llama-stack/llama_toolchain/cli/model/template.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

113 lines
3.8 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 textwrap
from termcolor import colored
from llama_toolchain.cli.subcommand import Subcommand
class ModelTemplate(Subcommand):
"""Llama model cli for describe a model template (message formats)"""
def __init__(self, subparsers: argparse._SubParsersAction):
super().__init__()
self.parser = subparsers.add_parser(
"template",
prog="llama model template",
description="Show llama model message formats",
epilog=textwrap.dedent(
"""
Example:
llama model template <options>
"""
),
formatter_class=argparse.RawTextHelpFormatter,
)
self._add_arguments()
self.parser.set_defaults(func=self._run_model_template_cmd)
def _prompt_type(self, value):
from llama_models.llama3.api.datatypes import ToolPromptFormat
try:
return ToolPromptFormat(value.lower())
except ValueError:
raise argparse.ArgumentTypeError(
f"{value} is not a valid ToolPromptFormat. Choose from {', '.join(t.value for t in ToolPromptFormat)}"
) from None
def _add_arguments(self):
self.parser.add_argument(
"-m",
"--model-family",
type=str,
default="llama3_1",
help="Model Family (llama3_1, llama3_X, etc.)",
)
self.parser.add_argument(
"--name",
type=str,
help="Usecase template name (system_message, user_message, assistant_message, tool_message)...",
required=False,
)
self.parser.add_argument(
"--format",
type=str,
help="ToolPromptFormat (json or function_tag). This flag is used to print the template in a specific formats.",
required=False,
default="json",
)
self.parser.add_argument(
"--raw",
action="store_true",
help="If set to true, don't pretty-print into a table. Useful to copy-paste.",
)
def _run_model_template_cmd(self, args: argparse.Namespace) -> None:
from llama_models.llama3.api.interface import (
list_jinja_templates,
render_jinja_template,
)
from llama_toolchain.cli.table import print_table
if args.name:
tool_prompt_format = self._prompt_type(args.format)
template, tokens_info = render_jinja_template(args.name, tool_prompt_format)
rendered = ""
for tok, is_special in tokens_info:
if is_special:
rendered += colored(tok, "yellow", attrs=["bold"])
else:
rendered += tok
if not args.raw:
rendered = rendered.replace("\n", "\n")
print_table(
[
(
"Name",
colored(template.template_name, "white", attrs=["bold"]),
),
("Template", rendered),
("Notes", template.notes),
],
separate_rows=True,
)
else:
print("Template: ", template.template_name)
print("=" * 40)
print(rendered)
else:
templates = list_jinja_templates()
headers = ["Role", "Template Name"]
print_table(
[(t.role, t.template_name) for t in templates],
headers,
)