phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: implement keyword, vector and hybrid search inside vector stores for PGVector provider (#3064)

Browse source 
# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
The purpose of this task is to implement
`openai/v1/vector_stores/{vector_store_id}/search` for PGVector
provider. It involves implementing vector similarity search, keyword
search and hybrid search for `PGVectorIndex`.

<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->
Closes #3006 

## Test Plan
<!-- Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.* -->
Run unit tests:
` ./scripts/unit-tests.sh `

Run integration tests for openai vector stores:
1. Export env vars:
```
export ENABLE_PGVECTOR=true
export PGVECTOR_HOST=localhost
export PGVECTOR_PORT=5432
export PGVECTOR_DB=llamastack
export PGVECTOR_USER=llamastack
export PGVECTOR_PASSWORD=llamastack
```

2. Create DB:
```
psql -h localhost -U postgres -c "CREATE ROLE llamastack LOGIN PASSWORD 'llamastack';"
psql -h localhost -U postgres -c "CREATE DATABASE llamastack OWNER llamastack;"
psql -h localhost -U llamastack -d llamastack -c "CREATE EXTENSION IF NOT EXISTS vector;"
```

3. Install sentence-transformers:
` uv pip install sentence-transformers  `

4. Run:
```
uv run --group test pytest -s -v --stack-config="inference=inline::sentence-transformers,vector_io=remote::pgvector" --embedding-model sentence-transformers/all-MiniLM-L6-v2 tests/integration/vector_io/test_openai_vector_stores.py
```
Inspect PGVector vector stores (optional):
```
psql llamastack                                                                                                         
psql (14.18 (Homebrew))
Type "help" for help.

llamastack=# \z
                                                    Access privileges
 Schema |                         Name                         | Type  | Access privileges | Column privileges | Policies 
--------+------------------------------------------------------+-------+-------------------+-------------------+----------
 public | llamastack_kvstore                                   | table |                   |                   | 
 public | metadata_store                                       | table |                   |                   | 
 public | vector_store_pgvector_main                           | table |                   |                   | 
 public | vector_store_vs_1dfbc061_1f4d_4497_9165_ecba2622ba3a | table |                   |                   | 
 public | vector_store_vs_2085a9fb_1822_4e42_a277_c6a685843fa7 | table |                   |                   | 
 public | vector_store_vs_2b3dae46_38be_462a_afd6_37ee5fe661b1 | table |                   |                   | 
 public | vector_store_vs_2f438de6_f606_4561_9d50_ef9160eb9060 | table |                   |                   | 
 public | vector_store_vs_3eeca564_2580_4c68_bfea_83dc57e31214 | table |                   |                   | 
 public | vector_store_vs_53942163_05f3_40e0_83c0_0997c64613da | table |                   |                   | 
 public | vector_store_vs_545bac75_8950_4ff1_b084_e221192d4709 | table |                   |                   | 
 public | vector_store_vs_688a37d8_35b2_4298_a035_bfedf5b21f86 | table |                   |                   | 
 public | vector_store_vs_70624d9a_f6ac_4c42_b8ab_0649473c6600 | table |                   |                   | 
 public | vector_store_vs_73fc1dd2_e942_4972_afb1_1e177b591ac2 | table |                   |                   | 
 public | vector_store_vs_9d464949_d51f_49db_9f87_e033b8b84ac9 | table |                   |                   | 
 public | vector_store_vs_a1e4d724_5162_4d6d_a6c0_bdafaf6b76ec | table |                   |                   | 
 public | vector_store_vs_a328fb1b_1a21_480f_9624_ffaa60fb6672 | table |                   |                   | 
 public | vector_store_vs_a8981bf0_2e66_4445_a267_a8fff442db53 | table |                   |                   | 
 public | vector_store_vs_ccd4b6a4_1efd_4984_ad03_e7ff8eadb296 | table |                   |                   | 
 public | vector_store_vs_cd6420a4_a1fc_4cec_948c_1413a26281c9 | table |                   |                   | 
 public | vector_store_vs_cd709284_e5cf_4a88_aba5_dc76a35364bd | table |                   |                   | 
 public | vector_store_vs_d7a4548e_fbc1_44d7_b2ec_b664417f2a46 | table |                   |                   | 
 public | vector_store_vs_e7f73231_414c_4523_886c_d1174eee836e | table |                   |                   | 
 public | vector_store_vs_ffd53588_819f_47e8_bb9d_954af6f7833d | table |                   |                   | 
(23 rows)

llamastack=# 
```

Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com>
This commit is contained in:
IAN MILLER 2025-08-29 15:30:12 +01:00 • committed by GitHub
parent e96e3c4da4
commit 3130ca0a78
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 1014 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

