mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
* 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>
58 lines
1.5 KiB
Python
58 lines
1.5 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 argparse
|
|
|
|
from .download import Download
|
|
from .model import ModelParser
|
|
from .stack import StackParser
|
|
|
|
|
|
class LlamaCLIParser:
|
|
"""Defines CLI parser for Llama CLI"""
|
|
|
|
def __init__(self):
|
|
self.parser = argparse.ArgumentParser(
|
|
prog="llama",
|
|
description="Welcome to the Llama CLI",
|
|
add_help=True,
|
|
)
|
|
|
|
# Default command is to print help
|
|
self.parser.set_defaults(func=lambda args: self.parser.print_help())
|
|
|
|
subparsers = self.parser.add_subparsers(title="subcommands")
|
|
|
|
# Add sub-commands
|
|
Download.create(subparsers)
|
|
ModelParser.create(subparsers)
|
|
StackParser.create(subparsers)
|
|
|
|
# Import sub-commands from agentic_system if they exist
|
|
try:
|
|
from llama_agentic_system.cli.subcommand_modules import SUBCOMMAND_MODULES
|
|
|
|
for module in SUBCOMMAND_MODULES:
|
|
module.create(subparsers)
|
|
|
|
except ImportError:
|
|
pass
|
|
|
|
def parse_args(self) -> argparse.Namespace:
|
|
return self.parser.parse_args()
|
|
|
|
def run(self, args: argparse.Namespace) -> None:
|
|
args.func(args)
|
|
|
|
|
|
def main():
|
|
parser = LlamaCLIParser()
|
|
args = parser.parse_args()
|
|
parser.run(args)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|