Kye
10 months ago
parent
8fe317b909
commit
5a60eb4f2d
@ -0,0 +1,70 @@
|
||||
|
||||
# Swarm Ecosystem
|
||||
|
||||
Welcome to the Swarm Ecosystem, a comprehensive suite of tools and frameworks designed to empower developers to orhestrate swarms of autonomous agents for a variety of applications. Dive into our ecosystem below:
|
||||
|
||||
| Project | Description | Link |
|
||||
| ------- | ----------- | ---- |
|
||||
| **Swarms Framework** | A Python-based framework that enables the creation, deployment, and scaling of reliable swarms of autonomous agents aimed at automating complex workflows. | [Swarms Framework](https://github.com/kyegomez/swarms) |
|
||||
| **Swarms Cloud** | A cloud-based service offering Swarms-as-a-Service with guaranteed 100% uptime, cutting-edge performance, and enterprise-grade reliability for seamless scaling and management of swarms. | [Swarms Cloud](https://github.com/kyegomez/swarms-core) |
|
||||
| **Swarms Core** | Provides backend utilities focusing on concurrency, multi-threading, and advanced execution strategies, developed in Rust for maximum efficiency and performance. | [Swarms Core](https://github.com/kyegomez/swarms-core) |
|
||||
| **Swarm Foundation Models** | A dedicated repository for the creation, optimization, and training of groundbreaking swarming models. Features innovative models like PSO with transformers, ant colony optimizations, and more, aiming to surpass traditional architectures like Transformers and SSMs. Open for community contributions and ideas. | [Swarm Foundation Models](https://github.com/kyegomez/swarms-pytorch) |
|
||||
| **Swarm Platform** | The Swarms dashboard Platform | [Swarm Platform](https://swarms.world/) |
|
||||
| **Swarms JS** | Swarms Framework in JS. Orchestrate any agents and enable multi-agent collaboration between various agents! | [Swarm JS](https://github.com/kyegomez/swarms-js) |
|
||||
|
||||
|
||||
|
||||
----
|
||||
|
||||
## 🫶 Contributions:
|
||||
|
||||
The easiest way to contribute is to pick any issue with the `good first issue` tag 💪. Read the Contributing guidelines [here](/CONTRIBUTING.md). Bug Report? [File here](https://github.com/swarms/gateway/issues) | Feature Request? [File here](https://github.com/swarms/gateway/issues)
|
||||
|
||||
Swarms is an open-source project, and contributions are VERY welcome. If you want to contribute, you can create new features, fix bugs, or improve the infrastructure. Please refer to the [CONTRIBUTING.md](https://github.com/kyegomez/swarms/blob/master/CONTRIBUTING.md) and our [contributing board](https://github.com/users/kyegomez/projects/1) to participate in Roadmap discussions!
|
||||
|
||||
<a href="https://github.com/kyegomez/swarms/graphs/contributors">
|
||||
<img src="https://contrib.rocks/image?repo=kyegomez/swarms" />
|
||||
</a>
|
||||
|
||||
<a href="https://github.com/kyegomez/swarms/graphs/contributors">
|
||||
<img src="https://contrib.rocks/image?repo=kyegomez/swarms-cloud" />
|
||||
</a>
|
||||
|
||||
<a href="https://github.com/kyegomez/swarms/graphs/contributors">
|
||||
<img src="https://contrib.rocks/image?repo=kyegomez/swarms-platform" />
|
||||
</a>
|
||||
|
||||
<a href="https://github.com/kyegomez/swarms/graphs/contributors">
|
||||
<img src="https://contrib.rocks/image?repo=kyegomez/swarms-js" />
|
||||
</a>
|
||||
|
||||
|
||||
|
||||
|
||||
----
|
||||
|
||||
## Community
|
||||
|
||||
Join our growing community around the world, for real-time support, ideas, and discussions on Swarms 😊
|
||||
|
||||
- View our official [Blog](https://swarms.apac.ai)
|
||||
- Chat live with us on [Discord](https://discord.gg/kS3rwKs3ZC)
|
||||
- Follow us on [Twitter](https://twitter.com/kyegomez)
|
||||
- Connect with us on [LinkedIn](https://www.linkedin.com/company/the-swarm-corporation)
|
||||
- Visit us on [YouTube](https://www.youtube.com/channel/UC9yXyitkbU_WSy7bd_41SqQ)
|
||||
- [Join the Swarms community on Discord!](https://discord.gg/AJazBmhKnr)
|
||||
- Join our Swarms Community Gathering every Thursday at 1pm NYC Time to unlock the potential of autonomous agents in automating your daily tasks [Sign up here](https://lu.ma/5p2jnc2v)
|
||||
|
||||
---
|
||||
|
||||
## Discovery Call
|
||||
Book a discovery call to learn how Swarms can lower your operating costs by 40% with swarms of autonomous agents in lightspeed. [Click here to book a time that works for you!](https://calendly.com/swarm-corp/30min?month=2023-11)
|
||||
|
||||
|
||||
|
||||
## Accelerate Backlog
|
||||
Help us accelerate our backlog by supporting us financially! Note, we're an open source corporation and so all the revenue we generate is through donations at the moment ;)
|
||||
|
||||
<a href="https://polar.sh/kyegomez"><img src="https://polar.sh/embed/fund-our-backlog.svg?org=kyegomez" /></a>
|
||||
|
||||
---
|
||||
@ -0,0 +1,34 @@
|
||||
from swarms import Agent, AnthropicChat, tool
|
||||
|
||||
|
||||
# Tool
|
||||
@tool # Wrap the function with the tool decorator
|
||||
def search_api(query: str, max_results: int = 10):
|
||||
"""
|
||||
Search the web for the query and return the top `max_results` results.
