Opper enables storing information in a vector database for retrieval. Opper manages the chunking of input data, and at the retrieval step performs operations to retrieve the best knowledge chunks as per semantic similarity.

​
Common operations

  • Use create knowledge base to create a new knowledge store to hold informatino
  • Use register file upload to upload files
  • Use add knowledge to upload text documents
  • Use query knowledge to retrieve semantically relevant chunks from the knowledge base.