forked from phoenix-oss/llama-stack-mirror
chore: enable pyupgrade fixes (#1806)
# What does this PR do? The goal of this PR is code base modernization. Schema reflection code needed a minor adjustment to handle UnionTypes and collections.abc.AsyncIterator. (Both are preferred for latest Python releases.) Note to reviewers: almost all changes here are automatically generated by pyupgrade. Some additional unused imports were cleaned up. The only change worth of note can be found under `docs/openapi_generator` and `llama_stack/strong_typing/schema.py` where reflection code was updated to deal with "newer" types. Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
This commit is contained in:
Ihar Hrachyshka
GitHub
parent
ffe3d0b2cd
commit
9e6561a1ec
319 changed files with 2843 additions and 3033 deletions
|
|
@ -5,7 +5,8 @@
|
|||
# the root directory of this source tree.
|
||||
import json
|
||||
import logging
|
||||
from typing import Any, AsyncGenerator, AsyncIterator, Dict, List, Optional, Union
|
||||
from collections.abc import AsyncGenerator, AsyncIterator
|
||||
from typing import Any
|
||||
|
||||
import httpx
|
||||
from openai import AsyncOpenAI
|
||||
|
|
@ -94,7 +95,7 @@ def build_hf_repo_model_entries():
|
|||
|
||||
def _convert_to_vllm_tool_calls_in_response(
|
||||
tool_calls,
|
||||
) -> List[ToolCall]:
|
||||
) -> list[ToolCall]:
|
||||
if not tool_calls:
|
||||
return []
|
||||
|
||||
|
|
@ -109,7 +110,7 @@ def _convert_to_vllm_tool_calls_in_response(
|
|||
]
|
||||
|
||||
|
||||
def _convert_to_vllm_tools_in_request(tools: List[ToolDefinition]) -> List[dict]:
|
||||
def _convert_to_vllm_tools_in_request(tools: list[ToolDefinition]) -> list[dict]:
|
||||
compat_tools = []
|
||||
|
||||
for tool in tools:
|
||||
|
|
@ -262,10 +263,10 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
|
|||
self,
|
||||
model_id: str,
|
||||
content: InterleavedContent,
|
||||
sampling_params: Optional[SamplingParams] = None,
|
||||
response_format: Optional[ResponseFormat] = None,
|
||||
stream: Optional[bool] = False,
|
||||
logprobs: Optional[LogProbConfig] = None,
|
||||
sampling_params: SamplingParams | None = None,
|
||||
response_format: ResponseFormat | None = None,
|
||||
stream: bool | None = False,
|
||||
logprobs: LogProbConfig | None = None,
|
||||
) -> CompletionResponse | AsyncGenerator[CompletionResponseStreamChunk, None]:
|
||||
self._lazy_initialize_client()
|
||||
if sampling_params is None:
|
||||
|
|
@ -287,15 +288,15 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
|
|||
async def chat_completion(
|
||||
self,
|
||||
model_id: str,
|
||||
messages: List[Message],
|
||||
sampling_params: Optional[SamplingParams] = None,
|
||||
tools: Optional[List[ToolDefinition]] = None,
|
||||
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
|
||||
tool_prompt_format: Optional[ToolPromptFormat] = None,
|
||||
response_format: Optional[ResponseFormat] = None,
|
||||
stream: Optional[bool] = False,
|
||||
logprobs: Optional[LogProbConfig] = None,
|
||||
tool_config: Optional[ToolConfig] = None,
|
||||
messages: list[Message],
|
||||
sampling_params: SamplingParams | None = None,
|
||||
tools: list[ToolDefinition] | None = None,
|
||||
tool_choice: ToolChoice | None = ToolChoice.auto,
|
||||
tool_prompt_format: ToolPromptFormat | None = None,
|
||||
response_format: ResponseFormat | None = None,
|
||||
stream: bool | None = False,
|
||||
logprobs: LogProbConfig | None = None,
|
||||
tool_config: ToolConfig | None = None,
|
||||
) -> ChatCompletionResponse | AsyncGenerator[ChatCompletionResponseStreamChunk, None]:
|
||||
self._lazy_initialize_client()
|
||||
if sampling_params is None:
|
||||
|
|
@ -385,7 +386,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
|
|||
)
|
||||
return model
|
||||
|
||||
async def _get_params(self, request: Union[ChatCompletionRequest, CompletionRequest]) -> dict:
|
||||
async def _get_params(self, request: ChatCompletionRequest | CompletionRequest) -> dict:
|
||||
options = get_sampling_options(request.sampling_params)
|
||||
if "max_tokens" not in options:
|
||||
options["max_tokens"] = self.config.max_tokens
|
||||
|
|
@ -422,10 +423,10 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
|
|||
async def embeddings(
|
||||
self,
|
||||
model_id: str,
|
||||
contents: List[str] | List[InterleavedContentItem],
|
||||
text_truncation: Optional[TextTruncation] = TextTruncation.none,
|
||||
output_dimension: Optional[int] = None,
|
||||
task_type: Optional[EmbeddingTaskType] = None,
|
||||
contents: list[str] | list[InterleavedContentItem],
|
||||
text_truncation: TextTruncation | None = TextTruncation.none,
|
||||
output_dimension: int | None = None,
|
||||
task_type: EmbeddingTaskType | None = None,
|
||||
) -> EmbeddingsResponse:
|
||||
self._lazy_initialize_client()
|
||||
assert self.client is not None
|
||||
|
|
@ -448,29 +449,29 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
|
|||
async def openai_completion(
|
||||
self,
|
||||
model: str,
|
||||