|
||||
"""
|
||||
return f"Search API: {query} -> {max_results} results"
|
||||
|
||||
|
||||
## Initialize the workflow
|
||||
agent = Agent(
|
||||
agent_name="Youtube Transcript Generator",
|
||||
agent_description=(
|
||||
"Generate a transcript for a youtube video on what swarms"
|
||||
" are!"
|
||||
),
|
||||
llm=AnthropicChat(),
|
||||
max_loops="auto",
|
||||
autosave=True,
|
||||
dashboard=False,
|
||||
streaming_on=True,
|
||||
verbose=True,
|
||||
stopping_token="<DONE>",
|
||||
tools=[search_api],
|
||||
)
|
||||
|
||||
# Run the workflow on a task
|
||||
agent(
|
||||
"Generate a transcript for a youtube video on what swarms are!"
|
||||
" Output a <DONE> token when done."
|
||||
)
|
||||
@ -0,0 +1,48 @@
|
||||
from langchain_community.chat_models.azure_openai import (
|
||||
AzureChatOpenAI,
|
||||
)
|
||||
from langchain_community.chat_models.openai import (
|
||||
ChatOpenAI as OpenAIChat,
|
||||
)
|
||||
from langchain_community.llms import (
|
||||
Anthropic,
|
||||
Cohere,
|
||||
MosaicML,
|
||||
OpenAI,
|
||||
Replicate,
|
||||
)
|
||||
|
||||
|
||||
class AnthropicChat(Anthropic):
|
||||
def __call__(self, *args, **kwargs):
|
||||
return self.invoke(*args, **kwargs)
|
||||
|
||||
|
||||
class CohereChat(Cohere):
|
||||
def __call__(self, *args, **kwargs):
|
||||
return self.invoke(*args, **kwargs)
|
||||
|
||||
|
||||
class MosaicMLChat(MosaicML):
|
||||
def __call__(self, *args, **kwargs):
|
||||
return self.invoke(*args, **kwargs)
|
||||
|
||||
|
||||
class OpenAILLM(OpenAI):
|
||||
def __call__(self, *args, **kwargs):
|
||||
return self.invoke(*args, **kwargs)
|
||||
|
||||
|
||||
class ReplicateLLM(Replicate):
|
||||
def __call__(self, *args, **kwargs):
|
||||
return self.invoke(*args, **kwargs)
|
||||
|
||||
|
||||
class AzureOpenAILLM(AzureChatOpenAI):
|
||||
def __call__(self, *args, **kwargs):
|
||||
return self.invoke(*args, **kwargs)
|
||||
|
||||
|
||||
class OpenAIChatLLM(OpenAIChat):
|
||||
def __call__(self, *args, **kwargs):
|
||||
return self.invoke(*args, **kwargs)
|
||||
@ -1,953 +0,0 @@
|
||||
"""Base implementation for tools or skills."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import inspect
|
||||
import warnings
|
||||
from abc import abstractmethod
|
||||
from functools import partial
|
||||
from inspect import signature
|
||||
from typing import Any, Awaitable, Callable, Dict, Union
|
||||
|
||||
from langchain.callbacks.base import BaseCallbackManager
|
||||
from langchain.callbacks.manager import (
|
||||
AsyncCallbackManager,
|
||||
AsyncCallbackManagerForToolRun,
|
||||
CallbackManager,
|
||||
CallbackManagerForToolRun,
|
||||
Callbacks,
|
||||
)
|
||||
from langchain.load.serializable import Serializable
|
||||
from langchain.schema.runnable import (
|
||||
Runnable,
|
||||
RunnableConfig,
|
||||
RunnableSerializable,
|
||||
)
|
||||
from pydantic import (
|
||||
BaseModel,
|
||||
Extra,
|
||||
Field,
|
||||
create_model,
|
||||
root_validator,
|
||||
validate_arguments,
|
||||
)
|
||||
|
||||
|
||||
class SchemaAnnotationError(TypeError):
|
||||
"""Raised when 'args_schema' is missing or has an incorrect type annotation."""
|
||||
|
||||
|
||||
def _create_subset_model(
|
||||
name: str, model: BaseModel, field_names: list
|
||||
) -> type[BaseModel]:
|
||||
"""Create a pydantic model with only a subset of model's fields."""
|
||||
fields = {}
|
||||
for field_name in field_names:
|
||||
field = model.__fields__[field_name]
|
||||
fields[field_name] = (field.outer_type_, field.field_info)
|
||||
return create_model(name, **fields) # type: ignore
|
||||
|
||||
|
||||
def _get_filtered_args(
|
||||
inferred_model: type[BaseModel],
|
||||
func: Callable,
|
||||
) -> dict:
|
||||
"""Get the arguments from a function's signature."""
|
||||
schema = inferred_model.schema()["properties"]
|
||||
valid_keys = signature(func).parameters
|
||||
return {
|
||||
k: schema[k]
|
||||
for k in valid_keys
|
||||
if k not in ("run_manager", "callbacks")
|
||||
}
|
||||
|
||||
|
||||
class _SchemaConfig:
|
||||
"""Configuration for the pydantic model."""
|
||||
|
||||
extra: Any = Extra.forbid
|
||||
arbitrary_types_allowed: bool = True
|
||||
|
||||
|
||||
def create_schema_from_function(
|
||||
model_name: str,
|
||||
func: Callable,
|
||||
) -> type[BaseModel]:
|
||||
"""Create a pydantic schema from a function's signature.
