Tables and data modeling · AutessaDB
Knowledge bases
An AutessaDB knowledge base is a table preset for documents: drag in files or whole folders and they are uploaded, indexed for semantic search and searchable right away. A Create Agent shortcut on the table provisions a ready-made search agent over it, which makes it the fastest route to retrieval-augmented generation (RAG) on your own documents.
-- the problem
RAG usually means a pipeline before the first answer
Grounding an assistant in your documents normally means a storage bucket, a chunker, an embedding job, a vector database and glue code to keep them in sync. A knowledge base does that inside one table, and keeps the files, their notes and their index together under the same sharing and security.
What you get
- A creation wizard with drag-and-drop for files or whole folders.
- Files are indexed automatically and searchable as soon as the upload finishes.
- File columns get an auto-generated notes companion that describes each document.
- A Semantic Search tab on the table returns ranked results with similarity scores.
- Create Agent provisions a Search agent over the knowledge base in one click.
- A knowledge base is still a table: share it, secure it, add columns, trigger on it.
- Knowledge bases can also be created through the API at /create-knowledge-base.
-- how it works
How does knowledge bases work in AutessaDB?
Create
Choose New, then Knowledge base, and name it.
Upload
Drag in documents or folders on the Upload Files step.
Search
Open the Semantic Search tab, type a question and read the ranked matches.
Add an agent
Click Create Agent for a Search agent that answers from the knowledge base.
-- every option
Knowledge base options
| option | what it does |
|---|---|
| Name and description | What the knowledge base holds, read by people and agents. |
| Upload Files | Drag-and-drop files or folders. |
| Semantic Search tab | Query, pick the vectorized column, see scores. |
| Create Agent | Provisions a ready-made Search agent over the table. |
| Sharing | The same READ, WRITE, PUBLISH and ADMIN levels as any table. |
-- permissions
Who can do what?
| access | can |
|---|---|
| Owner / ADMIN | Create, share and delete the knowledge base. |
| WRITE | Upload and remove documents. |
| READ | Search and read documents. |
◆ AI assist
Where AI helps
Each document is indexed with AI enrichment: summaries, key facts and the questions someone would likely ask of it, so searches match meaning. The Create Agent shortcut gives you an agent that searches the table at run time.
AI in AutessaDB works inside the same access rules as the person using it, and schema changes always wait for a person to apply them.
-- relations
How it connects
autessadb feature
Semantic search
The engine underneath every knowledge base.
autessadb feature
File and audio search
How documents get their searchable notes.
autessa platform
AI agents
Search agents answer from the knowledge base.
autessa product
Autessa Drive
For full folder trees with versions and sharing, use a Drive.
-- faq
Questions about knowledge bases
Is a knowledge base a separate vector database?
No. It is an AutessaDB table pre-configured for document storage and semantic search, so it shares the same security, sharing, triggers and APIs as every other table.
What file types can I upload?
Documents such as PDF, DOCX, XLSX and TXT, the same types a File column accepts.
Can search work on tables that are not knowledge bases?
Yes. Semantic search works on any vectorized column of any table; a knowledge base is just the one-click preset for bulk files.
100% customizable, code and all
Make AutessaDB fully your own.
Use it out of the box, then change anything. Ask Autobot, Autessa’s AI builder, for a new field, screen, report, workflow or agent and it builds it into your copy of the app. Or open the code and edit it yourself. Nothing is locked: the app, its data and its code are yours.
Start free and make it yours