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>
106 lines
3.4 KiB
Python
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}")
|