|
||||
Args:
|
||||
model_name: Name to assign to the generated pydandic schema
|
||||
func: Function to generate the schema from
|
||||
Returns:
|
||||
A pydantic model with the same arguments as the function
|
||||
"""
|
||||
# https://docs.pydantic.dev/latest/usage/validation_decorator/
|
||||
validated = validate_arguments(func, config=_SchemaConfig) # type: ignore
|
||||
inferred_model = validated.model # type: ignore
|
||||
if "run_manager" in inferred_model.__fields__:
|
||||
del inferred_model.__fields__["run_manager"]
|
||||
if "callbacks" in inferred_model.__fields__:
|
||||
del inferred_model.__fields__["callbacks"]
|
||||
# Pydantic adds placeholder virtual fields we need to strip
|
||||
valid_properties = _get_filtered_args(inferred_model, func)
|
||||
return _create_subset_model(
|
||||
f"{model_name}Schema", inferred_model, list(valid_properties)
|
||||
)
|
||||
|
||||
|
||||
class ToolException(Exception):
|
||||
"""An optional exception that tool throws when execution error occurs.
|
||||
|
||||
When this exception is thrown, the agent will not stop working,
|
||||
but will handle the exception according to the handle_tool_error
|
||||
variable of the tool, and the processing result will be returned
|
||||
to the agent as observation, and printed in red on the console.
|
||||
"""
|
||||
|
||||
|
||||
class BaseTool(RunnableSerializable[Union[str, Dict], Any]):
|
||||
"""Interface swarms tools must implement."""
|
||||
|
||||
def __init_subclass__(cls, **kwargs: Any) -> None:
|
||||
"""Create the definition of the new tool class."""
|
||||
super().__init_subclass__(**kwargs)
|
||||
|
||||
args_schema_type = cls.__annotations__.get(
|
||||
"args_schema", None
|
||||
)
|
||||
|
||||
if args_schema_type is not None:
|
||||
if (
|
||||
args_schema_type is None
|
||||
or args_schema_type == BaseModel
|
||||
):
|
||||
# Throw errors for common mis-annotations.
|
||||
# TODO: Use get_args / get_origin and fully
|
||||
# specify valid annotations.
|
||||
typehint_mandate = """
|
||||
class ChildTool(BaseTool):
|
||||
...
|
||||
args_schema: Type[BaseModel] = SchemaClass
|
||||
..."""
|
||||
name = cls.__name__
|
||||
raise SchemaAnnotationError(
|
||||
f"Tool definition for {name} must include valid"
|
||||
" type annotations for argument 'args_schema' to"
|
||||
" behave as expected.\nExpected annotation of"
|
||||
" 'Type[BaseModel]' but got"
|
||||
f" '{args_schema_type}'.\nExpected class looks"
|
||||
f" like:\n{typehint_mandate}"
|
||||
)
|
||||
|
||||
name: str
|
||||
"""The unique name of the tool that clearly communicates its purpose."""
|
||||
description: str
|
||||
"""Used to tell the model how/when/why to use the tool.
|
||||
|
||||
You can provide few-shot examples as a part of the description.
|
||||
"""
|
||||
args_schema: type[BaseModel] | None = None
|
||||
"""Pydantic model class to validate and parse the tool's input arguments."""
|
||||
return_direct: bool = False
|
||||
"""Whether to return the tool's output directly. Setting this to True means
|
||||
|
||||
that after the tool is called, the AgentExecutor will stop looping.
|
||||
"""
|
||||
verbose: bool = False
|
||||
"""Whether to log the tool's progress."""
|
||||
|
||||
callbacks: Callbacks = Field(default=None, exclude=True)
|
||||
"""Callbacks to be called during tool execution."""
|
||||
callback_manager: BaseCallbackManager | None = Field(
|
||||
default=None, exclude=True
|
||||
)
|
||||
"""Deprecated. Please use callbacks instead."""
|
||||
tags: list[str] | None = None
|
||||
"""Optional list of tags associated with the tool. Defaults to None
|
||||
These tags will be associated with each call to this tool,
|
||||
and passed as arguments to the handlers defined in `callbacks`.
|
||||
You can use these to eg identify a specific instance of a tool with its use case.
|
||||
"""
|
||||
metadata: dict[str, Any] | None = None
|
||||
"""Optional metadata associated with the tool. Defaults to None
|
||||
This metadata will be associated with each call to this tool,
|
||||
and passed as arguments to the handlers defined in `callbacks`.
|
||||
You can use these to eg identify a specific instance of a tool with its use case.
|
||||
"""
|
||||
|
||||
handle_tool_error: (
|
||||
bool | str | Callable[[ToolException], str] | None
|
||||
) = False
|
||||
"""Handle the content of the ToolException thrown."""
|
||||
|
||||
class Config(Serializable.Config):
|
||||
"""Configuration for this pydantic object."""
|
||||
|
||||
arbitrary_types_allowed = True
|
||||
|
||||
@property
|
||||
def is_single_input(self) -> bool:
|
||||
"""Whether the tool only accepts a single input."""
|
||||
keys = {k for k in self.args if k != "kwargs"}
|
||||
return len(keys) == 1
|
||||
|
||||
@property
|
||||
def args(self) -> dict:
|
||||
if self.args_schema is not None:
|
||||
return self.args_schema.schema()["properties"]
|
||||
else:
|
||||
schema = create_schema_from_function(self.name, self._run)
|
||||
return schema.schema()["properties"]
|
||||
|
||||
# --- Runnable ---
|
||||
|
||||
@property
|
||||
def input_schema(self) -> type[BaseModel]:
|
||||
"""The tool's input schema."""
