snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2025-07-27 16:51:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

always push the user defined vectors in arroy

Browse Source
This commit is contained in:
Tamo
2024-06-03 16:04:14 +02:00
parent a73ccc78a6
commit 5d50850e12
15 changed files with 189 additions and 450 deletions
Download Patch File Download Diff File Expand all files Collapse all files

244
milli/src/search/new/tests/snapshots/milli__search__new__tests__attribute_fid__attribute_fid_ngrams.snap
View File

@ -1,244 +0,0 @@
---
source: milli/src/search/new/tests/attribute_fid.rs
expression: "format!(\"{document_ids_scores:#?}\")"
---
[
(
2,
[
Fid(
Rank {
rank: 19,
max_rank: 19,
},
),
Position(
Rank {
rank: 91,
max_rank: 91,
},
),
],
),
(
6,
[
Fid(
Rank {
rank: 15,
max_rank: 19,
},
),
Position(
Rank {
rank: 81,
max_rank: 91,
},
),
],
),
(
5,
[
Fid(
Rank {
rank: 14,
max_rank: 19,
},
),
Position(
Rank {
rank: 79,
max_rank: 91,
},
),
],
),
(
4,
[
Fid(
Rank {
rank: 13,
max_rank: 19,
},
),
Position(
Rank {
rank: 77,
max_rank: 91,
},
),
],
),
(
3,
[
Fid(
Rank {
rank: 12,
max_rank: 19,
},
),
Position(
Rank {
rank: 83,
max_rank: 91,
},
),
],
),
(
9,
[
Fid(
Rank {
rank: 11,
max_rank: 19,
},
),
Position(
Rank {
rank: 75,
max_rank: 91,
},
),
],
),
(
8,
[
Fid(
Rank {
rank: 10,
max_rank: 19,
},
),
Position(
Rank {
rank: 79,
max_rank: 91,
},
),
],
),
(
7,
[
Fid(
Rank {
rank: 10,
max_rank: 19,
},
),
Position(
Rank {
rank: 73,
max_rank: 91,
},
),
],
),
(
11,
[
Fid(
Rank {
rank: 7,
max_rank: 19,
},
),
Position(
Rank {
rank: 77,
max_rank: 91,
},
),
],
),
(
10,
[
Fid(
Rank {
rank: 6,
max_rank: 19,
},
),
Position(
Rank {
rank: 81,
max_rank: 91,
},
),
],
),
(
13,
[
Fid(
Rank {
rank: 6,
max_rank: 19,
},
),
Position(
Rank {
rank: 81,
max_rank: 91,
},
),
],
),
(
12,
[
Fid(
Rank {
rank: 6,
max_rank: 19,
},
),
Position(
Rank {
rank: 78,
max_rank: 91,
},
),
],
),
(
14,
[
Fid(
Rank {
rank: 5,
max_rank: 19,
},
),
Position(
Rank {
rank: 75,
max_rank: 91,
},
),
],
),
(
0,
[
Fid(
Rank {
rank: 1,
max_rank: 19,
},
),
Position(
Rank {
rank: 91,
max_rank: 91,
},
),
],
),
]

7
milli/src/snapshots/index.rs/initial_field_distribution/1/field_distribution.snap
View File

@ -1,7 +0,0 @@
---
source: milli/src/index.rs
---
age 1 |
id 2 |
name 2 |

7
milli/src/snapshots/index.rs/initial_field_distribution/field_distribution.snap
View File

