mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
84 lines
2.4 KiB
Python
84 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 Any, Dict, List, Tuple
|
|
|
|
from llama_stack.distribution.datatypes import Api
|
|
|
|
from .routing_table import RoutingTable
|
|
from llama_stack.apis.memory import * # noqa: F403
|
|
from llama_stack.apis.inference import * # noqa: F403
|
|
|
|
|
|
class MemoryRouter(Memory):
|
|
"""Routes to an provider based on the memory bank type"""
|
|
|
|
def __init__(
|
|
self,
|
|
routing_table: RoutingTable,
|
|
) -> None:
|
|
self.routing_table = routing_table
|
|
|
|
async def initialize(self) -> None:
|
|
pass
|
|
|
|
async def shutdown(self) -> None:
|
|
pass
|
|
|
|
async def create_memory_bank(
|
|
self,
|
|
name: str,
|
|
config: MemoryBankConfig,
|
|
url: Optional[URL] = None,
|
|
) -> MemoryBank:
|
|
print("MemoryRouter: create_memory_bank")
|
|
|
|
async def get_memory_bank(self, bank_id: str) -> Optional[MemoryBank]:
|
|
print("MemoryRouter: get_memory_bank")
|
|
|
|
async def insert_documents(
|
|
self,
|
|
bank_id: str,
|
|
documents: List[MemoryBankDocument],
|
|
ttl_seconds: Optional[int] = None,
|
|
) -> None:
|
|
print("MemoryRouter: insert_documents")
|
|
|
|
async def query_documents(
|
|
self,
|
|
bank_id: str,
|
|
query: InterleavedTextMedia,
|
|
params: Optional[Dict[str, Any]] = None,
|
|
) -> QueryDocumentsResponse:
|
|
print("query_documents")
|
|
|
|
|
|
class InferenceRouter(Inference):
|
|
def __init__(
|
|
self,
|
|
routing_table: RoutingTable,
|
|
) -> None:
|
|
self.routing_table = routing_table
|
|
|
|
async def initialize(self) -> None:
|
|
pass
|
|
|
|
async def shutdown(self) -> None:
|
|
pass
|
|
|
|
async def chat_completion(
|
|
self,
|
|
model: str,
|
|
messages: 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] = ToolPromptFormat.json,
|
|
stream: Optional[bool] = False,
|
|
logprobs: Optional[LogProbConfig] = None,
|
|
) -> Union[ChatCompletionResponse, ChatCompletionResponseStreamChunk]:
|
|
print("Inference Router: chat_completion")
|