Skip to main content
The Knowledge Base section is where you upload documents, create collections, and build retrieval systems that your agents can query. Give your agents access to your company’s data, documentation, and knowledge.

​
Two Main Sections

​
Cloud Storage

Connect external storage providers to automatically sync and index documents:
  • SharePoint
  • OneDrive
  • Google Drive
Cloud Storage

​
RAG Pipeline

Build the retrieval system in 4 steps:
  1. Data Sources - Upload files or connect to storage
  2. Collections - Organize data into collections
  3. Knowledge Bases - Configure retrieval settings
  4. Retrieval Methods - Set up how agents search your data

​
Connecting Cloud Storage

1

Click Cloud Storage Tab

At the top of the Knowledge Base page
2

Click Connect Cloud Storage

Uknow Cloud
3

Choose Your Provider

Select SharePoint, OneDrive, or Google Drive
SharePoint Connection
4

Authenticate

Follow OAuth flow to grant access
5

Select Folders

Choose which folders to sync and index
Files are automatically synced and indexed. Updates to documents are reflected in your knowledge bases.

​
Building a RAG Pipeline

​
Step 1: Data Sources

Upload files or connect to storage:
  • Upload Files: PDF, DOCX, TXT, Markdown
  • Cloud Storage: Auto-sync from connected providers
Milvus Data Sources
Supported file types:
  • PDF
  • DOC, DOCX
  • TXT
  • MD (Markdown)

​
Step 2: Collections

Group related data sources:
  • Create collections by topic or project
  • Add multiple data sources to a collection
  • Configure chunking and embedding settings
Collection settings:
  • Chunk size: How to split documents (default: 1000 tokens)
  • Chunk overlap: Overlap between chunks (default: 200 tokens)
  • Embedding model: Which model to use for embeddings

​
Step 3: Knowledge Bases

Configure retrieval for your collection:
  • Name your knowledge base
  • Set the search method (vector, keyword, hybrid)
  • Configure result limits
Knowledge base options:
  • Top K: Number of results to return (default: 5)
  • Score threshold: Minimum relevance score (0.0 - 1.0)
  • Reranking: Enable reranking for better results

​
Step 4: Retrieval Methods

Set up how agents query your data:
  • Similarity search: Vector-based semantic search
  • Keyword search: Traditional keyword matching
  • Hybrid search: Combine vector + keyword for best results

​
Using Knowledge Bases in Agents

Once created, add knowledge bases to your agents: 
agents:
  - name: "support_agent"
    agent_type: "llm_agent"
    
    knowledge_bases:
      - name: "product_docs"
        top_k: 5
        score_threshold: 0.7
Or use the + button in Playground to insert knowledge bases. → Knowledge Base Setup - Complete YAML configuration reference and advanced retrieval options

​
Managing Your Data

​
Updating Documents

Cloud storage: Files auto-sync when changed Manual uploads:
  1. Go to Data Sources
  2. Click the data source
  3. Upload new version or delete old files

​
Deleting Data

Delete a data source: Removes from all collections Delete a collection: Knowledge bases using it will stop working Delete a knowledge base: Agents using it will fail
Always check which agents are using a knowledge base before deleting it

​
Best Practices

Organize by topic: Create collections for different knowledge domains (product docs, policies, code, etc.)
Use cloud storage for dynamic content: If your docs change frequently, connect cloud storage instead of manual uploads
Test retrieval quality: Use the search preview in Knowledge Bases to test if you’re getting relevant results
Start with hybrid search: Combines the best of vector and keyword search for most use cases

​
Common Issues

“No results found”: Check your score threshold - it might be too high. Try lowering to 0.5 or 0.6
“Irrelevant results”: Increase the score threshold or reduce top_k to get more focused results
“Cloud sync failed”: Re-authenticate your cloud storage connection in Settings → Integrations

​
What’s Next?

Knowledge Base Setup

YAML configuration and advanced retrieval options

Playground

Add knowledge bases to agents

Milvus

Vector database details

Uknow Cloud Storage

Cloud storage integration