|
||||
if self.args_schema is not None:
|
||||
return self.args_schema
|
||||
else:
|
||||
return create_schema_from_function(self.name, self._run)
|
||||
|
||||
def invoke(
|
||||
self,
|
||||
input: str | dict,
|
||||
config: RunnableConfig | None = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
config = config or {}
|
||||
return self.run(
|
||||
input,
|
||||
callbacks=config.get("callbacks"),
|
||||
tags=config.get("tags"),
|
||||
metadata=config.get("metadata"),
|
||||
run_name=config.get("run_name"),
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
async def ainvoke(
|
||||
self,
|
||||
input: str | dict,
|
||||
config: RunnableConfig | None = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
config = config or {}
|
||||
return await self.arun(
|
||||
input,
|
||||
callbacks=config.get("callbacks"),
|
||||
tags=config.get("tags"),
|
||||
metadata=config.get("metadata"),
|
||||
run_name=config.get("run_name"),
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
# --- Tool ---
|
||||
|
||||
def _parse_input(
|
||||
self,
|
||||
tool_input: str | dict,
|
||||
) -> str | dict[str, Any]:
|
||||
"""Convert tool input to pydantic model."""
|
||||
input_args = self.args_schema
|
||||
if isinstance(tool_input, str):
|
||||
if input_args is not None:
|
||||
key_ = next(iter(input_args.__fields__.keys()))
|
||||
input_args.validate({key_: tool_input})
|
||||
return tool_input
|
||||
else:
|
||||
if input_args is not None:
|
||||
result = input_args.parse_obj(tool_input)
|
||||
return {
|
||||
k: v
|
||||
for k, v in result.dict().items()
|
||||
if k in tool_input
|
||||
}
|
||||
return tool_input
|
||||
|
||||
@root_validator(skip_on_failure=True)
|
||||
def raise_deprecation(cls, values: dict) -> dict:
|
||||
"""Raise deprecation warning if callback_manager is used."""
|
||||
if values.get("callback_manager") is not None:
|
||||
warnings.warn(
|
||||
(
|
||||
"callback_manager is deprecated. Please use"
|
||||
" callbacks instead."
|
||||
),
|
||||
DeprecationWarning,
|
||||
)
|
||||
values["callbacks"] = values.pop("callback_manager", None)
|
||||
return values
|
||||
|
||||
@abstractmethod
|
||||
def _run(
|
||||
self,
|
||||
*args: Any,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
"""Use the tool.
|
||||
|
||||
Add run_manager: Optional[CallbackManagerForToolRun] = None
|
||||
to child implementations to enable tracing,
|
||||
"""
|
||||
|
||||
async def _arun(
|
||||
self,
|
||||
*args: Any,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
"""Use the tool asynchronously.
|
||||
|
||||
Add run_manager: Optional[AsyncCallbackManagerForToolRun] = None
|
||||
to child implementations to enable tracing,
|
||||
"""
|
||||
return await asyncio.get_running_loop().run_in_executor(
|
||||
None,
|
||||
partial(self._run, **kwargs),
|
||||
*args,
|
||||
)
|
||||
|
||||
def _to_args_and_kwargs(
|
||||
self, tool_input: str | dict
|
||||
) -> tuple[tuple, dict]:
|
||||
# For backwards compatibility, if run_input is a string,
|
||||
# pass as a positional argument.
|
||||
if isinstance(tool_input, str):
|
||||
return (tool_input,), {}
|
||||
else:
|
||||
return (), tool_input
|
||||
|
||||
def run(
|
||||
self,
|
||||
tool_input: str | dict,
|
||||
verbose: bool | None = None,
|
||||
start_color: str | None = "green",
|
||||
color: str | None = "green",
|
||||
callbacks: Callbacks = None,
|
||||
*,
|
||||
tags: list[str] | None = None,
|
||||
metadata: dict[str, Any] | None = None,
|
||||
run_name: str | None = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
"""Run the tool."""
|
||||
parsed_input = self._parse_input(tool_input)
|
||||
if not self.verbose and verbose is not None:
|
||||
verbose_ = verbose
|
||||
else:
|
||||
verbose_ = self.verbose
|
||||
callback_manager = CallbackManager.configure(
|
||||
callbacks,
|
||||
self.callbacks,
|
||||
verbose_,
|
||||
tags,
|
||||
self.tags,
|
||||
metadata,
|
||||
self.metadata,
|
||||
)
|
||||
# TODO: maybe also pass through run_manager is _run supports kwargs
|
||||
new_arg_supported = signature(self._run).parameters.get(
|
||||
"run_manager"
|
||||
)
|
||||
run_manager = callback_manager.on_tool_start(
|
||||
{"name": self.name, "description": self.description},
|
||||
(
|
||||
tool_input
|
||||
if isinstance(tool_input, str)
|
||||
else str(tool_input)
|
||||
),
|
||||
color=start_color,
|
||||
name=run_name,
|
||||
**kwargs,
|
||||
)
|
||||
try:
|
||||
tool_args, tool_kwargs = self._to_args_and_kwargs(
|
||||
parsed_input
|
||||
)
|
||||
observation = (
|
||||
self._run(
|
||||
*tool_args, run_manager=run_manager, **tool_kwargs
|
||||
)
|
||||
if new_arg_supported
|
||||
else self._run(*tool_args, **tool_kwargs)
|
||||
)
|
||||
except ToolException as e:
|
||||
if not self.handle_tool_error:
|
||||
run_manager.on_tool_error(e)
|
||||
raise e
|
||||
elif isinstance(self.handle_tool_error, bool):
|
||||
if e.args:
|
||||
observation = e.args[0]
|
||||
else:
|
||||
observation = "Tool execution error"
|
||||
elif isinstance(self.handle_tool_error, str):
|
||||
observation = self.handle_tool_error
|
||||
elif callable(self.handle_tool_error):
|
||||
observation = self.handle_tool_error(e)
|
||||
else:
|
||||
raise ValueError(
|
||||
"Got unexpected type of `handle_tool_error`."
