A premium vector database capability within the DataRobot Generative AI platform that stores chunked unstructured text and their embeddings for retrieval-augmented generation (RAG). Users can create vector database objects, connect supported data sources from the DataRobot Data Registry, configure embeddings and chunking, and attach these vector databases to LLM blueprints in the playground to ground model responses in proprietary data.
DataRobot Vector Databases (GenAI) is a premium capability within the DataRobot Generative AI platform for storing chunked unstructured text and their embeddings to support retrieval-augmented generation (RAG). It lets users ground large language model (LLM) responses in their own proprietary data by connecting data sources, configuring embeddings and chunking, and attaching vector databases to LLM blueprints.
Vector database objects
Data source integration
Embeddings configuration
Chunking configuration
RAG integration with LLMs
Playground / blueprint workflow
datarobot-vector-databases-genaimanaged-vector-databasesrag, vector-store, enterpriseLoading more......
