep a word only if it is not empty and fit in a LMDB key.
+        let lemma = token.lemma().trim();
+        if !lemma.is_empty() && lemma.len() <= MAX_WORD_LENGTH {
+            Some((self.position, token))
+        } else {
+            self.next()
+        }
+    }
+}
+
+/// Factorize tokenizer building.
+pub fn tokenizer_builder<'a>(
+    stop_words: Option<&'a fst::Set<Vec<u8>>>,
+    allowed_separators: Option<&'a [&str]>,
+    dictionary: Option<&'a [&str]>,
+    script_language: Option<&'a HashMap<Script, Vec<Language>>>,
+) -> TokenizerBuilder<'a, Vec<u8>> {
+    let mut tokenizer_builder = TokenizerBuilder::new();
+    if let Some(stop_words) = stop_words {
+        tokenizer_builder.stop_words(stop_words);
+    }
+    if let Some(dictionary) = dictionary {
+        tokenizer_builder.words_dict(dictionary);
+    }
+    if let Some(separators) = allowed_separators {
+        tokenizer_builder.separators(separators);
+    }
+
+    if let Some(script_language) = script_language {
+        tokenizer_builder.allow_list(script_language);
+    }
+
+    tokenizer_builder
+}
+
+/// Transform a JSON value into a string that can be indexed.
+fn json_to_string<'a>(value: &'a Value, buffer: &'a mut String) -> Option<&'a str> {
+    fn inner(value: &Value, output: &mut String) -> bool {
+        use std::fmt::Write;
+        match value {
+            Value::Null | Value::Object(_) => false,
+            Value::Bool(boolean) => write!(output, "{}", boolean).is_ok(),
+            Value::Number(number) => write!(output, "{}", number).is_ok(),
+            Value::String(string) => write!(output, "{}", string).is_ok(),
+            Value::Array(array) => {
+                let mut count = 0;
+                for value in array {
+                    if inner(value, output) {
+                        output.push_str(". ");
+                        count += 1;
+                    }
+                }
+                // check that at least one value was written
+                count != 0
+            }
+        }
+    }
+
+    if let Value::String(string) = value {
+        Some(string)
+    } else if inner(value, buffer) {
+        Some(buffer)
+    } else {
+        None
+    }
+}

milli/src/update/index_documents/extract/searchable/mod.rs

@@ -0,0 +1,114 @@
+use std::collections::{BTreeMap, BTreeSet};
+use std::convert::TryInto;
+use std::fs::File;
+use std::io;
+use std::io::BufReader;
+
+use field_word_position::FieldWordPositionExtractorBuilder;
+use obkv::KvReader;
+use roaring::RoaringBitmap;
+use word_docids::{WordDocidsDump, WordDocidsExtractor};
+
+use crate::update::del_add::{DelAdd, KvReaderDelAdd};
+use crate::update::index_documents::extract::extract_docid_word_positions::ScriptLanguageDocidsMap;
+use crate::update::index_documents::GrenadParameters;
+use crate::update::settings::InnerIndexSettingsDiff;
+use crate::{FieldId, Result, SerializationError};
+
+mod field_word_position;
+mod word_docids;
+
+#[tracing::instrument(level = "trace", skip_all, target = "indexing::extract")]
+pub fn extract_searchable_data<R: io::Read + io::Seek>(
+    obkv_documents: grenad::Reader<R>,
+    indexer: GrenadParameters,
+    settings_diff: &InnerIndexSettingsDiff,
+    max_positions_per_attributes: Option<u32>,
+) -> Result<(grenad::Reader<BufReader<File>>, ScriptLanguageDocidsMap)> {
+    let searchable_fields_to_index = settings_diff.searchable_fields_to_index();
+
+    let mut documents_ids = RoaringBitmap::new();
+
+    let add_builder =
+        FieldWordPositionExtractorBuilder::new(max_positions_per_attributes, &settings_diff.new)?;
+    let add_token_positions_extractor = add_builder.build();
+    let del_builder;
+    let del_token_positions_extractor = if settings_diff.settings_update_only {
+        del_builder = FieldWordPositionExtractorBuilder::new(
+            max_positions_per_attributes,
+            &settings_diff.old,
+        )?;
+        del_builder.build()
+    } else {
+        add_builder.build()
+    };
+    let token_positions_extractor = &[del_token_positions_extractor, add_token_positions_extractor];
+
+    let mut word_map = BTreeMap::new();
+    let mut word_docids_extractor = WordDocidsExtractor::new(settings_diff);
+
+    let mut cursor = obkv_documents.into_cursor()?;
+    // loop over documents
+    while let Some((key, value)) = cursor.move_on_next()? {
+        let document_id = key
+            .try_into()
+            .map(u32::from_be_bytes)
+            .map_err(|_| SerializationError::InvalidNumberSerialization)?;
+        let obkv = KvReader::<FieldId>::new(value);
+        // if the searchable fields didn't change, skip the searchable indexing for this document.