|
||||
" Expected bool, str or callable. Received:"
|
||||
f" {self.handle_tool_error}"
|
||||
)
|
||||
run_manager.on_tool_end(
|
||||
str(observation),
|
||||
color="red",
|
||||
name=self.name,
|
||||
**kwargs,
|
||||
)
|
||||
return observation
|
||||
except (Exception, KeyboardInterrupt) as e:
|
||||
run_manager.on_tool_error(e)
|
||||
raise e
|
||||
else:
|
||||
run_manager.on_tool_end(
|
||||
str(observation),
|
||||
color=color,
|
||||
name=self.name,
|
||||
**kwargs,
|
||||
)
|
||||
return observation
|
||||
|
||||
async def arun(
|
||||
self,
|
||||
tool_input: str | dict,
|
||||
verbose: bool | None = None,
|
||||
start_color: str | None = "green",
|
||||
color: str | None = "green",
|
||||
callbacks: Callbacks = None,
|
||||
*,
|
||||
tags: list[str] | None = None,
|
||||
metadata: dict[str, Any] | None = None,
|
||||
run_name: str | None = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
"""Run the tool asynchronously."""
|
||||
parsed_input = self._parse_input(tool_input)
|
||||
if not self.verbose and verbose is not None:
|
||||
verbose_ = verbose
|
||||
else:
|
||||
verbose_ = self.verbose
|
||||
callback_manager = AsyncCallbackManager.configure(
|
||||
callbacks,
|
||||
self.callbacks,
|
||||
verbose_,
|
||||
tags,
|
||||
self.tags,
|
||||
metadata,
|
||||
self.metadata,
|
||||
)
|
||||
new_arg_supported = signature(self._arun).parameters.get(
|
||||
"run_manager"
|
||||
)
|
||||
run_manager = await callback_manager.on_tool_start(
|
||||
{"name": self.name, "description": self.description},
|
||||
(
|
||||
tool_input
|
||||
if isinstance(tool_input, str)
|
||||
else str(tool_input)
|
||||
),
|
||||
color=start_color,
|
||||
name=run_name,
|
||||
**kwargs,
|
||||
)
|
||||
try:
|
||||
# We then call the tool on the tool input to get an observation
|
||||
tool_args, tool_kwargs = self._to_args_and_kwargs(
|
||||
parsed_input
|
||||
)
|
||||
observation = (
|
||||
await self._arun(
|
||||
*tool_args, run_manager=run_manager, **tool_kwargs
|
||||
)
|
||||
if new_arg_supported
|
||||
else await self._arun(*tool_args, **tool_kwargs)
|
||||
)
|
||||
except ToolException as e:
|
||||
if not self.handle_tool_error:
|
||||
await run_manager.on_tool_error(e)
|
||||
raise e
|
||||
elif isinstance(self.handle_tool_error, bool):
|
||||
if e.args:
|
||||
observation = e.args[0]
|
||||
else:
|
||||
observation = "Tool execution error"
|
||||
elif isinstance(self.handle_tool_error, str):
|
||||
observation = self.handle_tool_error
|
||||
elif callable(self.handle_tool_error):
|
||||
observation = self.handle_tool_error(e)
|
||||
else:
|
||||
raise ValueError(
|
||||
"Got unexpected type of `handle_tool_error`."
|
||||
" Expected bool, str or callable. Received:"
|
||||
f" {self.handle_tool_error}"
|
||||
)
|
||||
await run_manager.on_tool_end(
|
||||
str(observation),
|
||||
color="red",
|
||||
name=self.name,
|
||||
**kwargs,
|
||||
)
|
||||
return observation
|
||||
except (Exception, KeyboardInterrupt) as e:
|
||||
await run_manager.on_tool_error(e)
|
||||
raise e
|
||||
else:
|
||||
await run_manager.on_tool_end(
|
||||
str(observation),
|
||||
color=color,
|
||||
name=self.name,
|
||||
**kwargs,
|
||||
)
|
||||
return observation
|
||||
|
||||
def __call__(
|
||||
self, tool_input: str, callbacks: Callbacks = None
|
||||
) -> str:
|
||||
"""Make tool callable."""
|
||||
return self.run(tool_input, callbacks=callbacks)
|
||||
|
||||
|
||||
class Tool(BaseTool):
|
||||
"""Tool that takes in function or coroutine directly."""
|
||||
|
||||
description: str = ""
|
||||
func: Callable[..., str] | None
|
||||
"""The function to run when the tool is called."""
|
||||
coroutine: Callable[..., Awaitable[str]] | None = None
|
||||
"""The asynchronous version of the function."""
|
||||
|
||||
# --- Runnable ---
|
||||
async def ainvoke(
|
||||
self,
|
||||
input: str | dict,
|
||||
config: RunnableConfig | None = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
if not self.coroutine:
|
||||
# If the tool does not implement async, fall back to default implementation
|
||||
return await asyncio.get_running_loop().run_in_executor(
|
||||
None, partial(self.invoke, input, config, **kwargs)
|
||||
)
|
||||
|
||||
return await super().ainvoke(input, config, **kwargs)
|
||||
|
||||
# --- Tool ---
|
||||
|
||||
@property
|
||||
def args(self) -> dict:
|
||||
"""The tool's input arguments."""
