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

35
uv.lock generated
View file

@ -1859,6 +1859,7 @@ test = [
{ name = "mcp" },
{ name = "milvus-lite" },
{ name = "openai" },
{ name = "psycopg2-binary" },
{ name = "pymilvus" },
{ name = "pypdf" },
{ name = "requests" },
@ -1884,6 +1885,7 @@ unit = [
{ name = "moto", extra = ["s3"] },
{ name = "ollama" },
{ name = "openai" },
{ name = "psycopg2-binary" },
{ name = "pymilvus" },
{ name = "pypdf" },
{ name = "qdrant-client" },
@ -1978,6 +1980,7 @@ test = [
{ name = "mcp" },
{ name = "milvus-lite", specifier = ">=2.5.0" },
{ name = "openai" },
{ name = "psycopg2-binary", specifier = ">=2.9.0" },
{ name = "pymilvus", specifier = ">=2.5.12" },
{ name = "pypdf" },
{ name = "requests" },
@ -2002,6 +2005,7 @@ unit = [
{ name = "moto", extras = ["s3"], specifier = ">=5.1.10" },
{ name = "ollama" },
{ name = "openai" },
{ name = "psycopg2-binary", specifier = ">=2.9.0" },
{ name = "pymilvus", specifier = ">=2.5.12" },
{ name = "pypdf" },
{ name = "qdrant-client" },
@ -3139,6 +3143,37 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/50/1b/6921afe68c74868b4c9fa424dad3be35b095e16687989ebbb50ce4fceb7c/psutil-7.0.0-cp37-abi3-win_amd64.whl", hash = "sha256:4cf3d4eb1aa9b348dec30105c55cd9b7d4629285735a102beb4441e38db90553", size = 244885, upload-time = "2025-02-13T21:54:37.486Z" },
]
[[package]]
name = "psycopg2-binary"
version = "2.9.10"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/cb/0e/bdc8274dc0585090b4e3432267d7be4dfbfd8971c0fa59167c711105a6bf/psycopg2-binary-2.9.10.tar.gz", hash = "sha256:4b3df0e6990aa98acda57d983942eff13d824135fe2250e6522edaa782a06de2", size = 385764, upload-time = "2024-10-16T11:24:58.126Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/49/7d/465cc9795cf76f6d329efdafca74693714556ea3891813701ac1fee87545/psycopg2_binary-2.9.10-cp312-cp312-macosx_12_0_x86_64.whl", hash = "sha256:880845dfe1f85d9d5f7c412efea7a08946a46894537e4e5d091732eb1d34d9a0", size = 3044771, upload-time = "2024-10-16T11:20:35.234Z" },
{ url = "https://files.pythonhosted.org/packages/8b/31/6d225b7b641a1a2148e3ed65e1aa74fc86ba3fee850545e27be9e1de893d/psycopg2_binary-2.9.10-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:9440fa522a79356aaa482aa4ba500b65f28e5d0e63b801abf6aa152a29bd842a", size = 3275336, upload-time = "2024-10-16T11:20:38.742Z" },
{ url = "https://files.pythonhosted.org/packages/30/b7/a68c2b4bff1cbb1728e3ec864b2d92327c77ad52edcd27922535a8366f68/psycopg2_binary-2.9.10-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e3923c1d9870c49a2d44f795df0c889a22380d36ef92440ff618ec315757e539", size = 2851637, upload-time = "2024-10-16T11:20:42.145Z" },
{ url = "https://files.pythonhosted.org/packages/0b/b1/cfedc0e0e6f9ad61f8657fd173b2f831ce261c02a08c0b09c652b127d813/psycopg2_binary-2.9.10-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7b2c956c028ea5de47ff3a8d6b3cc3330ab45cf0b7c3da35a2d6ff8420896526", size = 3082097, upload-time = "2024-10-16T11:20:46.185Z" },
