phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 05:39:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

implement embedding generation in supported inference providers (#589)

Browse source 
This PR adds the ability to generate embeddings in all supported
inference providers.

```
pytest -v -s llama_stack/providers/tests/inference/test_embeddings.py -k "bedrock" --inference-model="amazon.titan-embed-text-v2:0"  --env EMBEDDING_DIMENSION=1024

 pytest -v -s -k "vllm"  --inferrence-model="intfloat/e5-mistral-7b-instruct"  llama_stack/providers/tests/inference/test_embeddings.py --env EMBEDDING_DIMENSION=4096  --env VLLM_URL="http://localhost:9798/v1"

pytest -v -s --inference-model="nomic-ai/nomic-embed-text-v1.5"  llama_stack/providers/tests/inference/test_embeddings.py  -k "fireworks"  --env FIREWORKS_API_KEY=<API_KEY>--env EMBEDDING_DIMENSION=128

pytest -v -s --inference-model="togethercomputer/m2-bert-80M-2k-retrieval"  llama_stack/providers/tests/inference/test_embeddings.py  -k "together"  --env TOGETHER_API_KEY=<API_KEY>--env EMBEDDING_DIMENSION=768

pytest -v -s -k "ollama"  --inference-model="all-minilm:v8"  llama_stack/providers/tests/inference/test_embeddings.py --env EMBEDDING_DIMENSION=384

 torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference" --inference-model="sentence-transformers/all-MiniLM-L6-v2"  llama_stack/providers/tests/inference/test_embeddings.py --env EMBEDDING_DIMENSION=384

```
This commit is contained in:
Dinesh Yeduguru 2024-12-12 11:17:39 -08:00
parent 6a23f24ee0
commit d362d2d740
32 changed files with 597 additions and 143 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/providers/registry/memory.py
View file

@ -39,6 +39,7 @@ def available_providers() -> List[ProviderSpec]:
module="llama_stack.providers.inline.memory.faiss",
config_class="llama_stack.providers.inline.memory.faiss.FaissImplConfig",
deprecation_warning="Please use the `inline::faiss` provider instead.",
api_dependencies=[Api.inference],
),
InlineProviderSpec(
api=Api.memory,
@ -46,6 +47,7 @@ def available_providers() -> List[ProviderSpec]:
pip_packages=EMBEDDING_DEPS + ["faiss-cpu"],
module="llama_stack.providers.inline.memory.faiss",
config_class="llama_stack.providers.inline.memory.faiss.FaissImplConfig",
api_dependencies=[Api.inference],
),
remote_provider_spec(
Api.memory,
@ -55,6 +57,7 @@ def available_providers() -> List[ProviderSpec]:
module="llama_stack.providers.remote.memory.chroma",
config_class="llama_stack.providers.remote.memory.chroma.ChromaRemoteImplConfig",
),
api_dependencies=[Api.inference],
),
InlineProviderSpec(
api=Api.memory,
@ -71,6 +74,7 @@ def available_providers() -> List[ProviderSpec]:
module="llama_stack.providers.remote.memory.pgvector",
config_class="llama_stack.providers.remote.memory.pgvector.PGVectorConfig",
),
api_dependencies=[Api.inference],
),
remote_provider_spec(
Api.memory,
@ -81,6 +85,7 @@ def available_providers() -> List[ProviderSpec]:
config_class="llama_stack.providers.remote.memory.weaviate.WeaviateConfig",
provider_data_validator="llama_stack.providers.remote.memory.weaviate.WeaviateRequestProviderData",
),
api_dependencies=[Api.inference],
),
remote_provider_spec(
api=Api.memory,
@ -90,6 +95,7 @@ def available_providers() -> List[ProviderSpec]:
module="llama_stack.providers.remote.memory.sample",
config_class="llama_stack.providers.remote.memory.sample.SampleConfig",
),
api_dependencies=[],
),
remote_provider_spec(
Api.memory,
@ -99,5 +105,6 @@ def available_providers() -> List[ProviderSpec]:
module="llama_stack.providers.remote.memory.qdrant",
config_class="llama_stack.providers.remote.memory.qdrant.QdrantConfig",
),
api_dependencies=[Api.inference],
),
]