phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Enable vision models for (Together, Fireworks, Meta-Reference, Ollama) (#376)

Browse source 
* Enable vision models for Together and Fireworks

* Works with ollama 0.4.0 pre-release with the vision model

* localize media for meta_reference inference

* Fix
This commit is contained in:
Ashwin Bharambe 2024-11-05 16:22:33 -08:00 • committed by GitHub
parent db30809141
commit cde9bc1388
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 465 additions and 81 deletions
Download patch file Download diff file Expand all files Collapse all files

51
llama_stack/providers/adapters/inference/together/together.py
View file

@ -26,6 +26,8 @@ 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,
convert_message_to_dict,
request_has_media,
)
from .config import TogetherImplConfig
@ -97,12 +99,12 @@ class TogetherInferenceAdapter(
async def _nonstream_completion(
self, request: CompletionRequest
) -> ChatCompletionResponse:
params = self._get_params_for_completion(request)
params = await self._get_params(request)
r = self._get_client().completions.create(**params)
return process_completion_response(r, self.formatter)
async def _stream_completion(self, request: CompletionRequest) -> AsyncGenerator:
params = self._get_params_for_completion(request)
params = await self._get_params(request)
# if we shift to TogetherAsyncClient, we won't need this wrapper
async def _to_async_generator():
@ -131,14 +133,6 @@ class TogetherInferenceAdapter(
return options
def _get_params_for_completion(self, request: CompletionRequest) -> dict:
return {
"model": self.map_to_provider_model(request.model),
"prompt": completion_request_to_prompt(request, self.formatter),
"stream": request.stream,
**self._build_options(request.sampling_params, request.response_format),
}
async def chat_completion(
self,
model: str,
@ -171,18 +165,24 @@ class TogetherInferenceAdapter(
async def _nonstream_chat_completion(
self, request: ChatCompletionRequest
) -> ChatCompletionResponse:
params = self._get_params(request)
r = self._get_client().completions.create(**params)
params = await self._get_params(request)
if "messages" in params:
r = self._get_client().chat.completions.create(**params)
else:
r = self._get_client().completions.create(**params)
return process_chat_completion_response(r, self.formatter)
async def _stream_chat_completion(
self, request: ChatCompletionRequest
) -> AsyncGenerator:
params = self._get_params(request)
params = await self._get_params(request)
# if we shift to TogetherAsyncClient, we won't need this wrapper
async def _to_async_generator():
s = self._get_client().completions.create(**params)
if "messages" in params:
s = self._get_client().chat.completions.create(**params)
else:
s = self._get_client().completions.create(**params)
for chunk in s:
yield chunk
@ -192,10 +192,29 @@ class TogetherInferenceAdapter(
):
yield chunk
def _get_params(self, request: ChatCompletionRequest) -> dict:
async def _get_params(
self, request: Union[ChatCompletionRequest, CompletionRequest]
) -> dict:
input_dict = {}
media_present = request_has_media(request)
if isinstance(request, ChatCompletionRequest):
if media_present:
input_dict["messages"] = [
await convert_message_to_dict(m) for m in request.messages
]
else:
input_dict["prompt"] = chat_completion_request_to_prompt(
request, self.formatter
)
else:
assert (
not media_present
), "Together does not support media for Completion requests"
input_dict["prompt"] = completion_request_to_prompt(request, self.formatter)
return {
"model": self.map_to_provider_model(request.model),
"prompt": chat_completion_request_to_prompt(request, self.formatter),
**input_dict,
"stream": request.stream,
**self._build_options(request.sampling_params, request.response_format),
}