Power AI apps on your enterprise data
Transform unstructured data into intelligence
Run ETL on unstructured data to create your knowledge warehouse. Much like daily ETL data pipelines move structured data into data warehouses, Prophecy enables the development of data pipelines that transport private, unstructured data into a vector database or OpenSearch/Elastic. This pipeline makes your data ready for analytics and keeps it up-to-date.
- Source components for reading documents from multiple origins like databases and application APIs
- Unstructured data transformations breaking your data into single-topic text articles
- Support for multiple large language model (LLM) vendors, aiding in vector generation and document lookup
- Vector database storage capability for any document along with necessary vectors
- At-scale execution on Apache Spark and orchestration capabilities for automated data pipeline execution
