Conversational AI Agent with Web Search (OpenAI & SerpAPI)

Unlock Real-time Information with this Conversational AI Agent

This n8n workflow deploys a powerful Langchain-based AI Agent capable of engaging in natural conversations and augmenting its knowledge with real-time web search capabilities. When you send a message via the chat trigger, the agent, powered by OpenAI's gpt-4o-mini, processes your query. If needed, it dynamically uses SerpAPI to fetch up-to-date information from the internet, then synthesizes this information to provide comprehensive and relevant responses. It's designed to be a smart assistant that can answer questions, perform research tasks, and provide information that goes beyond its static training data.

Key Features & Benefits

• Conversational Interface: Engage with the agent through a natural chat-like interaction using the webhook trigger.
• Advanced AI Reasoning: Leverages OpenAI's gpt-4o-mini for intelligent understanding, planning, and response generation.
• Real-time Web Search Ability: Integrated SerpAPI tool allows the agent to access current information from the internet, making its responses timely and relevant.
• Contextual Memory: Utilizes Window Buffer Memory to maintain conversation context for more coherent follow-up interactions.
• Langchain Powered: Built using n8n's Langchain nodes for robust and flexible agent capabilities.
• Boost Productivity: Get quick answers and research insights directly, streamlining information gathering processes.
• Extensible: Easily add more Langchain tools (e.g., for database queries, API interactions) or customize the agent's prompts and behavior within n8n.

• An n8n instance (Cloud or self-hosted).
• OpenAI API Key with access to the gpt-4o-mini model (or another compatible model).
• SerpAPI API Key.
• n8n Langchain nodes must be enabled/available in your instance.

1. Download the n8n workflow JSON file.
2. Import the workflow into your n8n instance.
3. Configure the 'OpenAI Chat Model' node:
   • Click on the node, then under 'Credential for OpenAI API', select or create your OpenAI credentials.
   • Ensure gpt-4o-mini is selected in the 'Model' parameter, or choose a suitable alternative.
4. Configure the 'SerpAPI' node:
   • Click on the node, then under 'Credential for SerpAPI API', select or create your SerpAPI credentials.
5. (Optional) Adjust parameters in the 'Window Buffer Memory' node if you require a different conversation memory length (e.g., Memory Key, Window Size).
6. The 'When chat message received' node acts as the webhook trigger. Once the workflow is active, n8n will provide Test and Production URLs in this node's settings.
7. Activate the workflow.
8. To interact with your AI Agent, send a POST request to the Production URL of the 'When chat message received' node. The request body should be JSON, for example: {"message": "What's the latest news on AI hardware?"}. You can use tools like cURL, Postman, or integrate it into your applications.