
Hybrid database for your regular data and your embeddings
Why would we need this?
In most applications, LLMs need to be connected to an ever changing set of data. Itโs simple enough to parse and embed a few PDFโs. However, managing this data is tedious when youโre working with large, multimodal datasets that consistently need to be updated, re-indexed, and replaced. Plus youโre likely managing multiple databases - one for vectors, and one for your other data. This gets painful really fast.Key Features:
- A flexible hybrid database. A single dataset in Baseplate can contain
- Embeddings
- Text
- Code
- Documents
- Images
- Links
- Database management
- Sync datasets with your tools (Google Drive, S3, Box, Sharepoint, etc.)
- Utilities for updating and managing vectors in bulk
- Organize and segment your data intuitively
- Work in the UI or programmatically via API
- Smart Search
- Choose an embedding model for your use case, tailored for your documents
- Multi-step Search. Retrieve context from multiple datasets within an app.
- Use keyword, semantic, or hybrid search
- Retreive whole documents or just relevant chunks
- App Builder
- Choose between a number of popular LLMs
- Build a custom prompt for your use case
- Test and deploy your app without any code
- Endpoints
- One-click Slackbots, Discord Bots, Teams Bots, and more!
- Build, test, and deploy your Apps via API endpoints
- Unlimited queries
- Built-in utilities for human feedback, logging, & caching