Knowledge Base

A knowledge base is like giving AI a dedicated reference book: you put your own documents, notes, and URLs into it, and then when chatting, let AI flip through this book to answer your questions.

Knowledge Base: the left panel is the list of created knowledge bases (at the top + New Knowledge Base), and on the right add file / note / directory / linked data sources to the selected knowledge base

What can you do with a knowledge base?

Here are a few real-world scenarios:

• Company knowledge assistant: put product manuals, API docs, and internal standards all into it, and when employees ask questions, AI answers automatically
• Personal information manager: put your work notes from previous years, reading excerpts, and email archives into it, and ask AI, "In which PPT last year did I mention that analysis framework?"
• Study partner: put courseware and papers into it, and let AI help you quiz chapter by chapter and answer questions
• Contract/regulation quick lookup: put legal provisions and contract templates into it, and ask AI about the application of specific clauses

Why use a knowledge base instead of just giving files directly to AI?

Limitations of directly giving files:

• Need to re-upload every time you ask a question, which is troublesome
• Single conversation has length limits; long documents won't fit
• Can't be reused across conversations

The knowledge base solves all the above problems: upload once, and then it can be called in any conversation, and can "precisely extract relevant passages" from a large amount of material to feed AI.

How to use it?

• For first-time use: see complete knowledge base tutorial
• Want to add images / scanned PDFs: first see document preprocessing, so AI can "understand" the text in images
• Want to know how to choose an embedding model: see embedding model reference
• Want to use it offline, without cloud embeddings: you can use the built-in local embedding modelThe knowledge base can build indexes and retrieve without needing internet access
• Want to know where the data is stored: see knowledge base data

combinations with other capabilities

• Knowledge base + assistant: attach a knowledge base to a certain assistant, and it specializes in this domain
• Knowledge base + agent: let the agent check the knowledge base on its own during task execution
• Knowledge base + Channels: send an agent that "knows how to check company documents" to be on duty in a Feishu group

Recommended to read first advanced capability map, to understand how the knowledge base works together with agents, MCP, channels, and other features.

---

Get help and submit feedback

If you encounter any questions, bugs, or have suggestions for feature improvements during configuration or use, please refer to Feedback and Suggestions for the official channels provided.