|
||||
if self.args_schema is not None:
|
||||
return self.args_schema.schema()["properties"]
|
||||
# For backwards compatibility, if the function signature is ambiguous,
|
||||
# assume it takes a single string input.
|
||||
return {"tool_input": {"type": "string"}}
|
||||
|
||||
def _to_args_and_kwargs(
|
||||
self, tool_input: str | dict
|
||||
) -> tuple[tuple, dict]:
|
||||
"""Convert tool input to pydantic model."""
|
||||
args, kwargs = super()._to_args_and_kwargs(tool_input)
|
||||
# For backwards compatibility. The tool must be run with a single input
|
||||
all_args = list(args) + list(kwargs.values())
|
||||
if len(all_args) != 1:
|
||||
raise ToolException(
|
||||
"Too many arguments to single-input tool"
|
||||
f" {self.name}. Args: {all_args}"
|
||||
)
|
||||
return tuple(all_args), {}
|
||||
|
||||
def _run(
|
||||
self,
|
||||
*args: Any,
|
||||
run_manager: CallbackManagerForToolRun | None = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
"""Use the tool."""
|
||||
if self.func:
|
||||
new_argument_supported = signature(
|
||||
self.func
|
||||
).parameters.get("callbacks")
|
||||
return (
|
||||
self.func(
|
||||
*args,
|
||||
callbacks=(
|
||||
run_manager.get_child()
|
||||
if run_manager
|
||||
else None
|
||||
),
|
||||
**kwargs,
|
||||
)
|
||||
if new_argument_supported
|
||||
else self.func(*args, **kwargs)
|
||||
)
|
||||
raise NotImplementedError("Tool does not support sync")
|
||||
|
||||
async def _arun(
|
||||
self,
|
||||
*args: Any,
|
||||
run_manager: AsyncCallbackManagerForToolRun | None = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
"""Use the tool asynchronously."""
|
||||
if self.coroutine:
|
||||
new_argument_supported = signature(
|
||||
self.coroutine
|
||||
).parameters.get("callbacks")
|
||||
return (
|
||||
await self.coroutine(
|
||||
*args,
|
||||
callbacks=(
|
||||
run_manager.get_child()
|
||||
if run_manager
|
||||
else None
|
||||
),
|
||||
**kwargs,
|
||||
)
|
||||
if new_argument_supported
|
||||
else await self.coroutine(*args, **kwargs)
|
||||
)
|
||||
else:
|
||||
return await asyncio.get_running_loop().run_in_executor(
|
||||
None,
|
||||
partial(self._run, run_manager=run_manager, **kwargs),
|
||||
*args,
|
||||
)
|
||||
|
||||
# TODO: this is for backwards compatibility, remove in future
|
||||
def __init__(
|
||||
self,
|
||||
name: str,
|
||||
func: Callable | None,
|
||||
description: str,
|
||||
**kwargs: Any,
|
||||
) -> None:
|
||||
"""Initialize tool."""
|
||||
super().__init__(
|
||||
name=name, func=func, description=description, **kwargs
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def from_function(
|
||||
cls,
|
||||
func: Callable | None,
|
||||
name: str, # We keep these required to support backwards compatibility
|
||||
description: str,
|
||||
return_direct: bool = False,
|
||||
args_schema: type[BaseModel] | None = None,
|
||||
coroutine: (Callable[..., Awaitable[Any]])
|
||||
| None = None, # This is last for compatibility, but should be after func
|
||||
**kwargs: Any,
|
||||
) -> Tool:
|
||||
"""Initialize tool from a function."""
|
||||
if func is None and coroutine is None:
|
||||
raise ValueError(
|
||||
"Function and/or coroutine must be provided"
|
||||
)
|
||||
return cls(
|
||||
name=name,
|
||||
func=func,
|
||||
coroutine=coroutine,
|
||||
description=description,
|
||||
return_direct=return_direct,
|
||||
args_schema=args_schema,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
|
||||
class StructuredTool(BaseTool):
|
||||
"""Tool that can operate on any number of inputs."""
|
||||
|
||||
description: str = ""
|
||||
args_schema: type[BaseModel] = Field(
|
||||
..., description="The tool schema."
|
||||
)
|
||||
"""The input arguments' schema."""
|
||||
func: Callable[..., Any] | None
|
||||
"""The function to run when the tool is called."""
|
||||
coroutine: Callable[..., Awaitable[Any]] | None = None
|
||||
"""The asynchronous version of the function."""
|
||||
|
||||
# --- Runnable ---
|
||||
async def ainvoke(
|
||||
self,
|
||||
input: str | dict,
|
||||
config: RunnableConfig | None = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
if not self.coroutine:
|
||||
# If the tool does not implement async, fall back to default implementation
|
||||
return await asyncio.get_running_loop().run_in_executor(
|
||||
None, partial(self.invoke, input, config, **kwargs)
|
||||
)
|
||||
|
||||
return await super().ainvoke(input, config, **kwargs)
|
||||
|
||||
# --- Tool ---
|
||||
|
||||
@property
|
||||
def args(self) -> dict:
|
||||
"""The tool's input arguments."""
|
||||
return self.args_schema.schema()["properties"]
|
||||
|
||||
def _run(
|
||||
self,
|
||||
*args: Any,
|
||||
run_manager: CallbackManagerForToolRun | None = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
"""Use the tool."""
