Skip to content

First release of generative search functionality

Latest
Latest
Compare
Choose a tag to compare
@nikolamilosevic86 nikolamilosevic86 released this 22 Nov 10:03
· 10 commits to main since this release
2024_11_22_01
cf273bd

Release story

This is the first release where VerifAI is modified in a way that can be used on local files and can be deployed as an Enterprise Search Engine or as a Productivity Engine.

Main features:

  • Easy installation by running a single script
  • Easy indexing of local files in PDF, PPTX, DOCX, MD and TXT formats
  • Combination of lexical and semantic search to find the most relevant documents
  • Usage of any HuggingFace listed model for document embeddings
  • Usage of any LLM that follows OpenAI API standard (deployed using vLLM, Nvidia NIM, Ollama, or via commercial APIs, such as OpenAI, Azure)
  • Supports large amounts of indexed documents (tested with over 200GB of data and 30 million documents)
  • Shows the closest sentence in the document to the generated claim
  • User registration and log-in
  • Pleasent user interface developed in React.js
  • Verification that generated text does not contain hallucinations by a specially fine-tuned model
Assets 2
Loading