Skip to content

add: extend pgvector vector search functionality #17415

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from
Closed

add: extend pgvector vector search functionality #17415

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7a1e5d1
add: extend pgvector vector search functionality
muzammilvd Dec 24, 2024
1ec3f80
change: include vector_search_method in cls return
muzammilvd Jan 28, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
77 changes: 70 additions & 7 deletions ...ctor_stores/llama-index-vector-stores-postgres/llama_index/vector_stores/postgres/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -130,6 +130,7 @@ class PGVectorStore(BasePydanticVectorStore):
user="postgres",
table_name="paul_graham_essay",
embed_dim=1536 # openai embedding dimension
vector_search_method="cosine_distance" # Optional specify vector search method. Default is cosine_distance.
)
```
"""
Expand Down Expand Up @@ -272,6 +273,7 @@ def from_params(
use_jsonb: bool = False,
hnsw_kwargs: Optional[Dict[str, Any]] = None,
create_engine_kwargs: Optional[Dict[str, Any]] = None,
vector_search_method: Optional[str] = "cosine_distance",
) -> "PGVectorStore":
"""Construct from params.

Expand All @@ -296,6 +298,7 @@ def from_params(
contains "hnsw_ef_construction", "hnsw_ef_search", "hnsw_m", and optionally "hnsw_dist_method". Defaults to None,
which turns off HNSW search.
create_engine_kwargs (Optional[Dict[str, Any]], optional): Engine parameters to pass to create_engine. Defaults to None.
vector_search_method (Optional[str], optional): Vector search method. Defaults to cosine_distance.

Returns:
PGVectorStore: Instance of PGVectorStore constructed from params.
Expand All @@ -321,6 +324,7 @@ def from_params(
use_jsonb=use_jsonb,
hnsw_kwargs=hnsw_kwargs,
create_engine_kwargs=create_engine_kwargs,
vector_search_method=vector_search_method,
)

@property
Expand Down Expand Up @@ -597,13 +601,72 @@ def _build_query(
) -> Any:
from sqlalchemy import select, text

stmt = select( # type: ignore
self._table_class.id,
self._table_class.node_id,
self._table_class.text,
self._table_class.metadata_,
self._table_class.embedding.cosine_distance(embedding).label("distance"),
).order_by(text("distance asc"))
match self.vector_search_method:
case "cosine_distance":
stmt = select( # type: ignore
self._table_class.id,
self._table_class.node_id,
self._table_class.text,
self._table_class.metadata_,
self._table_class.embedding.cosine_distance(embedding).label(
"distance"
),
).order_by(text("distance asc"))

case "max_inner_product":
stmt = select( # type: ignore
self._table_class.id,
self._table_class.node_id,
self._table_class.text,
self._table_class.metadata_,
self._table_class.embedding.max_inner_product(embedding).label(
"distance"
),
).order_by(text("distance asc"))

case "l2_distance":
stmt = select( # type: ignore
self._table_class.id,
self._table_class.node_id,
self._table_class.text,
self._table_class.metadata_,
self._table_class.embedding.l2_distance(embedding).label(
"distance"
),
).order_by(text("distance asc"))

case "l1_distance":
stmt = select( # type: ignore
self._table_class.id,
self._table_class.node_id,
self._table_class.text,
self._table_class.metadata_,
self._table_class.embedding.l1_distance(embedding).label(
"distance"
),
).order_by(text("distance asc"))

case "hamming_distance":
stmt = select( # type: ignore
self._table_class.id,
self._table_class.node_id,
self._table_class.text,
self._table_class.metadata_,
self._table_class.embedding.hamming_distance(embedding).label(
"distance"
),
).order_by(text("distance asc"))

case "jaccard_distance":
stmt = select( # type: ignore
self._table_class.id,
self._table_class.node_id,
self._table_class.text,
self._table_class.metadata_,
self._table_class.embedding.jaccard_distance(embedding).label(
"distance"
),
).order_by(text("distance asc"))

return self._apply_filters_and_limit(stmt, limit, metadata_filters)

Expand Down