phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update inference adapters

Browse source
This commit is contained in:
Xi Yan 2024-09-11 19:58:20 -07:00
parent 29d1ef3fdc
commit 7d6ebf4b72
5 changed files with 75 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

23
llama_toolchain/inference/adapters/ollama/ollama.py
View file

@ -84,7 +84,28 @@ class OllamaInferenceAdapter(Inference):
return options
async def chat_completion(self, request: ChatCompletionRequest) -> AsyncGenerator:
async def chat_completion(
self,
model: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = SamplingParams(),
tools: Optional[List[ToolDefinition]] = list(),
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
request = ChatCompletionRequest(
model=model,
messages=messages,
sampling_params=sampling_params,
tools=tools,
tool_choice=tool_choice,
tool_prompt_format=tool_prompt_format,
stream=stream,
logprobs=logprobs,
)
messages = prepare_messages(request)
# accumulate sampling params and other options to pass to ollama
options = self.get_ollama_chat_options(request)