mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-17 13:42:39 +00:00
implement embedding generation in supported inference providers (#589)
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:
parent
6a23f24ee0
commit
d362d2d740
32 changed files with 597 additions and 143 deletions
|
|
@ -18,6 +18,12 @@ def pytest_addoption(parser):
|
|||
default=None,
|
||||
help="Specify the inference model to use for testing",
|
||||
)
|
||||
parser.addoption(
|
||||
"--embedding-model",
|
||||
action="store",
|
||||
default=None,
|
||||
help="Specify the embedding model to use for testing",
|
||||
)
|
||||
|
||||
|
||||
def pytest_configure(config):
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue