forked from phoenix-oss/llama-stack-mirror
9487ad8294
* API Keys passed from Client instead of distro configuration * delete distribution registry * Rename the "package" word away * Introduce a "Router" layer for providers Some providers need to be factorized and considered as thin routing layers on top of other providers. Consider two examples: - The inference API should be a routing layer over inference providers, routed using the "model" key - The memory banks API is another instance where various memory bank types will be provided by independent providers (e.g., a vector store is served by Chroma while a keyvalue memory can be served by Redis or PGVector) This commit introduces a generalized routing layer for this purpose. * update `apis_to_serve` * llama_toolchain -> llama_stack * Codemod from llama_toolchain -> llama_stack - added providers/registry - cleaned up api/ subdirectories and moved impls away - restructured api/api.py - from llama_stack.apis.<api> import foo should work now - update imports to do llama_stack.apis.<api> - update many other imports - added __init__, fixed some registry imports - updated registry imports - create_agentic_system -> create_agent - AgenticSystem -> Agent * Moved some stuff out of common/; re-generated OpenAPI spec * llama-toolchain -> llama-stack (hyphens) * add control plane API * add redis adapter + sqlite provider * move core -> distribution * Some more toolchain -> stack changes * small naming shenanigans * Removing custom tool and agent utilities and moving them client side * Move control plane to distribution server for now * Remove control plane from API list * no codeshield dependency randomly plzzzzz * Add "fire" as a dependency * add back event loggers * stack configure fixes * use brave instead of bing in the example client * add init file so it gets packaged * add init files so it gets packaged * Update MANIFEST * bug fix --------- Co-authored-by: Hardik Shah <hjshah@fb.com> Co-authored-by: Xi Yan <xiyan@meta.com> Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
107 lines
3.3 KiB
Python
107 lines
3.3 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.
|
|
|
|
import asyncio
|
|
import json
|
|
from typing import Any, AsyncGenerator
|
|
|
|
import fire
|
|
import httpx
|
|
|
|
from llama_stack.distribution.datatypes import RemoteProviderConfig
|
|
from pydantic import BaseModel
|
|
from termcolor import cprint
|
|
|
|
from .event_logger import EventLogger
|
|
|
|
from .inference import (
|
|
ChatCompletionRequest,
|
|
ChatCompletionResponse,
|
|
ChatCompletionResponseStreamChunk,
|
|
CompletionRequest,
|
|
Inference,
|
|
UserMessage,
|
|
)
|
|
|
|
|
|
async def get_client_impl(config: RemoteProviderConfig, _deps: Any) -> Inference:
|
|
return InferenceClient(config.url)
|
|
|
|
|
|
def encodable_dict(d: BaseModel):
|
|
return json.loads(d.json())
|
|
|
|
|
|
class InferenceClient(Inference):
|
|
def __init__(self, base_url: str):
|
|
self.base_url = base_url
|
|
|
|
async def initialize(self) -> None:
|
|
pass
|
|
|
|
async def shutdown(self) -> None:
|
|
pass
|
|
|
|
async def completion(self, request: CompletionRequest) -> AsyncGenerator:
|
|
raise NotImplementedError()
|
|
|
|
async def chat_completion(self, request: ChatCompletionRequest) -> AsyncGenerator:
|
|
async with httpx.AsyncClient() as client:
|
|
async with client.stream(
|
|
"POST",
|
|
f"{self.base_url}/inference/chat_completion",
|
|
json=encodable_dict(request),
|
|
headers={"Content-Type": "application/json"},
|
|
timeout=20,
|
|
) as response:
|
|
if response.status_code != 200:
|
|
content = await response.aread()
|
|
cprint(
|
|
f"Error: HTTP {response.status_code} {content.decode()}", "red"
|
|
)
|
|
return
|
|
|
|
async for line in response.aiter_lines():
|
|
if line.startswith("data:"):
|
|
data = line[len("data: ") :]
|
|
try:
|
|
if request.stream:
|
|
if "error" in data:
|
|
cprint(data, "red")
|
|
continue
|
|
|
|
yield ChatCompletionResponseStreamChunk(
|
|
**json.loads(data)
|
|
)
|
|
else:
|
|
yield ChatCompletionResponse(**json.loads(data))
|
|
except Exception as e:
|
|
print(data)
|
|
print(f"Error with parsing or validation: {e}")
|
|
|
|
|
|
async def run_main(host: str, port: int, stream: bool):
|
|
client = InferenceClient(f"http://{host}:{port}")
|
|
|
|
message = UserMessage(content="hello world, troll me in two-paragraphs about 42")
|
|
cprint(f"User>{message.content}", "green")
|
|
iterator = client.chat_completion(
|
|
ChatCompletionRequest(
|
|
model="Meta-Llama3.1-8B-Instruct",
|
|
messages=[message],
|
|
stream=stream,
|
|
)
|
|
)
|
|
async for log in EventLogger().log(iterator):
|
|
log.print()
|
|
|
|
|
|
def main(host: str, port: int, stream: bool = True):
|
|
asyncio.run(run_main(host, port, stream))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
fire.Fire(main)
|