phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 20:02:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Rework InterleavedContentMedia datatype so URL downloading is in llama-stack

Browse source
This commit is contained in:
Ashwin Bharambe 2024-12-15 13:23:30 -08:00
parent c2f7905fa4
commit a9a041a1de
10 changed files with 368 additions and 146 deletions
Download patch file Download diff file Expand all files Collapse all files

11
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -22,6 +22,7 @@ from llama_stack.providers.utils.inference.model_registry import (
ModelRegistryHelper,
)
from llama_stack.providers.utils.inference.openai_compat import (
convert_message_to_openai_dict,
get_sampling_options,
process_chat_completion_response,
process_chat_completion_stream_response,
@ -30,7 +31,7 @@ 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,
interleaved_content_as_str,
request_has_media,
)
@ -71,7 +72,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
async def completion(
self,
model_id: str,
content: InterleavedTextMedia,
content: InterleavedContent,
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
@ -163,7 +164,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
if media_present:
# vllm does not seem to work well with image urls, so we download the images
input_dict["messages"] = [
await convert_message_to_dict(m, download=True)
await convert_message_to_openai_dict(m, download=True)
for m in request.messages
]
else:
@ -202,7 +203,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
async def embeddings(
self,
model_id: str,
contents: List[InterleavedTextMedia],
contents: List[InterleavedContent],
) -> EmbeddingsResponse:
model = await self.model_store.get_model(model_id)
@ -215,7 +216,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
), "VLLM does not support media for embeddings"
response = self.client.embeddings.create(
model=model.provider_resource_id,
input=[interleaved_text_media_as_str(content) for content in contents],
input=[interleaved_content_as_str(content) for content in contents],
**kwargs,
)