+        if !settings_diff.reindex_searchable()
+            && !searchable_fields_changed(&obkv, &searchable_fields_to_index)
+        {
+            continue;
+        }
+
+        documents_ids.push(document_id);
+
+        let mut buffer = String::new();
+        for field_id in searchable_fields_to_index.iter() {
+            let Some(field_obkv) = obkv.get(*field_id).map(KvReaderDelAdd::new) else { continue };
+
+            for (deladd, field_bytes) in field_obkv {
+                let mut extracted_positions =
+                    token_positions_extractor[deladd as usize].extract(field_bytes, &mut buffer)?;
+                for (position, token) in extracted_positions.iter() {
+                    let word = token.lemma().trim();
+                    if !word_map.contains_key(word) {
+                        word_map.insert(word.to_string(), word_map.len() as u32);
+                    }
+                    let word_id = word_map.get(word).unwrap();
+                    word_docids_extractor.insert(*word_id, *field_id, document_id, deladd);
+                }
+            }
+        }
+
+        if word_docids_extractor.rough_size_estimate()
+            > indexer.max_memory.map_or(512 * 1024 * 1024, |s| s.min(512 * 1024 * 1024))
+        {
+            let WordDocidsDump { .. } =
+                word_docids_extractor.dump(&word_map, &searchable_fields_to_index, indexer)?;
+        }
+    }
+
+    todo!()
+}
+
+/// Check if any searchable fields of a document changed.
+fn searchable_fields_changed(
+    obkv: &KvReader<FieldId>,
+    searchable_fields: &BTreeSet<FieldId>,
+) -> bool {
+    for field_id in searchable_fields {
+        let Some(field_obkv) = obkv.get(*field_id).map(KvReaderDelAdd::new) else { continue };
+        match (field_obkv.get(DelAdd::Deletion), field_obkv.get(DelAdd::Addition)) {
+            // if both fields are None, check the next field.
+            (None, None) => (),
+            // if both contains a value and values are the same, check the next field.
+            (Some(del), Some(add)) if del == add => (),
+            // otherwise the fields are different, return true.
+            _otherwise => return true,
+        }
+    }
+
+    false
+}

milli/src/update/index_documents/extract/searchable/word_docids.rs

@@ -0,0 +1,203 @@
+use std::collections::hash_map::Entry::{Occupied, Vacant};
+use std::collections::{BTreeMap, BTreeSet, HashMap, HashSet};
+use std::fs::File;
+use std::hash::Hash;
+use std::io::BufReader;
+use std::mem::size_of;
+
+use roaring::RoaringBitmap;
+
+use crate::update::del_add::KvWriterDelAdd;
+use crate::update::index_documents::extract::searchable::DelAdd;
+use crate::update::index_documents::{create_writer, writer_into_reader, GrenadParameters};
+use crate::update::settings::InnerIndexSettingsDiff;
+use crate::{CboRoaringBitmapCodec, DocumentId, FieldId, Result};
+
+pub struct WordDocidsExtractor<'a> {
+    word_fid_docids: RevertedIndex<(u32, FieldId)>,
+    settings_diff: &'a InnerIndexSettingsDiff,
+}
+
+impl<'a> WordDocidsExtractor<'a> {
+    pub fn new(settings_diff: &'a InnerIndexSettingsDiff) -> Self {
+        Self { word_fid_docids: RevertedIndex::new(), settings_diff }
+    }
+    pub fn insert(&mut self, wordid: u32, fieldid: FieldId, docid: DocumentId, del_add: DelAdd) {
+        self.word_fid_docids.insert((wordid, fieldid), docid, del_add);
+    }
+
+    pub fn rough_size_estimate(&self) -> usize {
+        self.word_fid_docids.rough_size_estimate()
+    }
+
+    pub fn dump(
+        &mut self,
+        word_map: &BTreeMap<String, u32>,
+        fields: &BTreeSet<FieldId>,
+        indexer: GrenadParameters,
+    ) -> Result<WordDocidsDump> {
+        let mut word_fid_docids_writer = create_writer(
+            indexer.chunk_compression_type,
+            indexer.chunk_compression_level,
+            tempfile::tempfile()?,
+        );
+
+        let mut word_docids_writer = create_writer(
+            indexer.chunk_compression_type,
+            indexer.chunk_compression_level,
+            tempfile::tempfile()?,
+        );
+
+        let mut exact_word_docids_writer = create_writer(
+            indexer.chunk_compression_type,
+            indexer.chunk_compression_level,
+            tempfile::tempfile()?,
+        );
+
+        let mut exact_word_deletion = RoaringBitmap::new();
+        let mut exact_word_addition = RoaringBitmap::new();
+        let mut word_deletion = RoaringBitmap::new();
+        let mut word_addition = RoaringBitmap::new();
+        let mut key_buffer = Vec::new();
+        let mut bitmap_buffer = Vec::new();
+        let mut obkv_buffer = Vec::new();
+        for (word, wid) in word_map {
+            exact_word_deletion.clear();
+            exact_word_addition.clear();
+            word_deletion.clear();
+            word_addition.clear();
+            for fid in fields {
