Databerry provides a user-friendly solution to quickly setup a semantic search system over your personal data without any technical knowledge.
- Load data from anywhere
- Raw text
- Web page
- Files
- Word
- Excel
- Powerpoint
- Markdown
- Plain Text
- Web Site (coming soon)
- Notion (coming soon)
- Airtable (coming soon)
- No-code: User-friendly interface to manage your datastores and chat with your data
- Securized API endpoint for querying your data
- Auto sync data sources (coming soon)
- Auto generates a ChatGPT Plugin for each datastore
- Vector Datbase: Qdrant
- Embeddigs: Openai's text-embedding-ada-002
- Chunk size: 256 tokens
- Next.js
- Joy UI
- LangchainJS
- PostgreSQL
- Prisma
- Qdrant
Inspired by the ChatGPT Retrieval Plugin.
Minimum requirements to run the projects locally
- Node.js v18
- Postgres Database
- Redis
- Qdrant
- GitHub App (NextAuth)
- Email Provider (NextAuth)
- OpenAI API Key
- AWS S3 Credentials
# Create .env.local
cp .env.example .env.local
# Install dependencies
pnpm install
# Generate DB tables
pnpm prisma:migrate:dev
# Run server
pnpm dev
# Run worker process
pnpm worker:datasource-loader
First cd .dev/databerry
then populate the config files app.env
and docker.env
as needed, then run the compose command:
docker compose --env-file docker.env up
You can fully rebuild dockers with :
docker compose --env-file docker.env up --build