phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

remove conflicting default for tool prompt format in chat completion (#742)

Browse source 
# What does this PR do?
We are setting a default value of json for tool prompt format, which
conflicts with llama 3.2/3.3 models since they use python list. This PR
changes the defaults to None and in the code, we infer default based on
the model.

Addresses: #695 

Tests:
❯ LLAMA_STACK_BASE_URL=http://localhost:5000 pytest -v
tests/client-sdk/inference/test_inference.py -k
"test_text_chat_completion"

 pytest llama_stack/providers/tests/inference/test_prompt_adapter.py
This commit is contained in:
Dinesh Yeduguru 2025-01-10 10:41:53 -08:00 • committed by GitHub
parent 24fa1adc2f
commit 8af6951106
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
21 changed files with 27 additions and 91 deletions
Download patch file Download diff file Expand all files Collapse all files

15
llama_stack/apis/inference/inference.py
View file

@ -5,7 +5,6 @@
# the root directory of this source tree.
from enum import Enum
from typing import (
Any,
AsyncIterator,
@ -26,16 +25,12 @@ from llama_models.llama3.api.datatypes import (
ToolDefinition,
ToolPromptFormat,
)
from llama_models.schema_utils import json_schema_type, register_schema, webmethod
from pydantic import BaseModel, Field, field_validator
from typing_extensions import Annotated
from llama_stack.apis.common.content_types import InterleavedContent
from llama_stack.apis.models import Model
from llama_stack.providers.utils.telemetry.trace_protocol import trace_protocol
@ -256,9 +251,7 @@ class ChatCompletionRequest(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)
response_format: Optional[ResponseFormat] = None
stream: Optional[bool] = False
@ -289,9 +282,7 @@ 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
@ -334,7 +325,7 @@ class Inference(Protocol):
# zero-shot tool definitions as input to the model
tools: Optional[List[ToolDefinition]] = None,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
tool_prompt_format: Optional[ToolPromptFormat] = None,
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,