forked from phoenix-oss/llama-stack-mirror
8af6951106
# What does this PR do? We are setting a default value of json for tool prompt format, which conflicts with llama 3.2/3.3 models since they use python list. This PR changes the defaults to None and in the code, we infer default based on the model. Addresses: #695 Tests: ❯ LLAMA_STACK_BASE_URL=http://localhost:5000 pytest -v tests/client-sdk/inference/test_inference.py -k "test_text_chat_completion" pytest llama_stack/providers/tests/inference/test_prompt_adapter.py
77 lines
2.4 KiB
Python
77 lines
2.4 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_models.schema_utils import json_schema_type, webmethod
|
|
from pydantic import BaseModel, Field
|
|
|
|
from llama_stack.apis.inference import (
|
|
CompletionMessage,
|
|
InterleavedContent,
|
|
LogProbConfig,
|
|
Message,
|
|
SamplingParams,
|
|
ToolChoice,
|
|
ToolDefinition,
|
|
ToolPromptFormat,
|
|
)
|
|
|
|
|
|
@json_schema_type
|
|
class BatchCompletionRequest(BaseModel):
|
|
model: str
|
|
content_batch: List[InterleavedContent]
|
|
sampling_params: Optional[SamplingParams] = SamplingParams()
|
|
logprobs: Optional[LogProbConfig] = None
|
|
|
|
|
|
@json_schema_type
|
|
class BatchCompletionResponse(BaseModel):
|
|
completion_message_batch: List[CompletionMessage]
|
|
|
|
|
|
@json_schema_type
|
|
class BatchChatCompletionRequest(BaseModel):
|
|
model: str
|
|
messages_batch: List[List[Message]]
|
|
sampling_params: Optional[SamplingParams] = SamplingParams()
|
|
|
|
# zero-shot tool definitions as input to the model
|
|
tools: Optional[List[ToolDefinition]] = Field(default_factory=list)
|
|
tool_choice: Optional[ToolChoice] = Field(default=ToolChoice.auto)
|
|
tool_prompt_format: Optional[ToolPromptFormat] = Field(default=None)
|
|
logprobs: Optional[LogProbConfig] = None
|
|
|
|
|
|
@json_schema_type
|
|
class BatchChatCompletionResponse(BaseModel):
|
|
completion_message_batch: List[CompletionMessage]
|
|
|
|
|
|
@runtime_checkable
|
|
class BatchInference(Protocol):
|
|
@webmethod(route="/batch-inference/completion")
|
|
async def batch_completion(
|
|
self,
|
|
model: str,
|
|
content_batch: List[InterleavedContent],
|
|
sampling_params: Optional[SamplingParams] = SamplingParams(),
|
|
logprobs: Optional[LogProbConfig] = None,
|
|
) -> BatchCompletionResponse: ...
|
|
|
|
@webmethod(route="/batch-inference/chat-completion")
|
|
async def batch_chat_completion(
|
|
self,
|
|
model: str,
|
|
messages_batch: List[List[Message]],
|
|
sampling_params: Optional[SamplingParams] = SamplingParams(),
|
|
# 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,
|
|
logprobs: Optional[LogProbConfig] = None,
|
|
) -> BatchChatCompletionResponse: ...
|