huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-24 00:12:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Readd tool_prompt

Browse Source
This commit is contained in:
Thomas SCHILLACI 2024-05-07 19:30:18 +02:00
parent 2f644779cb
commit 4607b7e9c4
2 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
clients/python/text_generation/client.py
View File

@ -171,6 +171,7 @@ class Client:
temperature: Optional[float] = None,
top_p: Optional[float] = None,
tools: Optional[List[Tool]] = None,
tool_prompt: Optional[str] = None,
tool_choice: Optional[str] = None,
stop: Optional[List[str]] = None,
):
@ -211,6 +212,8 @@ class Client:
higher are kept for generation
tools (`List[Tool]`):
List of tools to use
tool_prompt (`str`):
A prompt to be appended before the tools
tool_choice (`str`):
The tool to use
stop (`List[str]`):
@ -233,6 +236,7 @@ class Client:
temperature=temperature,
top_p=top_p,
tools=tools,
tool_prompt=tool_prompt,
tool_choice=tool_choice,
stop=stop,
)
@ -648,6 +652,7 @@ class AsyncClient:
temperature: Optional[float] = None,
top_p: Optional[float] = None,
tools: Optional[List[Tool]] = None,
tool_prompt: Optional[str] = None,
tool_choice: Optional[str] = None,
stop: Optional[List[str]] = None,
) -> Union[ChatComplete, AsyncIterator[ChatCompletionChunk]]:
@ -688,6 +693,8 @@ class AsyncClient:
higher are kept for generation
tools (`List[Tool]`):
List of tools to use
tool_prompt (`str`):
A prompt to be appended before the tools
tool_choice (`str`):
The tool to use
stop (`List[str]`):
@ -710,6 +717,7 @@ class AsyncClient:
temperature=temperature,
top_p=top_p,
tools=tools,
tool_prompt=tool_prompt,
tool_choice=tool_choice,
stop=stop,
)
@ -967,4 +975,4 @@ class AsyncClient:
except ValidationError:
# If we failed to parse the payload, then it is an error payload
raise parse_error(resp.status, json_payload)
yield response
yield response

2
clients/python/text_generation/types.py
View File

@ -453,4 +453,4 @@ class StreamResponse(BaseModel):
# Inference API currently deployed model
class DeployedModel(BaseModel):
model_id: str
sha: str
sha: str