mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-11 05:38:38 +00:00
0066d986c5
# What does this PR do? use SecretStr for OpenAIMixin providers - RemoteInferenceProviderConfig now has auth_credential: SecretStr - the default alias is api_key (most common name) - some providers override to use api_token (RunPod, vLLM, Databricks) - some providers exclude it (Ollama, TGI, Vertex AI) addresses #3517 ## Test Plan ci w/ new tests
85 lines
2.9 KiB
Python
85 lines
2.9 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
from typing import Any
|
|
|
|
from llama_stack.apis.inference import (
|
|
OpenAIMessageParam,
|
|
OpenAIResponseFormatParam,
|
|
)
|
|
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
|
|
|
|
from .config import RunpodImplConfig
|
|
|
|
|
|
class RunpodInferenceAdapter(OpenAIMixin):
|
|
"""
|
|
Adapter for RunPod's OpenAI-compatible API endpoints.
|
|
Supports VLLM for serverless endpoint self-hosted or public endpoints.
|
|
Can work with any runpod endpoints that support OpenAI-compatible API
|
|
"""
|
|
|
|
config: RunpodImplConfig
|
|
|
|
def get_base_url(self) -> str:
|
|
"""Get base URL for OpenAI client."""
|
|
return self.config.url
|
|
|
|
async def openai_chat_completion(
|
|
self,
|
|
model: str,
|
|
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,
|
|
):
|
|
"""Override to add RunPod-specific stream_options requirement."""
|
|
if stream and not stream_options:
|
|
stream_options = {"include_usage": True}
|
|
|
|
return await super().openai_chat_completion(
|
|
model=model,
|
|
messages=messages,
|
|
frequency_penalty=frequency_penalty,
|
|
function_call=function_call,
|
|
functions=functions,
|
|
logit_bias=logit_bias,
|
|
logprobs=logprobs,
|
|
max_completion_tokens=max_completion_tokens,
|
|
max_tokens=max_tokens,
|
|
n=n,
|
|
parallel_tool_calls=parallel_tool_calls,
|
|
presence_penalty=presence_penalty,
|
|
response_format=response_format,
|
|
seed=seed,
|
|
stop=stop,
|
|
stream=stream,
|
|
stream_options=stream_options,
|
|
temperature=temperature,
|
|
tool_choice=tool_choice,
|
|
tools=tools,
|
|
top_logprobs=top_logprobs,
|
|
top_p=top_p,
|
|
user=user,
|
|
)
|