Knowledge Base (RAG)

Upload your documents and let agents search them using Retrieval-Augmented Generation (RAG). Ground AI responses in your actual data instead of relying on the model's training data.

What is RAG?

RAG (Retrieval-Augmented Generation) is a technique where the AI searches your documents for relevant information before generating a response. This means your agent can answer questions using YOUR data — product docs, company policies, FAQ articles, etc.

Set Up via Dashboard

Open Knowledge Tab

Click 'Knowledge' in the dashboard sidebar.

Create a Collection

Click 'Create Collection' and give it a name (e.g., 'product-docs').

Upload Documents

Upload PDF, TXT, MD, or CSV files. Fluxgate auto-chunks and embeds them.

Wait for Processing

Documents are chunked, embedded, and indexed. This takes a few seconds per document.

Link to Agent

Go to the Agents tab, edit your agent, and link this knowledge collection.

Test It

Run the agent with a question about your documents. It will search the knowledge base automatically.

Upload via API

Knowledge Base APIbash

# Create a collection
curl -X POST http://localhost:8000/api/v1/knowledge/collections \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{ "name": "product-docs", "description": "Product documentation" }'

# Upload a document
curl -X POST http://localhost:8000/api/v1/knowledge/collections/COLLECTION_ID/documents \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@/path/to/document.pdf" \
  -F "metadata={"source":"product-docs"}"

# Search the knowledge base
curl -X POST http://localhost:8000/api/v1/knowledge/search \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{ "query": "return policy", "collection_id": "COLLECTION_ID", "limit": 5 }'

Best document types for RAG

FAQs, product manuals, policy documents, and support articles work best. Keep documents focused on specific topics for better search accuracy.

Multi-Agent

Workflows