mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 10:54:19 +00:00
e830814399
* Add distribution CLI scaffolding * More progress towards `llama distribution install` * getting closer to a distro definition, distro install + configure works * Distribution server now functioning * read existing configuration, save enums properly * Remove inference uvicorn server entrypoint and llama inference CLI command * updated dependency and client model name * Improved exception handling * local imports for faster cli * undo a typo, add a passthrough distribution * implement full-passthrough in the server * add safety adapters, configuration handling, server + clients * cleanup, moving stuff to common, nuke utils * Add a Path() wrapper at the earliest place * fixes * Bring agentic system api to toolchain Add adapter dependencies and resolve adapters using a topological sort * refactor to reduce size of `agentic_system` * move straggler files and fix some important existing bugs * ApiSurface -> Api * refactor a method out * Adapter -> Provider * Make each inference provider into its own subdirectory * installation fixes * Rename Distribution -> DistributionSpec, simplify RemoteProviders * dict key instead of attr * update inference config to take model and not model_dir * Fix passthrough streaming, send headers properly not part of body :facepalm * update safety to use model sku ids and not model dirs * Update cli_reference.md * minor fixes * add DistributionConfig, fix a bug in model download * Make install + start scripts do proper configuration automatically * Update CLI_reference * Nuke fp8_requirements, fold fbgemm into common requirements * Update README, add newline between API surface configurations * Refactor download functionality out of the Command so can be reused * Add `llama model download` alias for `llama download` * Show message about checksum file so users can check themselves * Simpler intro statements * get ollama working * Reduce a bunch of dependencies from toolchain Some improvements to the distribution install script * Avoid using `conda run` since it buffers everything * update dependencies and rely on LLAMA_TOOLCHAIN_DIR for dev purposes * add validation for configuration input * resort imports * make optional subclasses default to yes for configuration * Remove additional_pip_packages; move deps to providers * for inline make 8b model the default * Add scripts to MANIFEST * allow installing from test.pypi.org * Fix #2 to help with testing packages * Must install llama-models at that same version first * fix PIP_ARGS --------- Co-authored-by: Hardik Shah <hjshah@fb.com> Co-authored-by: Hardik Shah <hjshah@meta.com>
100 lines
3.1 KiB
Python
100 lines
3.1 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 AsyncGenerator
|
|
|
|
import fire
|
|
import httpx
|
|
from termcolor import cprint
|
|
|
|
from .api import (
|
|
ChatCompletionRequest,
|
|
ChatCompletionResponse,
|
|
ChatCompletionResponseStreamChunk,
|
|
CompletionRequest,
|
|
Inference,
|
|
UserMessage,
|
|
)
|
|
from .event_logger import EventLogger
|
|
|
|
|
|
async def get_client_impl(base_url: str):
|
|
return InferenceClient(base_url)
|
|
|
|
|
|
class InferenceClient(Inference):
|
|
def __init__(self, base_url: str):
|
|
print(f"Initializing client for {base_url}")
|
|
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",
|
|
data=request.json(),
|
|
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)
|