Full-stack RAG app built on Cloudflare
The Cloudflare RAG project is a fullstack application utilizing Cloudflare technologies, featuring a streaming UI, hybrid search, and support for multiple AI providers, with detailed development instructions provided.
Read original article
The Cloudflare RAG project is a fullstack application that showcases the development of a Retrieval Augmented Generation (RAG) app using various Cloudflare technologies. It integrates Cloudflare Workers, Pages, D1, KV, R2, AI Gateway, and Workers AI to create a robust application. Key features include a streaming user interface, hybrid search capabilities combining full-text and vector searches, support for multiple AI providers with fallback options, rate limiting, and OCR functionality. The project provides detailed development and deployment instructions, requiring tools like Node, pnpm, and wrangler CLI. Users can set up the application by installing dependencies, configuring necessary files, and running a local development server. The hybrid search mechanism involves rewriting user input into multiple queries, executing them against both D1 and Vectorize, and merging results for optimal response generation. The project is licensed under the MIT License, and the author is open to consulting on AI applications.
- The project demonstrates a fullstack RAG application using Cloudflare technologies.
- It features a streaming UI, hybrid search, and support for multiple AI providers.
- Detailed instructions for development and deployment are provided.
- The hybrid search mechanism enhances query execution and result merging.
- The project is licensed under the MIT License.
Related
Show HN: R2R V2 – A open source RAG engine with prod features
The R2R GitHub repository offers an open-source RAG answer engine for scalable systems, featuring multimodal support, hybrid search, and a RESTful API. It includes installation guides, a dashboard, and community support. Developers benefit from configurable functionalities and resources for integration. Full documentation is available on the repository for exploration and contribution.
Vercel AI SDK: RAG Guide
Retrieval-augmented generation (RAG) chatbots enhance Large Language Models (LLMs) by accessing external information for accurate responses. The process involves embedding queries, retrieving relevant material, and setting up projects with various tools.
More than chat, explore your own data with GraphRAG
Retrieval Augmented Generation (RAG) enhances Large Language Models by providing context through an open-source application using txtai, supporting Vector and Graph RAG, and facilitating easy data integration.
1 commentsRelated
Show HN: R2R V2 – A open source RAG engine with prod features
The R2R GitHub repository offers an open-source RAG answer engine for scalable systems, featuring multimodal support, hybrid search, and a RESTful API. It includes installation guides, a dashboard, and community support. Developers benefit from configurable functionalities and resources for integration. Full documentation is available on the repository for exploration and contribution.
Vercel AI SDK: RAG Guide
Retrieval-augmented generation (RAG) chatbots enhance Large Language Models (LLMs) by accessing external information for accurate responses. The process involves embedding queries, retrieving relevant material, and setting up projects with various tools.
More than chat, explore your own data with GraphRAG
Retrieval Augmented Generation (RAG) enhances Large Language Models by providing context through an open-source application using txtai, supporting Vector and Graph RAG, and facilitating easy data integration.