# Overview

<figure><img src="/files/9XrB4LYaM7pO5ch6Vk6A" alt=""><figcaption></figcaption></figure>

## What is Diaflow Vector Database?

The Diaflow Vector Database is an intelligent knowledge management system that enables you to upload, organize, and utilize your business documents, articles, and web content for AI-powered conversations and content generation. By converting your content into vector embeddings, the system allows for semantic search and contextual knowledge retrieval across your entire knowledge base.

Vector Database Overview Screenshot Alt text: Diaflow Vector Database main interface showing the sidebar navigation and vector management dashboard

## Key Features

* Multi-Format Support: Upload documents (PDF, DOCX, TXT, MD, CSV, XLSX, XLS, JSON), create articles, and crawl websites (HTTP, HTTPS)
* Smart Organization: Organize content using groups or maintain in root directory
* Semantic Search: Find relevant information using natural language queries
* AI Integration: Power your chatbots and content generation with your knowledge base
* Automated Processing: Intelligent chunking and vectorization of your content

## System Requirements

**Prerequisites:**

* Active Diaflow workspace account
* Web browser (Chrome, Firefox, Safari, or Edge - latest versions)
* Stable internet connection
* Files within supported formats and size limits

**Supported File Types:**

* Documents: .pdf, .docx, .txt, .md
* Spreadsheets: .xlsx, .xls, .csv
* Web content: http\:// and https\:// URLs
* JSON format files: .json

**File Limitations:**

* Text-based documents: Maximum 300,000 words per file
* Tabular files: Maximum 2000 rows per file
* Individual file upload: Maximum 50MB per file

Important Note: The current Diaflow UI allows attaching a file to multiple groups, while the backend service only supports querying a file under a single group. This limitation is documented for FAQ purposes and will be resolved in a future enhancement.

<br>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.diaflow.io/productivity-tools/diaflow-vectors/overview.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.