Neosearch

AI-based search engine done right.

Chatbot will understand your query and provide you suitable results by using various tools (code generation, weather search, etc).

Features

You could maximize or run the generated code in the code view.

Also, we support aisearch, which uses external search engines to provide you with the best results.

Neosearch supports real-time search with citation.

The LLM chatbot suggests the next question candidates for the user.

ToDo

• Finish implementing AISearch view
  • Make AISearch view to support tavily
  • Make AISearch view to support searxng
• Compare trafilatura bs4 and newspaper3k
• Implement the bulk indexer
• Implement the batch system for spider
  • Implement the spider with Trafilatura
    • Parse title, body, and metadata from HTML
    • Parse title, body, and metadata from PDF, etc
• Implement the dispatcher
  • Implement dispatcher for linkedin
  • Implement dispatcher for GitHub
  • Implement dispatcher for Medium
  • Implement dispatcher for Wikipedia
  • Implement dispatcher for namuwiki
• Implement the Hybrid Search retriever
  • Implement the ParadeDB retriever with LlamaIndex
  • Add support for caching layer for the retriever
• Update Rag Retriever to use the searxng engine
• Implement the CRAG workflow for the Rag Retriever
  • Add support for CRAG API that runs the CRAG workflow with user's query
• Implement the reranker
  • Add support for Cohere Reranker
  • Add support for FlashRank Reranker
• Add support for late-chunking for better IR