AI Lead Generator Agent

This project demonstrates how to use Composio to create a lead generation agent.

Overview

The AI Lead Generator Agent is a powerful tool built using Composio’s tooling ecosystem and agentic frameworks such as LlamaIndex. This agent streamlines the lead generation process for businesses by identifying potential leads, extracting valuable data, and organizing all lead information into a structured spreadsheet. With a user-friendly setup process and seamless integration capabilities, this agent can significantly enhance your outreach efficiency and sales pipeline management.

Getting Started

Python

1. Installation

   install dependencies

   pip install composio-llamaindex python-dotenv
   
2. Connecting to tools and models

   connect to required tools

   composio add peopledatalabs
   composio add googlesheets
   
   export OPENAI_API_KEY="<your-openai-api-key>"
   
3. Importing the required libraries

   import required libraries

   from composio_llamaindex import ComposioToolSet, App, Action
   from llama_index.core.agent import FunctionCallingAgentWorker
   from llama_index.core.llms import ChatMessage
   from llama_index.llms.openai import OpenAI
   from dotenv import load_dotenv
   
   load_dotenv()
   
4. Initializing the Tools and the LLM

   initialize toolset and llm

   toolset = ComposioToolSet(api_key="")
   tools = toolset.get_tools(apps=[App.PEOPLEDATALABS, App.GOOGLESHEETS])
   
   llm = OpenAI(model="gpt-4o")
   
5. Setting up Function Calling Worker

   setup function calling worker

   spreadsheetid = '14T4e0j1XsWjriQYeFMgkM2ihyvLAplPqB9q8hytytcw'
   prefix_messages = [
       ChatMessage(
           role="system",
           content=(
               f"""
               You are a lead research agent. Based on user input, find 10 relevant leads using people data labs.
               After finding the leads, create a Google Sheet with the details for the lead description, and spreadsheet ID: ${spreadsheetid}.
               Print the list of people and their details and the link to the google sheet."""
           ),
       )
   ]
   
   agent = FunctionCallingAgentWorker(
       tools=tools,
       llm=llm,
       prefix_messages=prefix_messages,
       max_function_calls=10,
       allow_parallel_tool_calls=False,
       verbose=True,
   ).as_agent()
   
6. Executing the Agent

   run the agent

   lead_description = 'Senior frontend developers in San Francisco'
   user_input = f"Create a lead list based on the description: {lead_description}"
   response = agent.chat(user_input)
   
7. Final Code

   final code

   from composio_llamaindex import ComposioToolSet, App, Action
   from llama_index.core.agent import FunctionCallingAgentWorker
   from llama_index.core.llms import ChatMessage
   from llama_index.llms.openai import OpenAI
   from dotenv import load_dotenv
   
   load_dotenv()
   toolset = ComposioToolSet(api_key="")
   tools = toolset.get_tools(apps=[App.PEOPLEDATALABS, App.GOOGLESHEETS])
   
   llm = OpenAI(model="gpt-4o")
   
   spreadsheetid = '14T4e0j1XsWjriQYeFMgkM2ihyvLAplPqB9q8hytytcw'
   prefix_messages = [
       ChatMessage(
           role="system",
           content=(
               f"""
               You are a lead research agent. Based on user input, find 10 relevant leads using people data labs.
               After finding the leads, create a Google Sheet with the details for the lead description, and spreadsheet ID: ${spreadsheetid}.
               Print the list of people and their details and the link to the google sheet."""
           ),
       )
   ]
   
   agent = FunctionCallingAgentWorker(
       tools=tools,
       llm=llm,
       prefix_messages=prefix_messages,
       max_function_calls=10,
       allow_parallel_tool_calls=False,
       verbose=True,
   ).as_agent()
   
   lead_description = 'Senior frontend developers in San Francisco'
   user_input = f"Create a lead list based on the description: {lead_description}"
   response = agent.chat(user_input)
   

Javascript

1. Installation

   install dependencies

   npm install composio-core ai @ai-sdk/openai dotenv
   
2. Connecting to tools and models

   connect to required tools

   composio add peopledatalabs
   composio add googlesheets
   
   export OPENAI_API_KEY="<your-openai-api-key>"
   export COMPOSIO_API_KEY="<your-composio-api-key>"
   
3. Importing the required libraries

   import required libraries

   import { openai } from "@ai-sdk/openai";
   import { VercelAIToolSet } from "composio-core";
   import dotenv from "dotenv";
   import { generateText } from "ai";
   
   dotenv.config();
   
4. Initializing the Tools and the LLM

   initialize toolset and llm

   const toolset = new VercelAIToolSet({
     apiKey: process.env.COMPOSIO_API_KEY,
   });
   
   const tools = await toolset.getTools([App.PEOPLEDATALABS, App.GOOGLESHEETS]);
   
5. Setting up Agent

   setup the ai agent

   const leadDescription = 'Senior frontend developers in San Francisco';
   const spreadsheetid='14T4e0j1XsWjriQYeFMgkM2ihyvLAplPqB9q8hytytcw'
   const output = await generateText({
   model: openai("gpt-4o"),
   streamText: false,
   tools: tools,
   prompt: `
           You are a lead research agent. Based on user input, find 10 relevant leads using people data labs.
           After finding the leads, create a Google Sheet with the details for the lead description: ${leadDescription}, and spreadsheet ID: ${spreadsheetid}.
           Print the list of people and their details and the link to the google sheet.
           `, 
   maxToolRoundtrips: 5,
   });
   
6. Final Code

   final code

   import { openai } from "@ai-sdk/openai";
   import { VercelAIToolSet } from "composio-core";
   import dotenv from "dotenv";
   import { generateText } from "ai";
   
   dotenv.config();
   
   const toolset = new VercelAIToolSet({
     apiKey: process.env.COMPOSIO_API_KEY,
   });
   
   const tools = await toolset.getTools([App.PEOPLEDATALABS, App.GOOGLESHEETS]);
   
   const leadDescription = 'Senior frontend developers in San Francisco';
   const spreadsheetid='14T4e0j1XsWjriQYeFMgkM2ihyvLAplPqB9q8hytytcw'
   const output = await generateText({
   model: openai("gpt-4o"),
   streamText: false,
   tools: tools,
   prompt: `
           You are a lead research agent. Based on user input, find 10 relevant leads using people data labs.
           After finding the leads, create a Google Sheet with the details for the lead description: ${leadDescription}, and spreadsheet ID: ${spreadsheetid}.
           Print the list of people and their details and the link to the google sheet.
           `, 
   maxToolRoundtrips: 5,
   });
   
   console.log("🎉Output from agent: ", output.text);