phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-18 07:18:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Enable vision models for Together and Fireworks

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-05 12:29:07 -08:00
parent 8de845a96d
commit 03013dafc1
9 changed files with 297 additions and 35 deletions
Download patch file Download diff file Expand all files Collapse all files

45
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
@ -102,7 +104,7 @@ class TogetherInferenceAdapter(
return process_completion_response(r, self.formatter)
async def _stream_completion(self, request: CompletionRequest) -> AsyncGenerator:
params = self._get_params_for_completion(request)
params = 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,
@ -172,7 +166,10 @@ class TogetherInferenceAdapter(
self, request: ChatCompletionRequest
) -> ChatCompletionResponse:
params = self._get_params(request)
r = self._get_client().completions.create(**params)
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(
@ -182,7 +179,10 @@ class TogetherInferenceAdapter(
# 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:
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"] = [
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),
}