Databerry provides a user-friendly solution to quickly setup a semantic search system over your personal data without any technical knowledge. Load data from various sources such as raw text, web page, files like Word, Excel, Powerpoint, PDF, Markdown or Plain Text. There is also the option to load data from web sites, Notion, and Airtable. The platform offers a no-code interface to manage your data stores and to chat with your data. Users have access to a secured API endpoint for querying their data and the system supports automatic syncing of data sources. Additionally, the platform auto generates a ChatGPT plugin for each datastore. Databerry leverages Vector Database Qdrant, Embeddings from OpenAI’s text-embedding-ada-002, Next.js, Joy UI, LangchainJS, PostgreSQL, and Prisma. Their Semantic Search Specs includes a Vector Datbase: Qdrant, Embeddings: Openais text-embedding-ada-002 and a Chunk size: 256 tokens. Databerry is inspired by the ChatGPT Retrieval Plugin by OpenAI.