{ url = "https://files.pythonhosted.org/packages/18/ed/0a8e4153c9b769f59c02fb5e7914f20f0b2483a19dae7bf2db54b743d0d0/psycopg2_binary-2.9.10-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f758ed67cab30b9a8d2833609513ce4d3bd027641673d4ebc9c067e4d208eec1", size = 3264776, upload-time = "2024-10-16T11:20:50.879Z" },
{ url = "https://files.pythonhosted.org/packages/10/db/d09da68c6a0cdab41566b74e0a6068a425f077169bed0946559b7348ebe9/psycopg2_binary-2.9.10-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8cd9b4f2cfab88ed4a9106192de509464b75a906462fb846b936eabe45c2063e", size = 3020968, upload-time = "2024-10-16T11:20:56.819Z" },
{ url = "https://files.pythonhosted.org/packages/94/28/4d6f8c255f0dfffb410db2b3f9ac5218d959a66c715c34cac31081e19b95/psycopg2_binary-2.9.10-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6dc08420625b5a20b53551c50deae6e231e6371194fa0651dbe0fb206452ae1f", size = 2872334, upload-time = "2024-10-16T11:21:02.411Z" },
{ url = "https://files.pythonhosted.org/packages/05/f7/20d7bf796593c4fea95e12119d6cc384ff1f6141a24fbb7df5a668d29d29/psycopg2_binary-2.9.10-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:d7cd730dfa7c36dbe8724426bf5612798734bff2d3c3857f36f2733f5bfc7c00", size = 2822722, upload-time = "2024-10-16T11:21:09.01Z" },
{ url = "https://files.pythonhosted.org/packages/4d/e4/0c407ae919ef626dbdb32835a03b6737013c3cc7240169843965cada2bdf/psycopg2_binary-2.9.10-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:155e69561d54d02b3c3209545fb08938e27889ff5a10c19de8d23eb5a41be8a5", size = 2920132, upload-time = "2024-10-16T11:21:16.339Z" },
{ url = "https://files.pythonhosted.org/packages/2d/70/aa69c9f69cf09a01da224909ff6ce8b68faeef476f00f7ec377e8f03be70/psycopg2_binary-2.9.10-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:c3cc28a6fd5a4a26224007712e79b81dbaee2ffb90ff406256158ec4d7b52b47", size = 2959312, upload-time = "2024-10-16T11:21:25.584Z" },
{ url = "https://files.pythonhosted.org/packages/d3/bd/213e59854fafe87ba47814bf413ace0dcee33a89c8c8c814faca6bc7cf3c/psycopg2_binary-2.9.10-cp312-cp312-win32.whl", hash = "sha256:ec8a77f521a17506a24a5f626cb2aee7850f9b69a0afe704586f63a464f3cd64", size = 1025191, upload-time = "2024-10-16T11:21:29.912Z" },
{ url = "https://files.pythonhosted.org/packages/92/29/06261ea000e2dc1e22907dbbc483a1093665509ea586b29b8986a0e56733/psycopg2_binary-2.9.10-cp312-cp312-win_amd64.whl", hash = "sha256:18c5ee682b9c6dd3696dad6e54cc7ff3a1a9020df6a5c0f861ef8bfd338c3ca0", size = 1164031, upload-time = "2024-10-16T11:21:34.211Z" },
{ url = "https://files.pythonhosted.org/packages/3e/30/d41d3ba765609c0763505d565c4d12d8f3c79793f0d0f044ff5a28bf395b/psycopg2_binary-2.9.10-cp313-cp313-macosx_12_0_x86_64.whl", hash = "sha256:26540d4a9a4e2b096f1ff9cce51253d0504dca5a85872c7f7be23be5a53eb18d", size = 3044699, upload-time = "2024-10-16T11:21:42.841Z" },
{ url = "https://files.pythonhosted.org/packages/35/44/257ddadec7ef04536ba71af6bc6a75ec05c5343004a7ec93006bee66c0bc/psycopg2_binary-2.9.10-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:e217ce4d37667df0bc1c397fdcd8de5e81018ef305aed9415c3b093faaeb10fb", size = 3275245, upload-time = "2024-10-16T11:21:51.989Z" },
