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

chore: more mypy fixes (#2029)

Browse source 
# What does this PR do?

Mainly tried to cover the entire llama_stack/apis directory, we only
have one left. Some excludes were just noop.

Signed-off-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Sébastien Han 2025-05-06 18:52:31 +02:00 • committed by GitHub
parent feb9eb8b0d
commit 1a529705da
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
27 changed files with 581 additions and 166 deletions
Download patch file Download diff file Expand all files Collapse all files

27
llama_stack/apis/inference/inference.py
View file

@ -4,6 +4,7 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
import sys
from collections.abc import AsyncIterator
from enum import Enum
from typing import (
@ -35,6 +36,16 @@ register_schema(ToolCall)
register_schema(ToolParamDefinition)
register_schema(ToolDefinition)
# TODO: use enum.StrEnum when we drop support for python 3.10
if sys.version_info >= (3, 11):
from enum import StrEnum
else:
class StrEnum(str, Enum):
"""Backport of StrEnum for Python 3.10 and below."""
pass
@json_schema_type
class GreedySamplingStrategy(BaseModel):
@ -187,7 +198,7 @@ class CompletionMessage(BaseModel):
role: Literal["assistant"] = "assistant"
content: InterleavedContent
stop_reason: StopReason
tool_calls: list[ToolCall] | None = Field(default_factory=list)
tool_calls: list[ToolCall] | None = Field(default_factory=lambda: [])
Message = Annotated[
@ -267,7 +278,7 @@ class ChatCompletionResponseEvent(BaseModel):
stop_reason: StopReason | None = None
class ResponseFormatType(Enum):
class ResponseFormatType(StrEnum):
"""Types of formats for structured (guided) decoding.
:cvar json_schema: Response should conform to a JSON schema. In a Python SDK, this is often a `pydantic` model.
@ -286,7 +297,7 @@ class JsonSchemaResponseFormat(BaseModel):
:param json_schema: The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model.
"""
type: Literal[ResponseFormatType.json_schema.value] = ResponseFormatType.json_schema.value
type: Literal[ResponseFormatType.json_schema] = ResponseFormatType.json_schema
json_schema: dict[str, Any]
@ -298,7 +309,7 @@ class GrammarResponseFormat(BaseModel):
:param bnf: The BNF grammar specification the response should conform to
"""
type: Literal[ResponseFormatType.grammar.value] = ResponseFormatType.grammar.value
type: Literal[ResponseFormatType.grammar] = ResponseFormatType.grammar
bnf: dict[str, Any]
@ -394,7 +405,7 @@ class ChatCompletionRequest(BaseModel):
messages: list[Message]
sampling_params: SamplingParams | None = Field(default_factory=SamplingParams)
tools: list[ToolDefinition] | None = Field(default_factory=list)
tools: list[ToolDefinition] | None = Field(default_factory=lambda: [])
tool_config: ToolConfig | None = Field(default_factory=ToolConfig)
response_format: ResponseFormat | None = None
@ -567,14 +578,14 @@ class OpenAIResponseFormatText(BaseModel):
@json_schema_type
class OpenAIJSONSchema(TypedDict, total=False):
name: str
description: str | None = None
strict: bool | None = None
description: str | None
strict: bool | None
# Pydantic BaseModel cannot be used with a schema param, since it already
# has one. And, we don't want to alias here because then have to handle
# that alias when converting to OpenAI params. So, to support schema,
# we use a TypedDict.
schema: dict[str, Any] | None = None
schema: dict[str, Any] | None
@json_schema_type