Show HN: Redash Fork with AI Capabilities

A developer has released a fork of the open-source data visualization tool Redash that adds AI capabilities, including text-to-query generation, auto-visualizations, auto-alerts, and AI-generated dashboards. The fork supports multiple AI providers such as Anthropic, DeepSeek, Gemini, Grok, HuggingFace, OLlama, OpenAI, and OpenRouter, and now runs on macOS as well as Linux. The project is available on GitHub and includes installation instructions for local and on-premise setups.

Redash is an amazing open source tool for querying and visualizing data. It allows you to connect to any data source, easily visualize and share your data, and collaborate with your team. For more information, please visit Redash GitHub repository https://github.com/getredash/redash . This fork adds support for AI. New Redash features: Data Source Description : Help the AI to understand your data better. Text To Query : Use AI to generate SQL, NoSQL and other queries from natural language questions. Auto Visualizations : Use AI to auto-generate visualizations for questions. Auto Alerts : Use AI to generate alert suggestions from your data and queries. Name To Dashboard : Use AI to generate dashboards from your queries and visualizations. MacOS Support : Now it runs on MacOS as well as on Linux. Watch the demo video on YouTube to see the new AI features in action. NOTICE: All tests were run on a local PC. Anthropic https://www.anthropic.com/ Cloud DeepSeek https://www.deepseek.com/ Cloud, Local & Remote Gemini https://gemini.google.com/ Cloud Grok https://grok.com/ Cloud HuggingFace https://huggingface.co/ Local OLlama https://ollama.com/ Cloud, Local & Remote OpenAI https://openai.com/ Cloud OpenRouter https://openrouter.ai/ Cloud See Redash's Prerequisites https://github.com/getredash/redash/wiki/Local-development-setup set-up-the-prerequisites for detailed instructions on how to install the prerequisites. git clone https://github.com/freaker2k7/redash cd redash make local init REDASH COOKIE SECRET=1234....1234 REDASH SECRET KEY=1234...1235 HF TOKEN=hf 1234...1234 make local run Alternatively, you can run the server and client separately: Run the server make up Run the client make start NOTE: This is useful if you want to run the server and client in separate machines. while $ curl -s -o /dev/null -w "%{http code}" http://localhost:5001 -ne 200 ; do; sleep 1; done 6. Open your web browser and go to http://localhost:5001 http://localhost:5001 to access Redash. Install Nginx if you haven't already - Nginx Installation Guide https://nginx.org/en/docs/install.html Then add the following configuration as redash.conf to your Nginx configuration folder usually located at /etc/nginx/conf.d/ : server { listen 80; server name yourdomain.com; If you want only HTTP, then remove from this comment... return 301 https://$host$request uri; } server { listen 443 ssl; server name yourdomain.com; ssl certificate /path/to/your/certificate.crt; ssl certificate key /path/to/your/private.key; ... up to this comment. while $ curl -s -o /dev/null -w "%{http code}" http://localhost:5001 -ne 200 ; do; sleep 1; done proxy pass http://localhost:5001; proxy set header Host $host; proxy set header X-Real-IP $remote addr; proxy set header X-Forwarded-For $proxy add x forwarded for; proxy set header X-Forwarded-Proto $scheme; } } NOTE: This step is suited only for on-premise installations. If you are using a cloud provider, think about using their load balancer or reverse proxy service instead. Quick installation steps for those who want to get started with Redash quickly: git clone https://github.com/freaker2k7/redash cd redash make quickstart NOTE: This will take a few good minutes to complete. Once done, you can access Redash at http://localhost:5001. Meanwhile, you can get some coffee. To stop Redash, run the following command in the project directory: make down Also, you can clean up a bit by running, in the project directory: make clean Now there is a helper Ubuntu docker in /macos-helper which assists with installing the python dependencies. Moreover it has an RDP support, so one can use Microsoft Remote Desktop Manager to access the Ubuntu GUI and work on the Redash server and client from there. You can build the helper docker with the following command: docker build -t macos-install-helper ./macos-helper Then run it with the following command: docker run -d -p 3389:3389 -v /var/run/docker.sock:/var/run/docker.sock -v $ pwd :/home/redash/redash --name ubuntu macos-install-helper /entrypoint.sh rdp Finally, you can connect to the Ubuntu GUI with the following credentials: Username: redash Password: 1234 Host: localhost Port: 3389 Please email me mailto:thenetfreaker+security@gmail.com to report any security vulnerabilities regarding the AI feature explicitly. We will acknowledge receipt of your vulnerability and strive to send you regular updates about our progress. If you're curious about the status of your disclosure please feel free to email us again. For any other issue, please issue or PR to the Redash GitHub repository https://github.com/getredash/redash . BSD-2-Clause.