phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 02:53:30 +00:00
Code Issues Projects Releases Packages Wiki 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/bedrock/bedrock.py
View file

@ -34,7 +34,7 @@ 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}"),
)
available_models = {

2
llama_stack/templates/cerebras/cerebras.py
View file

@ -62,7 +62,7 @@ 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}"),
)
default_tool_groups = [
ToolGroupInput(

2
llama_stack/templates/ci-tests/ci_tests.py
View file

@ -48,7 +48,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="sqlite-vec",
provider_type="inline::sqlite-vec",
config=SQLiteVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=SQLiteVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
)
embedding_provider = Provider(
provider_id="sentence-transformers",

2
llama_stack/templates/dev/dev.py
View file

@ -100,7 +100,7 @@ def get_distribution_template() -> DistributionTemplate:
Provider(
provider_id="sqlite-vec",
provider_type="inline::sqlite-vec",
config=SQLiteVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=SQLiteVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
),
Provider(
provider_id="${env.ENABLE_CHROMADB+chromadb}",

2
llama_stack/templates/fireworks/fireworks.py
View file

@ -56,7 +56,7 @@ 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}"),
)
available_models = {

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(

2
llama_stack/templates/hf-serverless/hf_serverless.py
View file

@ -52,7 +52,7 @@ 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(

2
llama_stack/templates/meta-reference-gpu/meta_reference.py
View file

@ -58,7 +58,7 @@ 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(

2
llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py
View file

@ -67,7 +67,7 @@ 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(

2
llama_stack/templates/ollama/ollama.py
View file

@ -45,7 +45,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider_sqlite = Provider(
provider_id="sqlite-vec",
provider_type="inline::sqlite-vec",
config=SQLiteVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=SQLiteVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
)
inference_model = ModelInput(

2
llama_stack/templates/remote-vllm/vllm.py
View file

@ -55,7 +55,7 @@ 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(

2
llama_stack/templates/sambanova/sambanova.py
View file

@ -46,7 +46,7 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(
__distro_dir__=f"distributions/{name}",
__distro_dir__=f"~/.llama/distributions/{name}",
),
),
Provider(

4
llama_stack/templates/template.py
View file

@ -86,7 +86,7 @@ class RunConfigSettings(BaseModel):
config_class = instantiate_class_type(config_class)
if hasattr(config_class, "sample_run_config"):
config = config_class.sample_run_config(__distro_dir__=f"distributions/{name}")
config = config_class.sample_run_config(__distro_dir__=f"~/.llama/distributions/{name}")
else:
config = {}
@ -107,7 +107,7 @@ class RunConfigSettings(BaseModel):
apis=apis,
providers=provider_configs,
metadata_store=SqliteKVStoreConfig.sample_run_config(
__distro_dir__=f"distributions/{name}",
__distro_dir__=f"~/.llama/distributions/{name}",
db_name="registry.db",
),
models=self.default_models or [],

2
llama_stack/templates/tgi/tgi.py
View file

@ -55,7 +55,7 @@ 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(

2
llama_stack/templates/together/together.py
View file

@ -49,7 +49,7 @@ 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}"),
)
embedding_provider = Provider(
provider_id="sentence-transformers",

2
llama_stack/templates/vllm-gpu/vllm.py
View file

@ -46,7 +46,7 @@ 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}"),
)
embedding_provider = Provider(
provider_id="sentence-transformers",