121
tests/unit/providers/vector_io/conftest.py
View file

@ -5,6 +5,7 @@
# the root directory of this source tree.
import random
from unittest.mock import AsyncMock, MagicMock, patch
import numpy as np
import pytest
@ -12,7 +13,7 @@ from chromadb import PersistentClient
from pymilvus import MilvusClient, connections
from llama_stack.apis.vector_dbs import VectorDB
from llama_stack.apis.vector_io import Chunk, ChunkMetadata
from llama_stack.apis.vector_io import Chunk, ChunkMetadata, QueryChunksResponse
from llama_stack.providers.inline.vector_io.chroma.config import ChromaVectorIOConfig
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.providers.inline.vector_io.faiss.faiss import FaissIndex, FaissVectorIOAdapter
@ -22,6 +23,8 @@ from llama_stack.providers.inline.vector_io.sqlite_vec import SQLiteVectorIOConf
from llama_stack.providers.inline.vector_io.sqlite_vec.sqlite_vec import SQLiteVecIndex, SQLiteVecVectorIOAdapter
from llama_stack.providers.remote.vector_io.chroma.chroma import ChromaIndex, ChromaVectorIOAdapter, maybe_await
from llama_stack.providers.remote.vector_io.milvus.milvus import MilvusIndex, MilvusVectorIOAdapter
from llama_stack.providers.remote.vector_io.pgvector.config import PGVectorVectorIOConfig
from llama_stack.providers.remote.vector_io.pgvector.pgvector import PGVectorIndex, PGVectorVectorIOAdapter
from llama_stack.providers.remote.vector_io.qdrant.qdrant import QdrantVectorIOAdapter
EMBEDDING_DIMENSION = 384
@ -29,7 +32,7 @@ COLLECTION_PREFIX = "test_collection"
MILVUS_ALIAS = "test_milvus"
@pytest.fixture(params=["milvus", "sqlite_vec", "faiss", "chroma"])
@pytest.fixture(params=["milvus", "sqlite_vec", "faiss", "chroma", "pgvector"])
def vector_provider(request):
return request.param
@ -333,15 +336,127 @@ async def qdrant_vec_index(qdrant_vec_db_path, embedding_dimension):
await index.delete()
@pytest.fixture
def mock_psycopg2_connection():
connection = MagicMock()
cursor = MagicMock()
cursor.__enter__ = MagicMock(return_value=cursor)
cursor.__exit__ = MagicMock()
connection.cursor.return_value = cursor
return connection, cursor
@pytest.fixture
async def pgvector_vec_index(embedding_dimension, mock_psycopg2_connection):
connection, cursor = mock_psycopg2_connection
vector_db = VectorDB(
identifier="test-vector-db",
embedding_model="test-model",
embedding_dimension=embedding_dimension,
provider_id="pgvector",
provider_resource_id="pgvector:test-vector-db",
)
with patch("llama_stack.providers.remote.vector_io.pgvector.pgvector.psycopg2"):
with patch("llama_stack.providers.remote.vector_io.pgvector.pgvector.execute_values"):
index = PGVectorIndex(vector_db, embedding_dimension, connection, distance_metric="COSINE")
index._test_chunks = []
original_add_chunks = index.add_chunks
async def mock_add_chunks(chunks, embeddings):
index._test_chunks = list(chunks)
await original_add_chunks(chunks, embeddings)
index.add_chunks = mock_add_chunks
async def mock_query_vector(embedding, k, score_threshold):
chunks = index._test_chunks[:k] if hasattr(index, "_test_chunks") else []
scores = [1.0] * len(chunks)
return QueryChunksResponse(chunks=chunks, scores=scores)
index.query_vector = mock_query_vector
yield index
@pytest.fixture
async def pgvector_vec_adapter(mock_inference_api, embedding_dimension):
config = PGVectorVectorIOConfig(
host="localhost",
port=5432,
db="test_db",
user="test_user",
password="test_password",
kvstore=SqliteKVStoreConfig(),
)
adapter = PGVectorVectorIOAdapter(config, mock_inference_api, None)
with patch("llama_stack.providers.remote.vector_io.pgvector.pgvector.psycopg2.connect") as mock_connect:
mock_conn = MagicMock()
mock_cursor = MagicMock()
mock_cursor.__enter__ = MagicMock(return_value=mock_cursor)
mock_cursor.__exit__ = MagicMock()
mock_conn.cursor.return_value = mock_cursor
mock_conn.autocommit = True
mock_connect.return_value = mock_conn
with patch(
"llama_stack.providers.remote.vector_io.pgvector.pgvector.check_extension_version"
) as mock_check_version:
mock_check_version.return_value = "0.5.1"
with patch("llama_stack.providers.utils.kvstore.kvstore_impl") as mock_kvstore_impl:
mock_kvstore = AsyncMock()
mock_kvstore_impl.return_value = mock_kvstore
with patch.object(adapter, "initialize_openai_vector_stores", new_callable=AsyncMock):
with patch("llama_stack.providers.remote.vector_io.pgvector.pgvector.upsert_models"):
await adapter.initialize()
adapter.conn = mock_conn
async def mock_insert_chunks(vector_db_id, chunks, ttl_seconds=None):
index = await adapter._get_and_cache_vector_db_index(vector_db_id)
if not index:
raise ValueError(f"Vector DB {vector_db_id} not found")
await index.insert_chunks(chunks)
adapter.insert_chunks = mock_insert_chunks
async def mock_query_chunks(vector_db_id, query, params=None):
index = await adapter._get_and_cache_vector_db_index(vector_db_id)
if not index:
raise ValueError(f"Vector DB {vector_db_id} not found")
return await index.query_chunks(query, params)
adapter.query_chunks = mock_query_chunks
test_vector_db = VectorDB(
identifier=f"pgvector_test_collection_{random.randint(1, 1_000_000)}",
provider_id="test_provider",
embedding_model="test_model",
embedding_dimension=embedding_dimension,
)
await adapter.register_vector_db(test_vector_db)
adapter.test_collection_id = test_vector_db.identifier
yield adapter
await adapter.shutdown()
@pytest.fixture
def vector_io_adapter(vector_provider, request):
"""Returns the appropriate vector IO adapter based on the provider parameter."""
vector_provider_dict = {
"milvus": "milvus_vec_adapter",
"faiss": "faiss_vec_adapter",
"sqlite_vec": "sqlite_vec_adapter",
"chroma": "chroma_vec_adapter",
"qdrant": "qdrant_vec_adapter",
"pgvector": "pgvector_vec_adapter",
}
return request.getfixturevalue(vector_provider_dict[vector_provider])