llama-stack-mirror/llama_toolchain/cli/stack/configure.py
Ashwin Bharambe 7bc7785b0d
API Updates: fleshing out RAG APIs, introduce "llama stack" CLI command (#51)
* 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>
2024-09-03 22:39:39 -07:00

106 lines
3.4 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.
import argparse
import json
from pathlib import Path
import yaml
from termcolor import cprint
from llama_toolchain.cli.subcommand import Subcommand
from llama_toolchain.common.config_dirs import BUILDS_BASE_DIR
from llama_toolchain.core.datatypes import * # noqa: F403
class StackConfigure(Subcommand):
"""Llama cli for configuring llama toolchain configs"""
def __init__(self, subparsers: argparse._SubParsersAction):
super().__init__()
self.parser = subparsers.add_parser(
"configure",
prog="llama stack configure",
description="configure a llama stack distribution",
formatter_class=argparse.RawTextHelpFormatter,
)
self._add_arguments()
self.parser.set_defaults(func=self._run_stack_configure_cmd)
def _add_arguments(self):
from llama_toolchain.core.distribution_registry import (
available_distribution_specs,
)
from llama_toolchain.core.package import BuildType
allowed_ids = [d.distribution_id for d in available_distribution_specs()]
self.parser.add_argument(
"distribution",
type=str,
choices=allowed_ids,
help="Distribution (one of: {})".format(allowed_ids),
)
self.parser.add_argument(
"--name",
type=str,
help="Name of the build",
required=True,
)
self.parser.add_argument(
"--type",
type=str,
default="conda_env",
choices=[v.value for v in BuildType],
)
def _run_stack_configure_cmd(self, args: argparse.Namespace) -> None:
from llama_toolchain.core.package import BuildType
build_type = BuildType(args.type)
name = args.name
config_file = (
BUILDS_BASE_DIR
/ args.distribution
/ build_type.descriptor()
/ f"{name}.yaml"
)
if not config_file.exists():
self.parser.error(
f"Could not find {config_file}. Please run `llama stack build` first"
)
return
configure_llama_distribution(config_file)
def configure_llama_distribution(config_file: Path) -> None:
from llama_toolchain.common.serialize import EnumEncoder
from llama_toolchain.core.configure import configure_api_providers
from llama_toolchain.core.distribution_registry import resolve_distribution_spec
with open(config_file, "r") as f:
config = PackageConfig(**yaml.safe_load(f))
dist = resolve_distribution_spec(config.distribution_id)
if dist is None:
raise ValueError(
f"Could not find any registered distribution `{config.distribution_id}`"
)
if config.providers:
cprint(
f"Configuration already exists for {config.distribution_id}. Will overwrite...",
"yellow",
attrs=["bold"],
)
config.providers = configure_api_providers(config.providers)
with open(config_file, "w") as fp:
to_write = json.loads(json.dumps(config.dict(), cls=EnumEncoder))
fp.write(yaml.dump(to_write, sort_keys=False))
print(f"YAML configuration has been written to {config_file}")