Create a problem-solving agent

Developing agents in Langchain is complex.

To simplify the development of agents, Langflow created a custom Agent component that simplifies configuration and lets developers focus on solving problems with agents.

The Agent component contains all of the elements you’ll need for creating an agent, including an LLM model selector, an Agent Instructions field, and a Current Date tool. Instead of managing additional components for LLM providers and prompts, just pick your model, enter instructions for the agent, and connect tools to the agent’s Tools port.

Learn how to build a flow starting with the agent component, and see how it can help you solve problems.

Prerequisites

Create a problem-solving agent with AgentComponent

Create a problem-solving agent in Langflow, starting with the Agent component.

Click New Flow, and then click Blank Flow.
Click and drag an Agent component to your workspace. The default settings are acceptable for now, so this guide assumes you’re using Open AI for the LLM.
Add your Open AI API Key to the Agent component.
Add Chat input and Chat output components to your flow, and connect them to the Agent component.

This basic flow enables you to chat with the agent in the Playground after you’ve connected some Tools.
Connect the Search API tool component to your agent.
Add your Search API key to the component. Your agent can now query the Search API for information.
Connect a Calculator tool for solving basic math problems.
Connect an API Request component to the agent. This component is not in the Tools category, but the agent can still use it as a tool if Tool Mode is enabled. Tool Mode makes a component into a tool by adding a Toolset port that can be connected to an agent’s Tools port.
To enable Tool Mode on the component, click Tool Mode. The component’s fields change dynamically based on the mode it’s in.

Solve problems with the agent

Your agent now has tools for performing a web search, doing basic math, and performing API requests. You can solve many problems with just these capabilities.

Your tabletop game group cancelled, and you’re stuck at home. Point API Request to an online rules document, tell your agent You are a fun game organizer who uses the tools at your disposal, and play a game.
You need to learn a new software language quickly. Point API Request to some docs, tell your agent You are a knowledgeable software developer who uses the tools at your disposal, and start learning.

See what problems you can solve with this flow. As your problem becomes more specialized, add a tool. For example, add a Python REPL component to solve math problems that are too challenging for the calculator.

Use an agent as a tool

The Agent component itself also supports Tool Mode for creating multi-agent flows.

Add an additional Agent component to your problem-solving flow that uses a different OpenAI model for more specialized problem solving.

Click and drag an Agent component to your workspace.
Add your Open AI API Key to the Agent component. In the Model Name field, select gpt-4o.
Click Tool Mode to use this new agent as a tool.
Connect the new agent’s Toolset port to the previously created agent’s Tools port.
Connect the Search API and API Request components to the new agent. The new agent will use gpt-4o for the larger tasks of scraping and searching information that requires large context windows. The problem-solving agent will now use this agent as a tool, with its unique LLM and toolset.

Add custom components as tools

An agent can use custom components as tools.

To add a custom component to the problem-solving agent flow, click New Custom Component.

Add custom Python code to the custom component.

Here’s an example text analyzer for sentiment analysis.

Python example code

from langflow.custom import Component
from langflow.io import MessageTextInput, Output
from langflow.schema import Data
import re
class TextAnalyzerComponent(Component):
display_name = "Text Analyzer"
description = "Analyzes and transforms input text."
documentation: str = "http://docs.langflow.org/components/custom"
icon = "chart-bar"
name = "TextAnalyzerComponent"
text
inputs = [
    MessageTextInput(
        name="input_text",
        display_name="Input Text",
        info="Enter text to analyze",
        value="Hello, World!",
        tool_mode=True,
    ),
]

outputs = [
    Output(display_name="Analysis Result", name="output", method="analyze_text"),
]

def analyze_text(self) -> Data:
    text = self.input_text

    # Perform text analysis
    word_count = len(text.split())
    char_count = len(text)
    sentence_count = len(re.findall(r'\w+[.!?]', text))

    # Transform text
    reversed_text = text[::-1]
    uppercase_text = text.upper()

    analysis_result = {
        "original_text": text,
        "word_count": word_count,
        "character_count": char_count,
        "sentence_count": sentence_count,
        "reversed_text": reversed_text,
        "uppercase_text": uppercase_text
    }

    data = Data(value=analysis_result)
    self.status = data
    return data

To enable the custom component as a tool, click Tool Mode.
Connect the tool output to the agent’s tools input.

Ask the agent, What tools are you using to answer my questions? Your response will be similar to the following, and will include your custom component.

I have access to several tools that assist me in answering your questions, including:
Search API: This allows me to search for recent information or results on the web.
HTTP Requests: I can make HTTP requests to various URLs to retrieve data or interact with APIs.
Calculator: I can evaluate basic arithmetic expressions.
Text Analyzer: I can analyze and transform input text.
Current Date and Time: I can retrieve the current date and time in various time zones.

Make any component a tool

The following components support Tool Mode:

URL
API request
Calculator
Current date

If the component you want to use as a tool doesn’t have a Tool Mode button, add tool_mode=True to the component’s code under MessageTextInput. For example, in the components as tools example above, tool_mode=True, is added so the custom component can be used as a tool. Tool Mode supports the MessageTextInput type.

inputs = [
    MessageTextInput(
        name="input_text",
        display_name="Input Text",
        info="Enter text to analyze",
        value="Hello, World!",
        tool_mode=True,
    ),
]

Add flows as tools

An agent can use flows that are saved in your workspace as tools.

To add a Flow as tool component, click and drag a Flow as tool component to your workspace.
Select the flow you want the agent to use as a tool.
Connect the tool output to the agent’s tools input.
Ask the agent, What tools are you using to answer my questions?

Your Flow as tool flow should be visible in the response.