phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-13 04:22:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add response format to signature

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-21 19:14:52 -07:00 • committed by Ashwin Bharambe
parent 6d26bbdce3
commit 40ba22f4c8
15 changed files with 93 additions and 32 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/adapters/inference/tgi/tgi.py
View file

@ -71,6 +71,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
model: str,
content: InterleavedTextMedia,
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
@ -81,6 +82,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
model: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
tools: Optional[List[ToolDefinition]] = None,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,