|
||||
if self.func:
|
||||
new_argument_supported = signature(
|
||||
self.func
|
||||
).parameters.get("callbacks")
|
||||
return (
|
||||
self.func(
|
||||
*args,
|
||||
callbacks=(
|
||||
run_manager.get_child()
|
||||
if run_manager
|
||||
else None
|
||||
),
|
||||
**kwargs,
|
||||
)
|
||||
if new_argument_supported
|
||||
else self.func(*args, **kwargs)
|
||||
)
|
||||
raise NotImplementedError("Tool does not support sync")
|
||||
|
||||
async def _arun(
|
||||
self,
|
||||
*args: Any,
|
||||
run_manager: AsyncCallbackManagerForToolRun | None = None,
|
||||
**kwargs: Any,
|
||||
) -> str:
|
||||
"""Use the tool asynchronously."""
|
||||
if self.coroutine:
|
||||
new_argument_supported = signature(
|
||||
self.coroutine
|
||||
).parameters.get("callbacks")
|
||||
return (
|
||||
await self.coroutine(
|
||||
*args,
|
||||
callbacks=(
|
||||
run_manager.get_child()
|
||||
if run_manager
|
||||
else None
|
||||
),
|
||||
**kwargs,
|
||||
)
|
||||
if new_argument_supported
|
||||
else await self.coroutine(*args, **kwargs)
|
||||
)
|
||||
return await asyncio.get_running_loop().run_in_executor(
|
||||
None,
|
||||
partial(self._run, run_manager=run_manager, **kwargs),
|
||||
*args,
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def from_function(
|
||||
cls,
|
||||
func: Callable | None = None,
|
||||
coroutine: Callable[..., Awaitable[Any]] | None = None,
|
||||
name: str | None = None,
|
||||
description: str | None = None,
|
||||
return_direct: bool = False,
|
||||
args_schema: type[BaseModel] | None = None,
|
||||
infer_schema: bool = True,
|
||||
**kwargs: Any,
|
||||
) -> StructuredTool:
|
||||
"""Create tool from a given function.
|
||||
|
||||
A classmethod that helps to create a tool from a function.
|
||||
|
||||
Args:
|
||||
func: The function from which to create a tool
|
||||
coroutine: The async function from which to create a tool
|
||||
name: The name of the tool. Defaults to the function name
|
||||
description: The description of the tool. Defaults to the function docstring
|
||||
return_direct: Whether to return the result directly or as a callback
|
||||
args_schema: The schema of the tool's input arguments
|
||||
infer_schema: Whether to infer the schema from the function's signature
|
||||
**kwargs: Additional arguments to pass to the tool
|
||||
|
||||
Returns:
|
||||
The tool
|
||||
|
||||
Examples:
|
||||
|
||||
.. code-block:: python
|
||||
|
||||
def add(a: int, b: int) -> int:
|
||||
\"\"\"Add two numbers\"\"\"
|
||||
return a + b
|
||||
tool = StructuredTool.from_function(add)
|
||||
tool.run(1, 2) # 3
|
||||
"""
|
||||
|
||||
if func is not None:
|
||||
source_function = func
|
||||
elif coroutine is not None:
|
||||
source_function = coroutine
|
||||
else:
|
||||
raise ValueError(
|
||||
"Function and/or coroutine must be provided"
|
||||
)
|
||||
name = name or source_function.__name__
|
||||
description = description or source_function.__doc__
|
||||
if description is None:
|
||||
raise ValueError(
|
||||
"Function must have a docstring if description not"
|
||||
" provided."
|
||||
)
|
||||
|
||||
# Description example:
|
||||
# search_api(query: str) - Searches the API for the query.
|
||||
sig = signature(source_function)
|
||||
description = f"{name}{sig} - {description.strip()}"
|
||||
_args_schema = args_schema
|
||||
if _args_schema is None and infer_schema:
|
||||
_args_schema = create_schema_from_function(
|
||||
f"{name}Schema", source_function
|
||||
)
|
||||
return cls(
|
||||
name=name,
|
||||
func=func,
|
||||
coroutine=coroutine,
|
||||
args_schema=_args_schema,
|
||||
description=description,
|
||||
return_direct=return_direct,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
|
||||
def tool(
|
||||
*args: str | Callable | Runnable,
|
||||
return_direct: bool = False,
|
||||
args_schema: type[BaseModel] | None = None,
|
||||
infer_schema: bool = True,
|
||||
) -> Callable:
|
||||
"""Make tools out of functions, can be used with or without arguments.
|
||||
|
||||
Args:
|
||||
*args: The arguments to the tool.
|
||||
return_direct: Whether to return directly from the tool rather
|
||||
than continuing the agent loop.
|
||||
args_schema: optional argument schema for user to specify
|
||||
infer_schema: Whether to infer the schema of the arguments from
|
||||
the function's signature. This also makes the resultant tool
|
||||
accept a dictionary input to its `run()` function.
|
||||
|
||||
Requires:
|
||||
- Function must be of type (str) -> str
|
||||
- Function must have a docstring
|
||||
|
||||
Examples:
|
||||
.. code-block:: python
|
||||
|
||||
@tool
|
||||
def search_api(query: str) -> str:
|
||||
# Searches the API for the query.
|
||||
return
|
||||
|
||||
|
||||
@tool("search", return_direct=True)
|
||||
def search_api(query: str) -> str:
|
||||
# Searches the API for the query.
|
||||
return
|
||||
"""
|
||||
|
||||
def _make_with_name(tool_name: str) -> Callable:
|
||||
def _make_tool(dec_func: Callable | Runnable) -> BaseTool:
|
||||
if isinstance(dec_func, Runnable):
|
||||
runnable = dec_func
|
||||
|
||||
if (
|
||||
runnable.input_schema.schema().get("type")
|
||||
!= "object"
|
||||
):
|
||||
raise ValueError(
|
||||
"Runnable must have an object schema."
