Build an AI Chatbot with InfraNodus Knowledge Graph for Enhanced Responses

Build an embeddable AI chatbot with an access to a knowledge base

This is an example of a simple AI chatbot that has access to external knowledge to augment its responses.

The knowledge can be added manually or imported from multiple sources (text and PDF files, websites, CSVs, Google search results, AI generated, YouTube search results, RSS feeds, etc) using InfraNodus.

• no OpenAI account needed • no vector store needed • easy data import: PDF, text, CSV, Google / YouTube results, RSS feeds, websites, or AI-generated

How it works

First, you add your data into your InfraNodus graph — this will be your knowledge base.

You can import this data from multiple sources or add it manually.

You will have a visual interface available that will show the main concepts and topics in your knowledge base, so you can have an overview of its structure and know how to improve it, if necessary.

Your data is represented as a knowledge graph which contains information about relations and topical clusters in your data, making the LLM responses much more precise.

How to use Copy the template Add your InfraNodus API key to the HTTP AI response node Create a new graph in InfraNodus with your data (or import from an external source) Add the name of this graph into the name field of the AI response HTTP node. That's it! You can query it using the embeddable web form available via a URL

Requirements

You only need an InfraNodus account to set this workflow up.

Free 14-day trials are available.