+                if let Some((deletion, addition)) = self.word_fid_docids.inner.get(&(*wid, *fid)) {
+                    if self.settings_diff.old.exact_attributes.contains(&fid) {
+                        exact_word_deletion |= deletion;
+                    } else {
+                        word_deletion |= deletion;
+                    }
+
+                    if self.settings_diff.new.exact_attributes.contains(&fid) {
+                        exact_word_addition |= addition;
+                    } else {
+                        word_addition |= addition;
+                    }
+
+                    if deletion != addition {
+                        key_buffer.clear();
+                        key_buffer.extend_from_slice(word.as_bytes());
+                        key_buffer.push(0);
+                        key_buffer.extend_from_slice(&fid.to_be_bytes());
+                        let value = bitmaps_into_deladd_obkv(
+                            deletion,
+                            addition,
+                            &mut obkv_buffer,
+                            &mut bitmap_buffer,
+                        )?;
+                        word_fid_docids_writer.insert(&key_buffer, value)?;
+                    }
+                }
+            }
+
+            key_buffer.clear();
+            key_buffer.extend_from_slice(word.as_bytes());
+            if exact_word_deletion != exact_word_addition {
+                let value = bitmaps_into_deladd_obkv(
+                    &exact_word_deletion,
+                    &exact_word_addition,
+                    &mut obkv_buffer,
+                    &mut bitmap_buffer,
+                )?;
+                exact_word_docids_writer.insert(&key_buffer, value)?;
+            }
+
+            if word_deletion != word_addition {
+                let value = bitmaps_into_deladd_obkv(
+                    &word_deletion,
+                    &word_addition,
+                    &mut obkv_buffer,
+                    &mut bitmap_buffer,
+                )?;
+                word_docids_writer.insert(&key_buffer, value)?;
+            }
+        }
+
+        self.word_fid_docids.clear();
+
+        Ok(WordDocidsDump {
+            word_fid_docids: writer_into_reader(word_fid_docids_writer)?,
+            word_docids: writer_into_reader(word_docids_writer)?,
+            exact_word_docids: writer_into_reader(exact_word_docids_writer)?,
+        })
+    }
+}
+
+fn bitmaps_into_deladd_obkv<'a>(
+    deletion: &RoaringBitmap,
+    addition: &RoaringBitmap,
+    obkv_buffer: &'a mut Vec<u8>,
+    bitmap_buffer: &mut Vec<u8>,
+) -> Result<&'a mut Vec<u8>> {
+    obkv_buffer.clear();
+    let mut value_writer = KvWriterDelAdd::new(obkv_buffer);
+    if !deletion.is_empty() {
+        bitmap_buffer.clear();
+        CboRoaringBitmapCodec::serialize_into(deletion, bitmap_buffer);
+        value_writer.insert(DelAdd::Deletion, &*bitmap_buffer)?;
+    }
+    if !addition.is_empty() {
+        bitmap_buffer.clear();
+        CboRoaringBitmapCodec::serialize_into(addition, bitmap_buffer);
+        value_writer.insert(DelAdd::Addition, &*bitmap_buffer)?;
+    }
+    Ok(value_writer.into_inner()?)
+}
+
+#[derive(Debug)]
+struct RevertedIndex<K> {
+    inner: HashMap<K, (RoaringBitmap, RoaringBitmap)>,
+    max_value_size: usize,
+}
+
+impl<K: PartialEq + Eq + Hash> RevertedIndex<K> {
+    pub fn insert(&mut self, key: K, docid: DocumentId, del_add: DelAdd) {
+        let size = match self.inner.entry(key) {
+            Occupied(mut entry) => {
+                let (ref mut del, ref mut add) = entry.get_mut();
+                match del_add {
+                    DelAdd::Deletion => del.insert(docid),
+                    DelAdd::Addition => add.insert(docid),
+                };
+                del.serialized_size() + add.serialized_size()
+            }
+            Vacant(entry) => {
+                let mut bitmap = RoaringBitmap::new();
+                bitmap.insert(docid);
+                let size = bitmap.serialized_size();
+                match del_add {
+                    DelAdd::Deletion => entry.insert((bitmap, RoaringBitmap::new())),
+                    DelAdd::Addition => entry.insert((RoaringBitmap::new(), bitmap)),
+                };
+                size * 2
+            }
+        };
+
+        self.max_value_size = self.max_value_size.max(size);
+    }
+
+    pub fn new() -> Self {
+        Self { inner: HashMap::new(), max_value_size: 0 }
+    }
+
+    pub fn rough_size_estimate(&self) -> usize {
+        self.inner.len() * size_of::<K>() + self.inner.len() * self.max_value_size
+    }
+
+    fn clear(&mut self) {
+        self.max_value_size = 0;
+        self.inner.clear();
+    }
+}
+
+pub struct WordDocidsDump {
+    pub word_fid_docids: grenad::Reader<BufReader<File>>,
+    pub word_docids: grenad::Reader<BufReader<File>>,
+    pub exact_word_docids: grenad::Reader<BufReader<File>>,
+}