Skip to content
Dhanasvi
Sign inExplore
Build a Knowledge Base Chatbot with Jotform, RAG Supabase, Together AI & Gemini logo

Build a Knowledge Base Chatbot with Jotform, RAG Supabase, Together AI & Gemini

Verified

Builds a RAG chatbot that retrieves Supabase embeddings and answers via Gemini.

n8nAI & LLMIntermediate👁 15 views
Open template
Updated 2026-06-15

What this workflow does

This workflow implements retrieval-augmented generation by storing text chunks and embeddings in Supabase, searching them on each query, and synthesizing answers with Gemini.

It is intended for developers and teams that need a private, embeddable knowledge-base chatbot without managing separate LLM infrastructure.

Who is this for?

Knowledge managers, support teams, and developers building internal or customer-facing chatbots that answer questions from uploaded PDFs.

What problem it solves

Manually searching documents or building chatbots from scratch is slow; this workflow automates PDF ingestion into a vector database and enables natural-language queries via an AI agent.

Live workflow preview

Interactive canvas of every node and connection — scroll and click to explore. Powered by n8n's preview.

Open the template on n8n to import and run it. View source template →

What it automates

Product support bot

Upload a product manual PDF via Jotform; users ask questions and receive answers grounded in the document.

Internal policy assistant

HR uploads company handbook; employees query policies without reading the full PDF.

Research Q&A

Researchers upload papers; the chatbot retrieves relevant chunks and summarizes findings.

How the workflow works

The 5 nodes in this automation, in order.

  1. 1HTTP RequesthttpRequest
  2. 2Supabasesupabase
  3. 3Codecode
  4. 4AI Agent@n8n/n8n-nodes-langchain.agent
  5. 5Google Gemini Chat Model@n8n/n8n-nodes-langchain.lmChatGoogleGemini

Apps & integrations used

HTTP RequestSupabaseAI AgentGoogle Gemini Chat Model

How to set up Build a Knowledge Base Chatbot with Jotform, RAG Supabase, Together AI & Gemini

  1. 1Create Supabase table 'RAG' and matchembeddings1 function using the provided SQL
  2. 2Build Jotform with name, email, and PDF upload fields
  3. 3Obtain Together AI key and insert into the two embedding nodes
  4. 4Replace Supabase credentials in Save embedding and Search Embeddings nodes
  5. 5Add Google Gemini and Together AI credentials in n8n
  6. 6Import workflow, connect Jotform trigger, and activate

How to customize this workflow

  • →Swap Together AI embeddings for another provider via HTTP Request node
  • →Replace Jotform trigger with Typeform or Google Form webhook
  • →Add an email notification node after successful PDF ingestion
  • →Change Gemini model to a different chat model supported by n8n

Build a Knowledge Base Chatbot with Jotform, RAG Supabase, Together AI & Gemini: pros & cons

Pros

  • +End-to-end RAG pipeline with PDF handling
  • +Uses existing Supabase and free-tier AI APIs
  • +Clear separation of ingestion and query flows
  • +No custom code beyond provided SQL

Cons

  • –Requires manual Supabase SQL setup
  • –Together AI key mandatory for embeddings
  • –No built-in chunking or PDF parsing configuration exposed
Did you find this helpful?

Frequently asked questions

It ingests PDFs from Jotform into Supabase embeddings and lets users chat with the content using Gemini via an AI Agent.

User reviews

Verified reviews from the community shape this listing's rating.

Loading reviews…

Sign in to review

Promote Build a Knowledge Base Chatbot with Jotform, RAG Supabase, Together AI & Gemini

Add this badge to your website, or share the tool.

DFeatured on DhanasviBuild a Knowledge Base Chatbot with Jotform, RAG Supabase, Together AI & Gemini 0