llama-stack/llama_stack/cli/model/template.py
Ashwin Bharambe 9487ad8294
API Updates (#73)
* API Keys passed from Client instead of distro configuration

* delete distribution registry

* Rename the "package" word away

* Introduce a "Router" layer for providers

Some providers need to be factorized and considered as thin routing
layers on top of other providers. Consider two examples:

- The inference API should be a routing layer over inference providers,
  routed using the "model" key
- The memory banks API is another instance where various memory bank
  types will be provided by independent providers (e.g., a vector store
  is served by Chroma while a keyvalue memory can be served by Redis or
  PGVector)

This commit introduces a generalized routing layer for this purpose.

* update `apis_to_serve`

* llama_toolchain -> llama_stack

* Codemod from llama_toolchain -> llama_stack

- added providers/registry
- cleaned up api/ subdirectories and moved impls away
- restructured api/api.py
- from llama_stack.apis.<api> import foo should work now
- update imports to do llama_stack.apis.<api>
- update many other imports
- added __init__, fixed some registry imports
- updated registry imports
- create_agentic_system -> create_agent
- AgenticSystem -> Agent

* Moved some stuff out of common/; re-generated OpenAPI spec

* llama-toolchain -> llama-stack (hyphens)

* add control plane API

* add redis adapter + sqlite provider

* move core -> distribution

* Some more toolchain -> stack changes

* small naming shenanigans

* Removing custom tool and agent utilities and moving them client side

* Move control plane to distribution server for now

* Remove control plane from API list

* no codeshield dependency randomly plzzzzz

* Add "fire" as a dependency

* add back event loggers

* stack configure fixes

* use brave instead of bing in the example client

* add init file so it gets packaged

* add init files so it gets packaged

* Update MANIFEST

* bug fix

---------

Co-authored-by: Hardik Shah <hjshah@fb.com>
Co-authored-by: Xi Yan <xiyan@meta.com>
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
2024-09-17 19:51:35 -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_stack.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_stack.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,
)