|
||||
)
|
||||
|
||||
async def ainvoke_wrapper(
|
||||
callbacks: Callbacks | None = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
return await runnable.ainvoke(
|
||||
kwargs, {"callbacks": callbacks}
|
||||
)
|
||||
|
||||
def invoke_wrapper(
|
||||
callbacks: Callbacks | None = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
return runnable.invoke(
|
||||
kwargs, {"callbacks": callbacks}
|
||||
)
|
||||
|
||||
coroutine = ainvoke_wrapper
|
||||
func = invoke_wrapper
|
||||
schema: type[BaseModel] | None = runnable.input_schema
|
||||
description = repr(runnable)
|
||||
elif inspect.iscoroutinefunction(dec_func):
|
||||
coroutine = dec_func
|
||||
func = None
|
||||
schema = args_schema
|
||||
description = None
|
||||
else:
|
||||
coroutine = None
|
||||
func = dec_func
|
||||
schema = args_schema
|
||||
description = None
|
||||
|
||||
if infer_schema or args_schema is not None:
|
||||
return StructuredTool.from_function(
|
||||
func,
|
||||
coroutine,
|
||||
name=tool_name,
|
||||
description=description,
|
||||
return_direct=return_direct,
|
||||
args_schema=schema,
|
||||
infer_schema=infer_schema,
|
||||
)
|
||||
# If someone doesn't want a schema applied, we must treat it as
|
||||
# a simple string->string function
|
||||
if func.__doc__ is None:
|
||||
raise ValueError(
|
||||
"Function must have a docstring if description"
|
||||
" not provided and infer_schema is False."
|
||||
)
|
||||
return Tool(
|
||||
name=tool_name,
|
||||
func=func,
|
||||
description=f"{tool_name} tool",
|
||||
return_direct=return_direct,
|
||||
coroutine=coroutine,
|
||||
)
|
||||
|
||||
return _make_tool
|
||||
|
||||
if (
|
||||
len(args) == 2
|
||||
and isinstance(args[0], str)
|
||||
and isinstance(args[1], Runnable)
|
||||
):
|
||||
return _make_with_name(args[0])(args[1])
|
||||
elif len(args) == 1 and isinstance(args[0], str):
|
||||
# if the argument is a string, then we use the string as the tool name
|
||||
# Example usage: @tool("search", return_direct=True)
|
||||
return _make_with_name(args[0])
|
||||
elif len(args) == 1 and callable(args[0]):
|
||||
# if the argument is a function, then we use the function name as the tool name
|
||||
# Example usage: @tool
|
||||
return _make_with_name(args[0].__name__)(args[0])
|
||||
elif len(args) == 0:
|
||||
# if there are no arguments, then we use the function name as the tool name
|
||||
# Example usage: @tool(return_direct=True)
|
||||
def _partial(func: Callable[[str], str]) -> BaseTool:
|
||||
return _make_with_name(func.__name__)(func)
|
||||
|
||||
return _partial
|
||||
else:
|
||||
raise ValueError("Too many arguments for tool decorator")
|
||||
@ -0,0 +1,61 @@
|
||||
from typing import Any, List, Union
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from swarms.tools.tool import BaseTool
|
||||
from swarms.utils.loguru_logger import logger
|
||||
|
||||
|
||||
class OmniTool(BaseModel):
|
||||
"""
|
||||
A class representing an OmniTool.
|
||||
|
||||
Attributes:
|
||||
tools (Union[List[BaseTool], List[BaseModel], List[Any]]): A list of tools.
|
||||
verbose (bool): A flag indicating whether to enable verbose mode.
|
||||
|
||||
Methods:
|
||||
transform_models_to_tools(): Transforms models to tools.
|
||||
__call__(*args, **kwargs): Calls the tools.
|
||||
|
||||
"""
|
||||
|
||||
tools: Union[List[BaseTool], List[BaseModel], List[Any]]
|
||||
verbose: bool = False
|
||||
|
||||
def transform_models_to_tools(self):
|
||||
"""
|
||||
Transforms models to tools.
|
||||
"""
|
||||
for i, tool in enumerate(self.tools):
|
||||
if isinstance(tool, BaseModel):
|
||||
tool_json = tool.model_dump_json()
|
||||
# Assuming BaseTool has a method to load from json
|
||||
self.tools[i] = BaseTool.load_from_json(tool_json)
|
||||
|
||||
def __call__(self, *args, **kwargs):
|
||||
"""
|
||||
Calls the tools.
|
||||
|
||||
Args:
|
||||
*args: Variable length argument list.
|
||||
**kwargs: Arbitrary keyword arguments.
|
||||
|
||||
Returns:
|
||||
Tuple: A tuple containing the arguments and keyword arguments.
|
||||
|
||||
"""
|
||||
try:
|
||||
self.transform_models_to_tools()
|
||||
logger.info(f"Number of tools: {len(self.tools)}")
|
||||
try:
|
||||
for tool in self.tools:
|
||||
logger.info(f"Running tool: {tool}")
|
||||
tool(*args, **kwargs)
|
||||
except Exception as e:
|
||||
logger.error(f"Error occurred while running tools: {e}")
|
||||
return args, kwargs
|
||||
|
||||
except Exception as error:
|
||||
logger.error(f"Error occurred while running tools: {error}")
|
||||
return args, kwargs
|
||||
Loading…
Reference in new issue