forked from phoenix-oss/llama-stack-mirror
ec4fc800cc
This is yet another of those large PRs (hopefully we will have less and less of them as things mature fast). This one introduces substantial improvements and some simplifications to the stack. Most important bits: * Agents reference implementation now has support for session / turn persistence. The default implementation uses sqlite but there's also support for using Redis. * We have re-architected the structure of the Stack APIs to allow for more flexible routing. The motivating use cases are: - routing model A to ollama and model B to a remote provider like Together - routing shield A to local impl while shield B to a remote provider like Bedrock - routing a vector memory bank to Weaviate while routing a keyvalue memory bank to Redis * Support for provider specific parameters to be passed from the clients. A client can pass data using `x_llamastack_provider_data` parameter which can be type-checked and provided to the Adapter implementations.
120 lines
3.8 KiB
Python
120 lines
3.8 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
|
|
|
|
from .pyopenapi.options import Options
|
|
from .pyopenapi.specification import Info, Server
|
|
from .pyopenapi.utility import Specification
|
|
|
|
# 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
|
|
|
|
schema_utils.json_schema_type = json_schema_type
|
|
|
|
from llama_models.llama3.api.datatypes import * # noqa: F403
|
|
from llama_stack.apis.agents import * # noqa: F403
|
|
from llama_stack.apis.dataset import * # noqa: F403
|
|
from llama_stack.apis.evals import * # noqa: F403
|
|
from llama_stack.apis.inference import * # noqa: F403
|
|
from llama_stack.apis.batch_inference import * # noqa: F403
|
|
from llama_stack.apis.memory import * # noqa: F403
|
|
from llama_stack.apis.telemetry import * # noqa: F403
|
|
from llama_stack.apis.post_training import * # noqa: F403
|
|
from llama_stack.apis.reward_scoring import * # noqa: F403
|
|
from llama_stack.apis.synthetic_data_generation import * # noqa: F403
|
|
from llama_stack.apis.safety import * # noqa: F403
|
|
from llama_stack.apis.models import * # noqa: F403
|
|
from llama_stack.apis.memory_banks import * # noqa: F403
|
|
from llama_stack.apis.shields import * # noqa: F403
|
|
|
|
|
|
class LlamaStack(
|
|
MemoryBanks,
|
|
Inference,
|
|
BatchInference,
|
|
Agents,
|
|
RewardScoring,
|
|
Safety,
|
|
SyntheticDataGeneration,
|
|
Datasets,
|
|
Telemetry,
|
|
PostTraining,
|
|
Memory,
|
|
Evaluations,
|
|
Models,
|
|
Shields,
|
|
):
|
|
pass
|
|
|
|
|
|
# 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)
|