phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-01 10:34:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

infer tool prompt format

Browse source
This commit is contained in:
Dinesh Yeduguru 2025-01-09 17:22:18 -08:00
parent 4938f2fe5d
commit 5f69747b89
21 changed files with 29 additions and 87 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/apis/batch_inference/batch_inference.py
View file

@ -7,7 +7,6 @@
from typing import List, Optional, Protocol, runtime_checkable
from llama_models.schema_utils import json_schema_type, webmethod
from pydantic import BaseModel, Field
from llama_stack.apis.inference import (
@ -44,9 +43,7 @@ class BatchChatCompletionRequest(BaseModel):
# zero-shot tool definitions as input to the model
tools: Optional[List[ToolDefinition]] = Field(default_factory=list)
tool_choice: Optional[ToolChoice] = Field(default=ToolChoice.auto)
tool_prompt_format: Optional[ToolPromptFormat] = Field(
default=ToolPromptFormat.json
)
tool_prompt_format: Optional[ToolPromptFormat] = Field(default=None)
logprobs: Optional[LogProbConfig] = None
@ -75,6 +72,6 @@ class BatchInference(Protocol):
# zero-shot tool definitions as input to the model
tools: Optional[List[ToolDefinition]] = list,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
tool_prompt_format: Optional[ToolPromptFormat] = None,
logprobs: Optional[LogProbConfig] = None,
) -> BatchChatCompletionResponse: ...