phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

refactor(test): unify vector_io tests and make them configurable (#1398)

Browse source 
## 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)
This commit is contained in:
Ashwin Bharambe 2025-03-04 13:37:45 -08:00 • committed by GitHub
parent fd8c991393
commit dd0db8038b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
27 changed files with 117 additions and 559 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/templates/hf-endpoint/hf_endpoint.py
View file

@ -51,7 +51,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
)
inference_model = ModelInput(