Classic Knowledge Base

Lyzr Studio’s Classic Knowledge Base feature allows you to create a no-code RAG pipeline for fast, searchable document understanding. It’s ideal for building lightweight Q&A systems from files, URLs, and plain text sources — optimized for quick setup and cost-efficient usage.

​

1. Choose Knowledge Base Type

Before creation, you’ll be prompted to choose the type of Knowledge Base:

• Classic (for general documents and text)
• Knowledge Graph (for relationship-heavy data)
• Semantic Model (for structured databases)

Select Classic Knowledge Base to proceed.

​

2. Create a Classic Knowledge Base

Define your new KB by entering essential details:

• Name: A meaningful title (e.g., “Marketing FAQs”).
• Description: Briefly explain the purpose of this KB.
• Vector Database: Choose where embeddings will be stored — options include Qdrant, Weaviate, or others integrated with Lyzr.

Click Create to initialize your Classic Knowledge Base.

​

3. Add Content from Multiple Sources

Lyzr supports uploading or linking multiple data types. Content types supported:

• File Upload: PDF, DOCX, TXT, CSV, JSON.
• Web Links: Direct URLs of documentation pages or websites.
• Copy-paste text: Manually input chunks of content.

Lyzr auto-detects file formats and applies the right parser. Behind the scenes:

• Content is split into semantically coherent chunks.
• Embeddings are generated using LLMs.
• The vector store indexes these chunks for fast retrieval.

​

4. Query & Test

Once your Classic KB is populated, test it directly inside Studio:

• Search Input: Ask natural language questions.
• Chunk Count: Control number of results returned (default: 10).
• Retrieval Type: Basic (similarity-based).
• Score Threshold: Filter out low-score responses for higher precision.

You can continue uploading more files or editing your KB over time. Lyzr will automatically update the index.

​

5. Integrate with Agents

The Classic KB can now be connected to Lyzr agents:

• Choose the KB as a data source during agent creation.
• The agent will use this KB to perform Retrieval-Augmented Generation (RAG).
• No coding required — fully visual interface for mapping knowledge and deploying agents.

​

Summary

The Classic Knowledge Base is best suited when you want to get started fast with document-based Q&A and lightweight RAG — no database or complex configuration needed.