phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-15 23:32:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Ran precommit

Browse source
This commit is contained in:
Omar Abdelwahab 2025-10-06 13:27:19 -07:00
parent 9886520b40
commit 9fc0d966f6
7 changed files with 153 additions and 310 deletions
Download patch file Download diff file Expand all files Collapse all files

38
llama_stack/apis/inference/inference.py
View file

@ -8,6 +8,9 @@ from collections.abc import AsyncIterator
from enum import Enum
from typing import Annotated, Any, Literal, Protocol, runtime_checkable
from pydantic import BaseModel, Field, field_validator
from typing_extensions import TypedDict
from llama_stack.apis.common.content_types import ContentDelta, InterleavedContent
from llama_stack.apis.common.responses import Order
from llama_stack.apis.models import Model
@ -23,9 +26,6 @@ from llama_stack.models.llama.datatypes import (
from llama_stack.providers.utils.telemetry.trace_protocol import trace_protocol
from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
from pydantic import BaseModel, Field, field_validator
from typing_extensions import TypedDict
register_schema(ToolCall)
register_schema(ToolDefinition)
@ -381,9 +381,7 @@ class ToolConfig(BaseModel):
tool_choice: ToolChoice | str | None = Field(default=ToolChoice.auto)
tool_prompt_format: ToolPromptFormat | None = Field(default=None)
system_message_behavior: SystemMessageBehavior | None = Field(
default=SystemMessageBehavior.append
)
system_message_behavior: SystemMessageBehavior | None = Field(default=SystemMessageBehavior.append)
def model_post_init(self, __context: Any) -> None:
if isinstance(self.tool_choice, str):
@ -512,21 +510,15 @@ class OpenAIFile(BaseModel):
OpenAIChatCompletionContentPartParam = Annotated[
OpenAIChatCompletionContentPartTextParam
| OpenAIChatCompletionContentPartImageParam
| OpenAIFile,
OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam | OpenAIFile,
Field(discriminator="type"),
]
register_schema(
OpenAIChatCompletionContentPartParam, name="OpenAIChatCompletionContentPartParam"
)
register_schema(OpenAIChatCompletionContentPartParam, name="OpenAIChatCompletionContentPartParam")
OpenAIChatCompletionMessageContent = str | list[OpenAIChatCompletionContentPartParam]
OpenAIChatCompletionTextOnlyMessageContent = (
str | list[OpenAIChatCompletionContentPartTextParam]
)
OpenAIChatCompletionTextOnlyMessageContent = str | list[OpenAIChatCompletionContentPartTextParam]
@json_schema_type
@ -694,9 +686,7 @@ class OpenAIResponseFormatJSONObject(BaseModel):
OpenAIResponseFormatParam = Annotated[
OpenAIResponseFormatText
| OpenAIResponseFormatJSONSchema
| OpenAIResponseFormatJSONObject,
OpenAIResponseFormatText | OpenAIResponseFormatJSONSchema | OpenAIResponseFormatJSONObject,
Field(discriminator="type"),
]
register_schema(OpenAIResponseFormatParam, name="OpenAIResponseFormatParam")
@ -986,16 +976,8 @@ class InferenceProvider(Protocol):
async def rerank(
self,
model: str,
query: (
str
| OpenAIChatCompletionContentPartTextParam
| OpenAIChatCompletionContentPartImageParam
),
items: list[
str
| OpenAIChatCompletionContentPartTextParam
| OpenAIChatCompletionContentPartImageParam
],
query: (str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam),
items: list[str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam],
max_num_results: int | None = None,
) -> RerankResponse:
"""Rerank a list of documents based on their relevance to a query.