mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
abdf7cddf3
* wip * dataset validation * test_scoring * cleanup * clean up test * comments * error checking * dataset client * test client: * datasetio client * clean up * basic scoring function works * scorer wip * equality scorer * score batch impl * score batch * update scoring test * refactor * validate scorer input * address comments * evals with generation * add all rows scores to ScoringResult * minor typing * bugfix * scoring function def rename * rebase name * refactor * address comments * Update iOS inference instructions for new quantization * Small updates to quantization config * Fix score threshold in faiss * Bump version to 0.0.45 * Handle both ipv6 and ipv4 interfaces together * update manifest for build templates * Update getting_started.md * chatcompletion & completion input type validation * inclusion->subsetof * error checking * scoring_function -> scoring_fn rename, scorer -> scoring_fn rename * address comments * [Evals API][5/n] fixes to generate openapi spec (#323) * generate openapi * typing comment, dataset -> dataset_id * remove custom type * sample eval run.yaml --------- Co-authored-by: Dalton Flanagan <6599399+dltn@users.noreply.github.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
126 lines
4 KiB
Python
126 lines
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.
|
|
|
|
# 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.datasets import * # noqa: F403
|
|
from llama_stack.apis.datasetio import * # noqa: F403
|
|
from llama_stack.apis.scoring import * # noqa: F403
|
|
from llama_stack.apis.scoring_functions import * # noqa: F403
|
|
from llama_stack.apis.eval 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.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
|
|
from llama_stack.apis.inspect import * # noqa: F403
|
|
|
|
|
|
class LlamaStack(
|
|
MemoryBanks,
|
|
Inference,
|
|
BatchInference,
|
|
Agents,
|
|
Safety,
|
|
SyntheticDataGeneration,
|
|
Datasets,
|
|
Telemetry,
|
|
PostTraining,
|
|
Memory,
|
|
Eval,
|
|
Scoring,
|
|
ScoringFunctions,
|
|
DatasetIO,
|
|
Models,
|
|
Shields,
|
|
Inspect,
|
|
):
|
|
pass
|
|
|
|
|
|
# TODO: this should be fixed in the generator itself so it reads appropriate annotations
|
|
STREAMING_ENDPOINTS = [
|
|
"/agents/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)
|