Databerry provides a user-friendly solution to quickly setup a semantic search system over your personal data without any technical knowledge. With features like loading data from anywhere including raw text, web pages, files like Word, Excel, Powerpoint, PDF, Markdown and Plain text, databerry comes with a stack of technologies like Next.js, Joy UI, LangchainJS, PostgreSQL, Prisma, Qdrant for seamless operation. It also comes with Auto sync data sources (coming soon), and Auto generates a ChatGPT Plugin for each datastore. Databerry uses Vector Database: Qdrant and Embeddigs: Openais text-embedding-ada-002 with Chunk size: 256 tokens for seamless operation. The project can be run locally with minimum requirements which include Node.js v18, Postgres Database, Redis, Qdrant, GitHub App (NextAuth), Email Provider (NextAuth), OpenAI API Key and AWS S3 Credentials.
