9.3 KiB

Raw Blame History

Tools

Here, we're going to see advanced tool usage.

[!TIP] If you're new to agents, make sure to first read the main agents documentation.

Let's take again the tool example from main documentation, for which we had implemented a tool decorator.

If you need to add variation, like custom attributes for your tool, you can build your tool following the fine-grained method: building a class that inherits from the [Tool] superclass.

The custom tool needs:

An attribute name, which corresponds to the name of the tool itself. The name usually describes what the tool does. Since the code returns the model with the most downloads for a task, let's name it model_download_counter.
An attribute description is used to populate the agent's system prompt.
An inputs attribute, which is a dictionary with keys "type" and "description". It contains information that helps the Python interpreter make educated choices about the input.
An output_type attribute, which specifies the output type.
A forward method which contains the inference code to be executed.

The types for both inputs and output_type should be amongst Pydantic formats, they can be either of these: [~AUTHORIZED_TYPES].

Also, all imports should be put within the tool's forward function, else you will get an error.

from agents import Tool

class HFModelDownloadsTool(Tool):
    name = "model_download_counter"
    description = """
    This is a tool that returns the most downloaded model of a given task on the Hugging Face Hub.
    It returns the name of the checkpoint."""

    inputs = {
        "task": {
            "type": "string",
            "description": "the task category (such as text-classification, depth-estimation, etc)",
        }
    }
    output_type = "string"

    def forward(self, task: str):
        from huggingface_hub import list_models

        model = next(iter(list_models(filter=task, sort="downloads", direction=-1)))
        return model.id
tool = HFModelDownloadsTool()

Now the custom HfModelDownloadsTool class is ready.

You can also share your custom tool to the Hub by calling [~Tool.push_to_hub] on the tool. Make sure you've created a repository for it on the Hub and are using a token with read access.

tool.push_to_hub("m-ric/hf-model-downloads", token="<YOUR_HUGGINGFACEHUB_API_TOKEN>")

Load the tool with the [~Tool.load_tool] function and pass it to the tools parameter in your agent. Since running tools means running custom code, you need to make sure you trust the repository, and pass trust_remote_code=True.

from agents import load_tool, CodeAgent

model_download_tool = load_tool("m-ric/hf-model-downloads", trust_remote_code=True)

Import a Space as a tool 🚀

You can directly import a Space from the Hub as a tool using the [Tool.from_space] method!

You only need to provide the id of the Space on the Hub, its name, and a description that will help you agent understand what the tool does. Under the hood, this will use gradio-client library to call the Space.

For instance, let's import the FLUX.1-dev Space from the Hub and use it to generate an image.

image_generation_tool = Tool.from_space(
    "black-forest-labs/FLUX.1-schnell",
    name="image_generator",
    description="Generate an image from a prompt")

image_generation_tool("A sunny beach")

And voilà, here's your image! 🏖️

Then you can use this tool just like any other tool. For example, let's improve the prompt a rabbit wearing a space suit and generate an image of it.

from agents import CodeAgent, HfApiEngine

llm_engine = HfApiEngine("Qwen/Qwen2.5-Coder-32B-Instruct")
agent = CodeAgent(tools=[image_generation_tool], llm_engine=llm_engine)

agent.run(
    "Improve this prompt, then generate an image of it.", prompt='A rabbit wearing a space suit'
)

=== Agent thoughts:
improved_prompt could be "A bright blue space suit wearing rabbit, on the surface of the moon, under a bright orange sunset, with the Earth visible in the background"

Now that I have improved the prompt, I can use the image generator tool to generate an image based on this prompt.
>>> Agent is executing the code below:
image = image_generator(prompt="A bright blue space suit wearing rabbit, on the surface of the moon, under a bright orange sunset, with the Earth visible in the background")
final_answer(image)

How cool is this? 🤩

Use gradio-tools

gradio-tools is a powerful library that allows using Hugging Face Spaces as tools. It supports many existing Spaces as well as custom Spaces.

Transformers supports gradio_tools with the [Tool.from_gradio] method. For example, let's use the StableDiffusionPromptGeneratorTool from gradio-tools toolkit for improving prompts to generate better images.

Import and instantiate the tool, then pass it to the Tool.from_gradio method:

from gradio_tools import StableDiffusionPromptGeneratorTool

gradio_prompt_generator_tool = StableDiffusionPromptGeneratorTool()
prompt_generator_tool = Tool.from_gradio(gradio_prompt_generator_tool)

[!WARNING] gradio-tools require textual inputs and outputs even when working with different modalities like image and audio objects. Image and audio inputs and outputs are currently incompatible.

Use LangChain tools

We love Langchain and think it has a very compelling suite of tools. To import a tool from LangChain, use the from_langchain() method.

Here is how you can use it to recreate the intro's search result using a LangChain web search tool. This tool will need pip install langchain google-search-results -q to work properly.

from langchain.agents import load_tools

search_tool = Tool.from_langchain(load_tools(["serpapi"])[0])

agent = CodeAgent(tools=[search_tool], llm_engine=llm_engine)

agent.run("How many more blocks (also denoted as layers) are in BERT base encoder compared to the encoder from the architecture proposed in Attention is All You Need?")

Manage your agent's toolbox

You can manage an agent's toolbox by adding or replacing a tool.

Let's add the model_download_tool to an existing agent initialized with only the default toolbox.

from agents import HfApiEngine

llm_engine = HfApiEngine("Qwen/Qwen2.5-Coder-32B-Instruct")

agent = CodeAgent(tools=[], llm_engine=llm_engine, add_base_tools=True)
agent.toolbox.add_tool(model_download_tool)

Now we can leverage the new tool:

agent.run(
    "Can you give me the name of the model that has the most downloads in the 'text-to-video' task on the Hugging Face Hub but reverse the letters?"
)

[!WARNING] Beware when adding tools to an agent that already works well because it can bias selection towards your tool or select another tool other than the one already defined.

Use the agent.toolbox.update_tool() method to replace an existing tool in the agent's toolbox. This is useful if your new tool is a one-to-one replacement of the existing tool because the agent already knows how to perform that specific task. Just make sure the new tool follows the same API as the replaced tool or adapt the system prompt template to ensure all examples using the replaced tool are updated.

Use a collection of tools

You can leverage tool collections by using the ToolCollection object, with the slug of the collection you want to use. Then pass them as a list to initialize you agent, and start using them!

from transformers import ToolCollection, CodeAgent

image_tool_collection = ToolCollection(
    collection_slug="huggingface-tools/diffusion-tools-6630bb19a942c2306a2cdb6f",
    token="<YOUR_HUGGINGFACEHUB_API_TOKEN>"
)
agent = CodeAgent(tools=[*image_tool_collection.tools], llm_engine=llm_engine, add_base_tools=True)

agent.run("Please draw me a picture of rivers and lakes.")

To speed up the start, tools are loaded only if called by the agent.

This gets you this image:

9.3 KiB Raw Blame History