prompt: Union[str, List[str], List[int], List[List[int]]],
|
||||
best_of: Optional[int] = None,
|
||||
echo: Optional[bool] = None,
|
||||
frequency_penalty: Optional[float] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
guided_choice: Optional[List[str]] = None,
|
||||
prompt_logprobs: Optional[int] = None,
|
||||
prompt: str | list[str] | list[int] | list[list[int]],
|
||||
best_of: int | None = None,
|
||||
echo: bool | None = None,
|
||||
frequency_penalty: float | None = None,
|
||||
logit_bias: dict[str, float] | None = None,
|
||||
logprobs: bool | None = None,
|
||||
max_tokens: int | None = None,
|
||||
n: int | None = None,
|
||||
presence_penalty: float | None = None,
|
||||
seed: int | None = None,
|
||||
stop: str | list[str] | None = None,
|
||||
stream: bool | None = None,
|
||||
stream_options: dict[str, Any] | None = None,
|
||||
temperature: float | None = None,
|
||||
top_p: float | None = None,
|
||||
user: str | None = None,
|
||||
guided_choice: list[str] | None = None,
|
||||
prompt_logprobs: int | None = None,
|
||||
) -> OpenAICompletion:
|
||||
self._lazy_initialize_client()
|
||||
model_obj = await self._get_model(model)
|
||||
|
||||
extra_body: Dict[str, Any] = {}
|
||||
extra_body: dict[str, Any] = {}
|
||||
if prompt_logprobs is not None and prompt_logprobs >= 0:
|
||||
extra_body["prompt_logprobs"] = prompt_logprobs
|
||||
if guided_choice:
|
||||
|
|
@ -501,29 +502,29 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
|
|||
async def openai_chat_completion(
|
||||
self,
|
||||
model: str,
|
||||
messages: List[OpenAIMessageParam],
|
||||
frequency_penalty: Optional[float] = None,
|
||||
function_call: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
functions: Optional[List[Dict[str, Any]]] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_completion_tokens: Optional[int] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
parallel_tool_calls: Optional[bool] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
response_format: Optional[OpenAIResponseFormatParam] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
tool_choice: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
tools: Optional[List[Dict[str, Any]]] = None,
|
||||
top_logprobs: Optional[int] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
) -> Union[OpenAIChatCompletion, AsyncIterator[OpenAIChatCompletionChunk]]:
|
||||
messages: list[OpenAIMessageParam],
|
||||
frequency_penalty: float | None = None,
|
||||
function_call: str | dict[str, Any] | None = None,
|
||||
functions: list[dict[str, Any]] | None = None,
|
||||
logit_bias: dict[str, float] | None = None,
|
||||
logprobs: bool | None = None,
|
||||
max_completion_tokens: int | None = None,
|
||||
max_tokens: int | None = None,
|
||||
n: int | None = None,
|
||||
parallel_tool_calls: bool | None = None,
|
||||
presence_penalty: float | None = None,
|
||||
response_format: OpenAIResponseFormatParam | None = None,
|
||||
seed: int | None = None,
|
||||
stop: str | list[str] | None = None,
|
||||
stream: bool | None = None,
|
||||
stream_options: dict[str, Any] | None = None,
|
||||
temperature: float | None = None,
|
||||
tool_choice: str | dict[str, Any] | None = None,
|
||||
tools: list[dict[str, Any]] | None = None,
|
||||
top_logprobs: int | None = None,
|
||||
top_p: float | None = None,
|
||||
user: str | None = None,
|
||||
) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
|
||||
self._lazy_initialize_client()
|
||||
model_obj = await self._get_model(model)
|
||||
params = await prepare_openai_completion_params(
|
||||
|
|
@ -556,21 +557,21 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
|
|||
async def batch_completion(
|
||||
self,
|
||||
model_id: str,
|
||||
content_batch: List[InterleavedContent],
|
||||
sampling_params: Optional[SamplingParams] = None,
|
||||
response_format: Optional[ResponseFormat] = None,
|
||||
logprobs: Optional[LogProbConfig] = None,
|
||||
content_batch: list[InterleavedContent],
|
||||
sampling_params: SamplingParams | None = None,
|
||||
response_format: ResponseFormat | None = None,
|
||||
logprobs: LogProbConfig | None = None,
|
||||
):
|
||||
raise NotImplementedError("Batch completion is not supported for Ollama")
|
||||
|
||||
async def batch_chat_completion(
|
||||
self,
|
||||
model_id: str,
|
||||
messages_batch: List[List[Message]],
|
||||
sampling_params: Optional[SamplingParams] = None,
|
||||
tools: Optional[List[ToolDefinition]] = None,
|
||||
tool_config: Optional[ToolConfig] = None,
|
||||
response_format: Optional[ResponseFormat] = None,
|
||||
logprobs: Optional[LogProbConfig] = None,
|
||||
messages_batch: list[list[Message]],
|
||||
sampling_params: SamplingParams | None = None,
|
||||
tools: list[ToolDefinition] | None = None,
|
||||
tool_config: ToolConfig | None = None,
|
||||
response_format: ResponseFormat | None = None,
|
||||
logprobs: LogProbConfig | None = None,
|
||||
):
|
||||
raise NotImplementedError("Batch chat completion is not supported for Ollama")
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue