mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-31 03:50:00 +00:00
90ed785fbd
TODO: - make sure docstrings are refreshed as needed. - make sure this passes tests. - address a TODO in code (obsolete comment?) - make sure client side still works. - analyze if any providers need adjustments. Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
48 lines
1.6 KiB
Python
48 lines
1.6 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 List, Optional, Protocol, runtime_checkable
|
|
|
|
from llama_stack.apis.inference import (
|
|
ChatCompletionResponse,
|
|
CompletionResponse,
|
|
InterleavedContent,
|
|
LogProbConfig,
|
|
Message,
|
|
ResponseFormat,
|
|
SamplingParams,
|
|
ToolChoice,
|
|
ToolDefinition,
|
|
ToolPromptFormat,
|
|
)
|
|
from llama_stack.schema_utils import webmethod
|
|
|
|
|
|
@runtime_checkable
|
|
class BatchInference(Protocol):
|
|
@webmethod(route="/batch-inference/completion", method="POST")
|
|
async def batch_completion(
|
|
self,
|
|
model: str,
|
|
content_batch: List[InterleavedContent],
|
|
sampling_params: Optional[SamplingParams] = None,
|
|
response_format: Optional[ResponseFormat] = None,
|
|
logprobs: Optional[LogProbConfig] = None,
|
|
) -> list[CompletionResponse]: ...
|
|
|
|
@webmethod(route="/batch-inference/chat-completion", method="POST")
|
|
async def batch_chat_completion(
|
|
self,
|
|
model: str,
|
|
messages_batch: List[List[Message]],
|
|
sampling_params: Optional[SamplingParams] = None,
|
|
# zero-shot tool definitions as input to the model
|
|
tools: Optional[List[ToolDefinition]] = list,
|
|
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
|
|
tool_prompt_format: Optional[ToolPromptFormat] = None,
|
|
response_format: Optional[ResponseFormat] = None,
|
|
logprobs: Optional[LogProbConfig] = None,
|
|
) -> list[ChatCompletionResponse]: ...
|