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

moar fixes

Browse source
This commit is contained in:
Ashwin Bharambe 2025-10-02 10:56:32 -07:00
parent c1c06e6e2f
commit d9b47218c6
35 changed files with 6269 additions and 611 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/utils/inference/openai_compat.py
View file

@ -635,7 +635,7 @@ async def convert_message_to_openai_dict_new(
id=tool.call_id,
function=OpenAIFunction(
name=(tool.tool_name if not isinstance(tool.tool_name, BuiltinTool) else tool.tool_name.value),
arguments=json.dumps(tool.arguments),
arguments=tool.arguments, # Already a JSON string, don't double-encode
),
type="function",
)

52
llama_stack/providers/utils/inference/openai_mixin.py
View file

@ -286,34 +286,34 @@ class OpenAIMixin(ModelRegistryHelper, NeedsRequestProviderData, ABC):
messages = [await _localize_image_url(m) for m in messages]
resp = await self.client.chat.completions.create(
**await prepare_openai_completion_params(
model=await self._get_provider_model_id(model),
messages=messages,
frequency_penalty=frequency_penalty,
function_call=function_call,
functions=functions,
logit_bias=logit_bias,
logprobs=logprobs,
max_completion_tokens=max_completion_tokens,
max_tokens=max_tokens,
n=n,
parallel_tool_calls=parallel_tool_calls,
presence_penalty=presence_penalty,
response_format=response_format,
seed=seed,
stop=stop,
stream=stream,
stream_options=stream_options,
temperature=temperature,
tool_choice=tool_choice,
tools=tools,
top_logprobs=top_logprobs,
top_p=top_p,
user=user,
)
params = await prepare_openai_completion_params(
model=await self._get_provider_model_id(model),
messages=messages,
frequency_penalty=frequency_penalty,
function_call=function_call,
functions=functions,
logit_bias=logit_bias,
logprobs=logprobs,
max_completion_tokens=max_completion_tokens,
max_tokens=max_tokens,
n=n,
parallel_tool_calls=parallel_tool_calls,
presence_penalty=presence_penalty,
response_format=response_format,
seed=seed,
stop=stop,
stream=stream,
stream_options=stream_options,
temperature=temperature,
tool_choice=tool_choice,
tools=tools,
top_logprobs=top_logprobs,
top_p=top_p,
user=user,
)
resp = await self.client.chat.completions.create(**params)
return await self._maybe_overwrite_id(resp, stream) # type: ignore[no-any-return]
async def openai_embeddings(