{ url = "https://files.pythonhosted.org/packages/1b/11/48ea1cd11de67f9efd7262085588790a95d9dfcd9b8a687d46caf7305c1a/psycopg2_binary-2.9.10-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:245159e7ab20a71d989da00f280ca57da7641fa2cdcf71749c193cea540a74f7", size = 2851631, upload-time = "2024-10-16T11:21:57.584Z" },
{ url = "https://files.pythonhosted.org/packages/62/e0/62ce5ee650e6c86719d621a761fe4bc846ab9eff8c1f12b1ed5741bf1c9b/psycopg2_binary-2.9.10-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3c4ded1a24b20021ebe677b7b08ad10bf09aac197d6943bfe6fec70ac4e4690d", size = 3082140, upload-time = "2024-10-16T11:22:02.005Z" },
{ url = "https://files.pythonhosted.org/packages/27/ce/63f946c098611f7be234c0dd7cb1ad68b0b5744d34f68062bb3c5aa510c8/psycopg2_binary-2.9.10-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3abb691ff9e57d4a93355f60d4f4c1dd2d68326c968e7db17ea96df3c023ef73", size = 3264762, upload-time = "2024-10-16T11:22:06.412Z" },
{ url = "https://files.pythonhosted.org/packages/43/25/c603cd81402e69edf7daa59b1602bd41eb9859e2824b8c0855d748366ac9/psycopg2_binary-2.9.10-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8608c078134f0b3cbd9f89b34bd60a943b23fd33cc5f065e8d5f840061bd0673", size = 3020967, upload-time = "2024-10-16T11:22:11.583Z" },
{ url = "https://files.pythonhosted.org/packages/5f/d6/8708d8c6fca531057fa170cdde8df870e8b6a9b136e82b361c65e42b841e/psycopg2_binary-2.9.10-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:230eeae2d71594103cd5b93fd29d1ace6420d0b86f4778739cb1a5a32f607d1f", size = 2872326, upload-time = "2024-10-16T11:22:16.406Z" },
{ url = "https://files.pythonhosted.org/packages/ce/ac/5b1ea50fc08a9df82de7e1771537557f07c2632231bbab652c7e22597908/psycopg2_binary-2.9.10-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:bb89f0a835bcfc1d42ccd5f41f04870c1b936d8507c6df12b7737febc40f0909", size = 2822712, upload-time = "2024-10-16T11:22:21.366Z" },
{ url = "https://files.pythonhosted.org/packages/c4/fc/504d4503b2abc4570fac3ca56eb8fed5e437bf9c9ef13f36b6621db8ef00/psycopg2_binary-2.9.10-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:f0c2d907a1e102526dd2986df638343388b94c33860ff3bbe1384130828714b1", size = 2920155, upload-time = "2024-10-16T11:22:25.684Z" },
{ url = "https://files.pythonhosted.org/packages/b2/d1/323581e9273ad2c0dbd1902f3fb50c441da86e894b6e25a73c3fda32c57e/psycopg2_binary-2.9.10-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:f8157bed2f51db683f31306aa497311b560f2265998122abe1dce6428bd86567", size = 2959356, upload-time = "2024-10-16T11:22:30.562Z" },
{ url = "https://files.pythonhosted.org/packages/08/50/d13ea0a054189ae1bc21af1d85b6f8bb9bbc5572991055d70ad9006fe2d6/psycopg2_binary-2.9.10-cp313-cp313-win_amd64.whl", hash = "sha256:27422aa5f11fbcd9b18da48373eb67081243662f9b46e6fd07c3eb46e4535142", size = 2569224, upload-time = "2025-01-04T20:09:19.234Z" },
]
[[package]]
name = "ptyprocess"
version = "0.7.0"