phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 17:22:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

address feedback

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-12-11 16:24:37 -08:00
parent e167e9eb93
commit 5821ec9ef3
12 changed files with 61 additions and 76 deletions
Download patch file Download diff file Expand all files Collapse all files

13
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -29,6 +29,7 @@ from llama_stack.providers.utils.inference.openai_compat import (
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_prompt,
completion_request_to_prompt,
content_has_media,
convert_message_to_dict,
request_has_media,
)
@ -206,10 +207,16 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
model = await self.model_store.get_model(model_id)
kwargs = {}
if model.metadata.get("embedding_dimensions"):
kwargs["dimensions"] = model.metadata.get("embedding_dimensions")
assert model.model_type == ModelType.embedding_model
assert model.metadata.get("embedding_dimensions")
kwargs["dimensions"] = model.metadata.get("embedding_dimensions")
assert all(
not content_has_media(content) for content in contents
), "VLLM does not support media for embeddings"
response = self.client.embeddings.create(
model=model.provider_resource_id, input=contents, **kwargs
model=model.provider_resource_id,
input=[interleaved_text_media_as_str(content) for content in contents],
**kwargs,
)
embeddings = [data.embedding for data in response.data]