mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
7bc7785b0d
* add tools to chat completion request
* use templates for generating system prompts
* Moved ToolPromptFormat and jinja templates to llama_models.llama3.api
* <WIP> memory changes
- inlined AgenticSystemInstanceConfig so API feels more ergonomic
- renamed it to AgentConfig, AgentInstance -> Agent
- added a MemoryConfig and `memory` parameter
- added `attachments` to input and `output_attachments` to the response
- some naming changes
* InterleavedTextAttachment -> InterleavedTextMedia, introduce memory tool
* flesh out memory banks API
* agentic loop has a RAG implementation
* faiss provider implementation
* memory client works
* re-work tool definitions, fix FastAPI issues, fix tool regressions
* fix agentic_system utils
* basic RAG seems to work
* small bug fixes for inline attachments
* Refactor custom tool execution utilities
* Bug fix, show memory retrieval steps in EventLogger
* No need for api_key for Remote providers
* add special unicode character ↵ to showcase newlines in model prompt templates
* remove api.endpoints imports
* combine datatypes.py and endpoints.py into api.py
* Attachment / add TTL api
* split batch_inference from inference
* minor import fixes
* use a single impl for ChatFormat.decode_assistant_mesage
* use interleaved_text_media_as_str() utilityt
* Fix api.datatypes imports
* Add blobfile for tiktoken
* Add ToolPromptFormat to ChatFormat.encode_message so that tools are encoded properly
* templates take optional --format={json,function_tag}
* Rag Updates
* Add `api build` subcommand -- WIP
* fix
* build + run image seems to work
* <WIP> adapters
* bunch more work to make adapters work
* api build works for conda now
* ollama remote adapter works
* Several smaller fixes to make adapters work
Also, reorganized the pattern of __init__ inside providers so
configuration can stay lightweight
* llama distribution -> llama stack + containers (WIP)
* All the new CLI for api + stack work
* Make Fireworks and Together into the Adapter format
* Some quick fixes to the CLI behavior to make it consistent
* Updated README phew
* Update cli_reference.md
* llama_toolchain/distribution -> llama_toolchain/core
* Add termcolor
* update paths
* Add a log just for consistency
* chmod +x scripts
* Fix api dependencies not getting added to configuration
* missing import lol
* Delete utils.py; move to agentic system
* Support downloading of URLs for attachments for code interpreter
* Simplify and generalize `llama api build` yay
* Update `llama stack configure` to be very simple also
* Fix stack start
* Allow building an "adhoc" distribution
* Remote `llama api []` subcommands
* Fixes to llama stack commands and update docs
* Update documentation again and add error messages to llama stack start
* llama stack start -> llama stack run
* Change name of build for less confusion
* Add pyopenapi fork to the repository, update RFC assets
* Remove conflicting annotation
* Added a "--raw" option for model template printing
---------
Co-authored-by: Hardik Shah <hjshah@fb.com>
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
Co-authored-by: Dalton Flanagan <6599399+dltn@users.noreply.github.com>
84 lines
2.7 KiB
Python
84 lines
2.7 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_toolchain.stack import LlamaStack
|
|
|
|
|
|
# TODO: this should be fixed in the generator itself so it reads appropriate annotations
|
|
STREAMING_ENDPOINTS = ["/agentic_system/turn/create"]
|
|
|
|
|
|
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)
|