mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
* 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>
113 lines
3.8 KiB
Python
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,
|
|
)
|