@ -1,7 +0,0 @@
---
source: milli/src/index.rs
---
age 1 |
id 2 |
name 2 |

75
milli/src/update/index_documents/extract/extract_vector_points.rs
View File

@ -8,7 +8,6 @@ use std::sync::Arc;
use bytemuck::cast_slice;
use grenad::Writer;
use itertools::EitherOrBoth;
use ordered_float::OrderedFloat;
use roaring::RoaringBitmap;
use serde_json::Value;
@ -50,7 +49,7 @@ enum VectorStateDelta {
// Note: changing the value of the manually specified vector **should not record** this delta
WasGeneratedNowManual(Vec<Vec<f32>>),
ManualDelta(Vec<Vec<f32>>, Vec<Vec<f32>>),
ManualDelta(Vec<Vec<f32>>),
// Add the vector computed from the specified prompt
// Remove any previous vector
@ -59,14 +58,12 @@ enum VectorStateDelta {
}
impl VectorStateDelta {
fn into_values(self) -> (bool, String, (Vec<Vec<f32>>, Vec<Vec<f32>>)) {
fn into_values(self) -> (bool, String, Vec<Vec<f32>>) {
match self {
VectorStateDelta::NoChange => Default::default(),
VectorStateDelta::NowRemoved => (true, Default::default(), Default::default()),
VectorStateDelta::WasGeneratedNowManual(add) => {
(true, Default::default(), (Default::default(), add))
}
VectorStateDelta::ManualDelta(del, add) => (false, Default::default(), (del, add)),
VectorStateDelta::WasGeneratedNowManual(add) => (true, Default::default(), add),
VectorStateDelta::ManualDelta(add) => (false, Default::default(), add),
VectorStateDelta::NowGenerated(prompt) => (true, prompt, Default::default()),
}
}
@ -166,8 +163,14 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
// lazily get it when needed
let document_id = || -> Value { from_utf8(external_id_bytes).unwrap().into() };
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 mut parsed_vectors = ParsedVectorsDiff::new(
docid,
embedders_configs,
obkv,
old_vectors_fid,
new_vectors_fid,
)
.map_err(|error| error.to_crate_error(document_id().to_string()))?;
for EmbedderVectorExtractor {
embedder_name,
@ -182,7 +185,7 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
{
let delta = match parsed_vectors.remove(embedder_name) {
(Some(old), Some(new)) => {
match (old.is_user_provided(), new.is_user_provided()) {
match (old.map_or(true, |old| old.is_user_provided()), new.is_user_provided()) {
(true, true) | (false, false) => (),
(true, false) => {
remove_from_user_defined.insert(docid);
@ -193,7 +196,6 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
}
// no autogeneration
let del_vectors = old.into_array_of_vectors();
let add_vectors = new.into_array_of_vectors();
if add_vectors.len() > usize::from(u8::MAX) {
@ -203,15 +205,15 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
)));
}
VectorStateDelta::ManualDelta(del_vectors, add_vectors)
VectorStateDelta::ManualDelta(add_vectors)
}
(Some(_old), None) => {
(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 {
if document_is_kept && old.is_some() {
remove_from_user_defined.insert(docid);
// becomes autogenerated
VectorStateDelta::NowGenerated(prompt.render(
@ -219,6 +221,8 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
DelAdd::Addition,
new_fields_ids_map,
)?)
} else if document_is_kept && old.is_none() {
VectorStateDelta::NoChange
} else {
VectorStateDelta::NowRemoved
}
@ -315,8 +319,8 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
Ok(results)
}
/// Computes the diff between both Del and Add numbers and
/// only inserts the parts that differ in the sorter.
/// We cannot compute the diff between both Del and Add vectors.
/// We'll push every vector and compute the difference later in TypedChunk.
fn push_vectors_diff(
remove_vectors_writer: &mut Writer<BufWriter<File>>,
prompts_writer: &mut Writer<BufWriter<File>>,
@ -325,7 +329,7 @@ fn push_vectors_diff(
delta: VectorStateDelta,
reindex_vectors: bool,
) -> Result<()> {
let (must_remove, prompt, (mut del_vectors, mut add_vectors)) = delta.into_values();
let (must_remove, prompt, 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.
@ -340,44 +344,25 @@ fn push_vectors_diff(
}
// We sort and dedup the vectors
del_vectors.sort_unstable_by(|a, b| compare_vectors(a, b));
add_vectors.sort_unstable_by(|a, b| compare_vectors(a, b));
del_vectors.dedup_by(|a, b| compare_vectors(a, b).is_eq());
add_vectors.dedup_by(|a, b| compare_vectors(a, b).is_eq());
let merged_vectors_iter =
itertools::merge_join_by(del_vectors, add_vectors, |del, add| compare_vectors(del, add));
// let merged_vectors_iter =
// itertools::merge_join_by(del_vectors, add_vectors, |del, add| compare_vectors(del, add));
// insert vectors into the writer
for (i, eob) in merged_vectors_iter.into_iter().enumerate().take(u16::MAX as usize) {
for (i, vector) in add_vectors.into_iter().enumerate().take(u16::MAX as usize) {
// Generate the key by extending the unique index to it.
key_buffer.truncate(TRUNCATE_SIZE);
let index = u16::try_from(i).unwrap();
key_buffer.extend_from_slice(&index.to_be_bytes());
match eob {
EitherOrBoth::Both(_, _) => (), // no need to touch anything
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 !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();
obkv.insert(DelAdd::Deletion, cast_slice(&vector))?;
let bytes = obkv.into_inner()?;
manual_vectors_writer.insert(&key_buffer, bytes)?;
}
}
EitherOrBoth::Right(vector) => {
// We insert only the Add part of the Obkv to inform
// that we only want to remove all those vectors.
let mut obkv = KvWriterDelAdd::memory();
obkv.insert(DelAdd::Addition, cast_slice(&vector))?;
let bytes = obkv.into_inner()?;
manual_vectors_writer.insert(&key_buffer, bytes)?;
}
}
// We insert only the Add part of the Obkv to inform
// that we only want to remove all those vectors.
let mut obkv = KvWriterDelAdd::memory();
obkv.insert(DelAdd::Addition, cast_slice(&vector))?;
let bytes = obkv.into_inner()?;
manual_vectors_writer.insert(&key_buffer, bytes)?;
}
Ok(())

