mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
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>
87 lines
2.8 KiB
Python
87 lines
2.8 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.
|
|
|
|
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described found in the
|
|
# LICENSE file in the root directory of this source tree.
|
|
|
|
from datetime import datetime
|
|
from pathlib import Path
|
|
|
|
import fire
|
|
import yaml
|
|
|
|
from llama_models import schema_utils
|
|
|
|
# We do some monkey-patching to ensure our definitions only use the minimal
|
|
# (json_schema_type, webmethod) definitions from the llama_models package. For
|
|
# generation though, we need the full definitions and implementations from the
|
|
# (json-strong-typing) package.
|
|
|
|
from strong_typing.schema import json_schema_type
|
|
|
|
from .pyopenapi.options import Options
|
|
from .pyopenapi.specification import Info, Server
|
|
from .pyopenapi.utility import Specification
|
|
|
|
schema_utils.json_schema_type = json_schema_type
|
|
|
|
from llama_stack.apis.stack import LlamaStack
|
|
|
|
|
|
# TODO: this should be fixed in the generator itself so it reads appropriate annotations
|
|
STREAMING_ENDPOINTS = [
|
|
"/agentic_system/turn/create",
|
|
"/inference/chat_completion",
|
|
]
|
|
|
|
|
|
def patch_sse_stream_responses(spec: Specification):
|
|
for path, path_item in spec.document.paths.items():
|
|
if path in STREAMING_ENDPOINTS:
|
|
content = path_item.post.responses["200"].content.pop("application/json")
|
|
path_item.post.responses["200"].content["text/event-stream"] = content
|
|
|
|
|
|
def main(output_dir: str):
|
|
output_dir = Path(output_dir)
|
|
if not output_dir.exists():
|
|
raise ValueError(f"Directory {output_dir} does not exist")
|
|
|
|
now = str(datetime.now())
|
|
print(
|
|
"Converting the spec to YAML (openapi.yaml) and HTML (openapi.html) at " + now
|
|
)
|
|
print("")
|
|
spec = Specification(
|
|
LlamaStack,
|
|
Options(
|
|
server=Server(url="http://any-hosted-llama-stack.com"),
|
|
info=Info(
|
|
title="[DRAFT] Llama Stack Specification",
|
|
version="0.0.1",
|
|
description="""This is the specification of the llama stack that provides
|
|
a set of endpoints and their corresponding interfaces that are tailored to
|
|
best leverage Llama Models. The specification is still in draft and subject to change.
|
|
Generated at """
|
|
+ now,
|
|
),
|
|
),
|
|
)
|
|
|
|
patch_sse_stream_responses(spec)
|
|
|
|
with open(output_dir / "llama-stack-spec.yaml", "w", encoding="utf-8") as fp:
|
|
yaml.dump(spec.get_json(), fp, allow_unicode=True)
|
|
|
|
with open(output_dir / "llama-stack-spec.html", "w") as fp:
|
|
spec.write_html(fp, pretty_print=True)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
fire.Fire(main)
|