Indegen AI Retrieval Engine using RAG.
- 🤖Welcome to IndegenAI – your intelligent agent for retrieval-augmented conversations. Ask anything from uploaded content or the broader world.
- 📄Upload PDFs, DOCX, or plain text files. The bot will index and retrieve answers directly from your content.
- 🌐It also responds to general knowledge or external-world queries using its built-in language model capabilities.
- 🧠Built with a memory layer, so it can hold context over multiple turns, allowing deeper and more natural conversations.
- ☁️Runs on a fully serverless architecture for scalable, low-latency performance—no infrastructure management required.
- 🛠️Powered by LangChain.js + vector search + the Vercel AI SDK in a Next.js environment.
- 🔍Uses a vector store retriever (e.g., Supabase, Pinecone) to provide semantic, context-aware responses from your documents.
- 📥Go ahead, upload a file and start exploring insights — one question at a time.