22
milli/src/vector/parsed_vectors.rs
View File

@ -4,8 +4,9 @@ use obkv::KvReader;
use serde_json::{from_slice, Value};
use super::Embedding;
use crate::index::IndexEmbeddingConfig;
use crate::update::del_add::{DelAdd, KvReaderDelAdd};
use crate::{FieldId, InternalError, UserError};
use crate::{DocumentId, FieldId, InternalError, UserError};
pub const RESERVED_VECTORS_FIELD_NAME: &str = "_vectors";
@ -42,17 +43,19 @@ pub struct ExplicitVectors {
}
pub struct ParsedVectorsDiff {
pub old: Option<BTreeMap<String, Vectors>>,
pub old: BTreeMap<String, Option<Vectors>>,
pub new: Option<BTreeMap<String, Vectors>>,
}
impl ParsedVectorsDiff {
pub fn new(
docid: DocumentId,
embedders_configs: &[IndexEmbeddingConfig],
documents_diff: KvReader<'_, FieldId>,
old_vectors_fid: Option<FieldId>,
new_vectors_fid: Option<FieldId>,
) -> Result<Self, Error> {
let old = match old_vectors_fid
let mut old = match old_vectors_fid
.and_then(|vectors_fid| documents_diff.get(vectors_fid))
.map(KvReaderDelAdd::new)
.map(|obkv| to_vector_map(obkv, DelAdd::Deletion))
@ -68,7 +71,13 @@ impl ParsedVectorsDiff {
return Err(error);
}
}
.flatten();
.flatten().map_or(BTreeMap::default(), |del| del.into_iter().map(|(name, vec)| (name, Some(vec))).collect());
for embedding_config in embedders_configs {
if embedding_config.user_defined.contains(docid) {
old.entry(embedding_config.name.to_string()).or_insert(None);
}
}
let new = new_vectors_fid
.and_then(|vectors_fid| documents_diff.get(vectors_fid))
.map(KvReaderDelAdd::new)
@ -78,8 +87,9 @@ impl ParsedVectorsDiff {
Ok(Self { old, new })
}
pub fn remove(&mut self, embedder_name: &str) -> (Option<Vectors>, Option<Vectors>) {
let old = self.old.as_mut().and_then(|old| old.remove(embedder_name));
/// Return (Some(None), _) in case the vector is user defined and contained in the database.
pub fn remove(&mut self, embedder_name: &str) -> (Option<Option<Vectors>>, Option<Vectors>) {
let old = self.old.remove(embedder_name);
let new = self.new.as_mut().and_then(|new| new.remove(embedder_name));
(old, new)
}