phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

API Updates (#73)

Browse source 
* 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>
This commit is contained in:
Ashwin Bharambe 2024-09-17 19:51:35 -07:00 • committed by GitHub
parent f294eac5f5
commit 9487ad8294
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
213 changed files with 1725 additions and 1204 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/cli/model/__init__.py Normal file
View file

@ -0,0 +1,7 @@
# 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.
from .model import ModelParser # noqa

75
llama_stack/cli/model/describe.py Normal file
View file

@ -0,0 +1,75 @@
# 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 llama_models.sku_list import resolve_model
from termcolor import colored
from llama_stack.cli.subcommand import Subcommand
from llama_stack.cli.table import print_table
from llama_stack.distribution.utils.serialize import EnumEncoder
class ModelDescribe(Subcommand):
"""Show details about a model"""
def __init__(self, subparsers: argparse._SubParsersAction):
super().__init__()
self.parser = subparsers.add_parser(
"describe",
prog="llama model describe",
description="Show details about a llama model",
formatter_class=argparse.RawTextHelpFormatter,
)
self._add_arguments()
self.parser.set_defaults(func=self._run_model_describe_cmd)
def _add_arguments(self):
self.parser.add_argument(
"-m",
"--model-id",
type=str,
required=True,
)
def _run_model_describe_cmd(self, args: argparse.Namespace) -> None:
model = resolve_model(args.model_id)
if model is None:
self.parser.error(
f"Model {args.model_id} not found; try 'llama model list' for a list of available models."
)
return
rows = [
(
colored("Model", "white", attrs=["bold"]),
colored(model.descriptor(), "white", attrs=["bold"]),
),
("HuggingFace ID", model.huggingface_repo or "<Not Available>"),
("Description", model.description_markdown),
("Context Length", f"{model.max_seq_length // 1024}K tokens"),
("Weights format", model.quantization_format.value),
("Model params.json", json.dumps(model.model_args, indent=4)),
]
if model.recommended_sampling_params is not None:
sampling_params = model.recommended_sampling_params.dict()
for k in ("max_tokens", "repetition_penalty"):
del sampling_params[k]
rows.append(
(
"Recommended sampling params",
json.dumps(sampling_params, cls=EnumEncoder, indent=4),
)
)
print_table(
rows,
separate_rows=True,
)

24
llama_stack/cli/model/download.py Normal file
View file

@ -0,0 +1,24 @@
# 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
from llama_stack.cli.subcommand import Subcommand
class ModelDownload(Subcommand):
def __init__(self, subparsers: argparse._SubParsersAction):
super().__init__()
self.parser = subparsers.add_parser(
"download",
prog="llama model download",
description="Download a model from llama.meta.com or Hugging Face Hub",
formatter_class=argparse.RawTextHelpFormatter,
)
from llama_stack.cli.download import setup_download_parser
setup_download_parser(self.parser)

60
llama_stack/cli/model/list.py Normal file
View file

@ -0,0 +1,60 @@
# 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
from llama_models.sku_list import all_registered_models
from llama_stack.cli.subcommand import Subcommand
from llama_stack.cli.table import print_table
class ModelList(Subcommand):
"""List available llama models"""
def __init__(self, subparsers: argparse._SubParsersAction):
super().__init__()
self.parser = subparsers.add_parser(
"list",
prog="llama model list",
description="Show available llama models",
formatter_class=argparse.RawTextHelpFormatter,
)
self._add_arguments()
self.parser.set_defaults(func=self._run_model_list_cmd)
def _add_arguments(self):
self.parser.add_argument(
"--show-all",
action="store_true",
help="Show all models (not just defaults)",
)
def _run_model_list_cmd(self, args: argparse.Namespace) -> None:
headers = [
"Model Descriptor",
"HuggingFace Repo",
"Context Length",
]
rows = []
for model in all_registered_models():
if not args.show_all and not model.is_featured:
continue
descriptor = model.descriptor()
rows.append(
[
descriptor,
model.huggingface_repo,
f"{model.max_seq_length // 1024}K",
]
)
print_table(
rows,
headers,
separate_rows=True,
)

34
llama_stack/cli/model/model.py Normal file
View file

@ -0,0 +1,34 @@
# 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
from llama_stack.cli.model.describe import ModelDescribe
from llama_stack.cli.model.download import ModelDownload
from llama_stack.cli.model.list import ModelList
from llama_stack.cli.model.template import ModelTemplate
from llama_stack.cli.subcommand import Subcommand
class ModelParser(Subcommand):
"""Llama cli for model interface apis"""
def __init__(self, subparsers: argparse._SubParsersAction):
super().__init__()
self.parser = subparsers.add_parser(
"model",
prog="llama model",
description="Work with llama models",
)
subparsers = self.parser.add_subparsers(title="model_subcommands")
# Add sub-commands
ModelDownload.create(subparsers)
ModelList.create(subparsers)
ModelTemplate.create(subparsers)
ModelDescribe.create(subparsers)

113
llama_stack/cli/model/template.py Normal file
View file

@ -0,0 +1,113 @@
# 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,
)