Build a Smart Conversational AI Assistant with Local LLM & Tool Use
detail.loadingPreview
Deploy a powerful conversational AI assistant powered by a local Ollama LLM. This workflow enables your chatbot to understand user queries, maintain conversation context, and dynamically leverage external tools like Wikipedia and a weather API to provide accurate, real-time information.
About This Workflow
This n8n workflow empowers you to create an intelligent conversational AI assistant, running on your local machine using Ollama and the Llama 3.2 LLM. It intelligently processes user chat messages, maintaining context over the last 20 interactions for fluid conversations. The AI agent is equipped with dynamic tool-use capabilities, allowing it to seamlessly fetch current weather information via an Open-Meteo API for any given location, and retrieve general knowledge from Wikipedia. This setup is ideal for building custom, privacy-focused chatbots that can respond to diverse queries by integrating real-time data and extensive knowledge bases, all within your n8n automation ecosystem.
Key Features
- Local LLM Integration: Utilize Llama 3.2 via Ollama for privacy-focused and cost-effective AI inference, keeping your data in-house.
- Intelligent Tool Use: AI agent dynamically selects and employs specialized tools (Weather API, Wikipedia) to answer complex and specific user queries.
- Conversational Memory: Maintains context over the last 20 messages with a buffer memory, ensuring natural and continuous interactions.
- Real-time Information Retrieval: Provides up-to-date weather forecasts and comprehensive general knowledge on demand.
- Customizable Assistant: Easily modify the agent's persona and add more tools to expand its capabilities for various use cases.
How To Use
- Set up Ollama: Ensure Ollama is installed and running locally on your machine, with the
llama3.2:latestmodel downloaded and available. - Configure Ollama Chat Model: In the
Ollama Chat Modelnode, connect to your local Ollama service using appropriate credentials. Verify thatllama3.2:latestis selected as the model. - Define AI Agent Persona: Review the
AI Agentnode's "System Message" under the "Options" section. This message instructs the agent on its persona and the tools it has access to (e.g., weather and Wikipedia). - No further configuration needed for Wikipedia or Weather Tool: The
WikipediaandWeather HTTP Requestnodes are pre-configured to function as tools that the AI agent can intelligently call upon. - Start Chatting: Use the
On new manual Chat Messagetrigger node to input your queries and begin interacting with your smart AI assistant.
Apps Used
Workflow JSON
{
"id": "5421e4a3-9c21-4341-8b07-d1bbe038b3ae",
"name": "Build a Smart Conversational AI Assistant with Local LLM & Tool Use",
"nodes": 29,
"category": "Operations",
"status": "active",
"version": "1.0.0"
}Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.
Get This Workflow
ID: 5421e4a3-9c21...
About the Author
DevOps_Master_X
Infrastructure Expert
Specializing in CI/CD pipelines, Docker, and Kubernetes automations.
Statistics
Related Workflows
Discover more workflows you might like
Instant WooCommerce Order Notifications via Telegram
When a new order is placed on your WooCommerce store, instantly receive detailed notifications directly to your Telegram chat. Stay on top of your e-commerce operations with real-time alerts, including order specifics and a direct link to view the order.
On-Demand Microsoft SQL Query Execution
This workflow allows you to manually trigger and execute any SQL query against your Microsoft SQL Server database. Perfect for ad-hoc data lookups, administrative tasks, or quick tests, giving you direct control over your database operations.
Automate Getty Images Editorial Search & CMS Integration
This n8n workflow automates searching for editorial images on Getty Images, extracts key details and embed codes, and prepares them for seamless integration into your Content Management System (CMS), streamlining your content creation process.