phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 16:32:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

implement embedding generation in supported inference providers

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-12-09 12:48:56 -08:00
parent b896be2311
commit e167e9eb93
16 changed files with 383 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/registry/inference.py
View file

@ -18,6 +18,7 @@ META_REFERENCE_DEPS = [
"transformers",
"zmq",
"lm-format-enforcer",
"sentence-transformers",
]
@ -52,6 +53,13 @@ def available_providers() -> List[ProviderSpec]:
module="llama_stack.providers.inline.inference.vllm",
config_class="llama_stack.providers.inline.inference.vllm.VLLMConfig",
),
InlineProviderSpec(
api=Api.inference,
provider_type="inline::sentence-transformers",
pip_packages=["sentence-transformers"],
module="llama_stack.providers.inline.inference.sentence_transformers",
config_class="llama_stack.providers.inline.inference.sentence_transformers.config.SentenceTransformersInferenceConfig",
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(