Commit graph

4 commits

Author SHA1 Message Date
Francisco Arceo
9e1ddf2b53
chore: Updating sqlite-vec to make non-blocking calls (#1762)
# What does this PR do?
This PR updates the sqlite-vec database calls to be non-blocking. Note
that each operation creates a new connection, which incurs some
performance overhead but is reasonable given [SQLite's threading and
connections constraints](https://www.sqlite.org/threadsafe.html).

Summary of changes:
- Refactored `SQLiteVecIndex` class to store database path instead of
connection object
- Added `_create_sqlite_connection()` helper function to create
connections on demand
- Ensured proper connection closure in all database operations
- Fixed test fixtures to use a file-based SQLite database for
thread-safety
- Updated the `SQLiteVecVectorIOAdapter` class to handle per-operation
connections

This PR helps chip away at
https://github.com/meta-llama/llama-stack/issues/1489

## Test Plan
sqlite-vec unit tests passed locally as well as a test script using the
client as a library.

## Misc

FYI @varshaprasad96 @kevincogan

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
2025-03-23 17:25:44 -07:00
Daniele Martinoli
cca9bd6cc3
feat: Qdrant inline provider (#1273)
# What does this PR do?
Removed local execution option from the remote Qdrant provider and
introduced an explicit inline provider for the embedded execution.
Updated the ollama template to include this option: this part can be
reverted in case we don't want to have two default `vector_io`
providers.

(Closes #1082)

## Test Plan
Build and run an ollama distro:
```bash
llama stack build --template ollama --image-type conda
llama stack run --image-type conda ollama
```

Run one of the sample ingestionapplicatinos like
[rag_with_vector_db.py](https://github.com/meta-llama/llama-stack-apps/blob/main/examples/agents/rag_with_vector_db.py),
but replace this line:
```py
    selected_vector_provider = vector_providers[0]
```
with the following, to use the `qdrant` provider:
```py
    selected_vector_provider = vector_providers[1]
```

After running the test code, verify the timestamp of the Qdrant store:
```bash
% ls -ltr ~/.llama/distributions/ollama/qdrant.db/collection/test_vector_db_*
total 784
-rw-r--r--@ 1 dmartino  staff  401408 Feb 26 10:07 storage.sqlite
```

[//]: # (## Documentation)

---------

Signed-off-by: Daniele Martinoli <dmartino@redhat.com>
Co-authored-by: Francisco Arceo <farceo@redhat.com>
2025-03-18 14:04:21 -07:00
Ben Browning
00570fde31
chore: Get sqlite_vec and vector_store unit tests passing (#1413) 2025-03-05 13:20:13 -05:00
Ashwin Bharambe
dd0db8038b
refactor(test): unify vector_io tests and make them configurable (#1398)
## Test Plan


`LLAMA_STACK_CONFIG=inference=sentence-transformers,vector_io=sqlite-vec
pytest -s -v test_vector_io.py --embedding-model all-miniLM-L6-V2
--inference-model='' --vision-inference-model=''`

```
test_vector_io.py::test_vector_db_retrieve[txt=:vis=:emb=all-miniLM-L6-V2] PASSED
test_vector_io.py::test_vector_db_register[txt=:vis=:emb=all-miniLM-L6-V2] PASSED
test_vector_io.py::test_insert_chunks[txt=:vis=:emb=all-miniLM-L6-V2-test_case0] PASSED
test_vector_io.py::test_insert_chunks[txt=:vis=:emb=all-miniLM-L6-V2-test_case1] PASSED
test_vector_io.py::test_insert_chunks[txt=:vis=:emb=all-miniLM-L6-V2-test_case2] PASSED
test_vector_io.py::test_insert_chunks[txt=:vis=:emb=all-miniLM-L6-V2-test_case3] PASSED
test_vector_io.py::test_insert_chunks[txt=:vis=:emb=all-miniLM-L6-V2-test_case4] PASSED
```

Same thing with:
- LLAMA_STACK_CONFIG=inference=sentence-transformers,vector_io=faiss
- LLAMA_STACK_CONFIG=fireworks

(Note that ergonomics will soon be improved re: cmd-line options and env
variables)
2025-03-04 13:37:45 -08:00
Renamed from llama_stack/providers/tests/vector_io/test_sqlite_vec.py (Browse further)