Blog
Building AI Agents with LangChain and VibeCodeCheap
← Back to Blog

Building AI Agents with LangChain and VibeCodeCheap

• 2 min read
langchain ai-agents tutorial python

AI agents are transforming how we build intelligent applications. In this tutorial, we’ll build a powerful AI agent using LangChain and VibeCodeCheap’s affordable API.

What We’ll Build

A research assistant agent that can:

  • Search the web for information
  • Summarize content
  • Answer follow-up questions
  • Maintain conversation context

Prerequisites

  • Python 3.9+
  • VibeCodeCheap API key
  • Basic Python knowledge

Step 1: Install Dependencies

pip install langchain langchain-openai python-dotenv

Step 2: Configure the API

Create a .env file:

OPENAI_API_KEY=your-vibecodecheap-key
OPENAI_API_BASE=https://api.vibecodecheap.com/v1

Step 3: Create the Agent

from langchain_openai import ChatOpenAI
from langchain.agents import AgentExecutor, create_openai_functions_agent
from langchain.tools import tool
from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
import os
from dotenv import load_dotenv

load_dotenv()

# Initialize the LLM with VibeCodeCheap
llm = ChatOpenAI(
    model="claude-sonnet-4.5",
    openai_api_key=os.getenv("OPENAI_API_KEY"),
    openai_api_base=os.getenv("OPENAI_API_BASE"),
)

@tool
def search_web(query: str) -> str:
    """Search the web for information."""
    # Your search implementation
    return f"Search results for: {query}"

@tool
def summarize(text: str) -> str:
    """Summarize the given text."""
    return llm.invoke(f"Summarize this: {text}").content

# Create the agent
tools = [search_web, summarize]

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a helpful research assistant."),
    MessagesPlaceholder(variable_name="chat_history"),
    ("human", "{input}"),
    MessagesPlaceholder(variable_name="agent_scratchpad"),
])

agent = create_openai_functions_agent(llm, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

Step 4: Run the Agent

result = agent_executor.invoke({
    "input": "Research the latest trends in AI coding assistants",
    "chat_history": []
})

print(result["output"])

Why VibeCodeCheap for AI Agents?

Building agents requires many API calls. Our pricing makes it affordable:

  • 50% lower costs - More experiments, less worry
  • OpenAI compatible - Works with LangChain out of the box
  • Multiple models - Try Claude, GPT-4, Gemini
  • High rate limits - Handle production workloads

Next Steps

  • Add more tools to your agent
  • Implement memory for long conversations
  • Deploy as a web service

Start building AI agents today

API for Your AI Agents

Build AI agents with Claude Code, LangChain, CrewAI. One API key for Claude, Gemini models.

Get API Key View Documentation
API for Your AI Agents

Related Posts

Build Your AI Agents Now

API proxy for Claude Code, LangChain, CrewAI & more. One API key for Claude, Gemini models.

Get API Key Read Documentation