Question 1

What is DocsRay?

Accepted Answer

DocsRay is a lightweight PDF Question-Answering (Q&A) tool powered by Retrieval-Augmented Generation (RAG) with MCP (Model Context Protocol) Support. It allows you to ask questions about your PDF documents and get accurate, context-aware answers.

Question 2

What file types does DocsRay support?

Accepted Answer

DocsRay supports over 30 file formats including Microsoft Office documents (.docx, .xlsx, .pptx), plain text (.txt), image formats (.jpg, .png, .gif, .bmp, .tiff, .webp), HTML, and Markdown. It automatically converts these formats to PDF for processing.

Question 3

How do I install DocsRay?

Accepted Answer

You can install DocsRay using pip: pip install docsray

Question 4

How do I download the required models for DocsRay?

Accepted Answer

You can download the models using the following command: docsray download-models

Question 5

How do I start the web interface?

Accepted Answer

You can start the web interface using the following command: docsray web

Question 6

What is MCP Integration?

Accepted Answer

MCP (Model Context Protocol) integration allows DocsRay to seamlessly integrate with Claude Desktop and other MCP-compatible AI models, enabling contextual interaction with your documents directly from these platforms.

Question 7

How do I configure Claude Desktop for MCP integration?

Accepted Answer

You can configure Claude Desktop using the following command: docsray configure-claude

Question 8

What are the different performance modes in DocsRay?

Accepted Answer

DocsRay has three performance modes: FAST_MODE, Standard, and FULL_FEATURE_MODE. The mode is automatically selected based on your system's resources, but you can force a specific mode using the DOCSRAY_FAST_MODE environment variable.

Question 9

What models does DocsRay use?

Accepted Answer

DocsRay uses models such as bge-m3, multilingual-e5-large, Gemma-3-1B, and Gemma-3-4B for embedding and answer generation.

Question 10

How much storage space do the models require?

Accepted Answer

The models require approximately 8GB of storage space in total.

Question 11

How do I clear the cache in DocsRay?

Accepted Answer

You can clear the cache using the clear_all_cache MCP command or by manually deleting the contents of the cache directory (~/.docsray/cache/).

Question 12

Does DocsRay support visual content analysis?

Accepted Answer

Yes, DocsRay supports visual content analysis using models like Gemma-3-4B. It can analyze images, charts, and diagrams within your documents.

Question 13

How do I enable or disable visual analysis?

Accepted Answer

You can enable or disable visual analysis through the web interface or by adjusting the analyze_visuals parameter in the Python API.

Question 14

How does the auto-restart feature work?

Accepted Answer

DocsRay includes an automatic restart feature that helps maintain service stability by automatically recovering from errors, memory issues, or crashes. Use the --auto-restart flag when starting the web or MCP server.

Question 15

What is the FAST_MODE and when should I use it?

Accepted Answer

FAST_MODE is an optimized mode for resource-constrained environments. It reduces memory usage and processing time by using lower-precision models and disabling certain features like visual analysis. Use it when running DocsRay on laptops or servers with limited resources.

Question 16

How can DocsRay be integrated with the UBOS platform?

Accepted Answer

DocsRay can be integrated with UBOS to enhance AI Agent development and deployment. It can be easily incorporated into UBOS-managed AI Agents, improving their ability to understand and interact with documents. UBOS also simplifies the deployment and management of DocsRay in a business environment.

DocsRay

Resources

Project Details

Recomended MCP Servers

Featured Templates

Image Generation with Stable Diffusion

Multi-language AI Translator

Service ERP

Talk with Claude 3

Pharmacy Admin Panel

AI Video Generator

Start your free trial