A post-retrieval temporal layer designed to improve RAG systems by addressing time-blindness in vector searches. This library implements validity filtering, document kind classification, and exponential decay scoring to ensure retrieved information is fresh and accurate. It functions downstream of existing vector search systems without requiring re-indexing or new infrastructure.
>"How I added temporal awareness and freshness tracking to a RAG system with no sense of time."
This article discusses how AI tools can be used to enhance the reading experience by providing instant access to information and background details, similar to using a dictionary or Wikipedia, but with the ability to ask more complex questions. The author shares personal examples of using AI while reading 'The Dark Forest' and other books to clarify plot points and gain a better understanding of the material.
This article discusses the importance of knowledge graphs in providing context for AI agents, highlighting their advantages over traditional retrieval systems in terms of precision, reasoning, and explainability.
This article discusses the development of multimodal Retrieval Augmented Generation (RAG) systems which allow for the processing of various file types using AI. The article provides a beginner-friendly guide with example Python code and explains the three levels of multimodal RAG systems.
This article discusses the importance of determining user query intent to enhance search results. It covers how to identify search and answer intents, implement intent detection using language models, and adjust retrieval strategies accordingly.
This page provides documentation for the rerank API, including endpoints, request parameters, and response formats.
Maximize search relevancy and RAG accuracy with Jina Reranker. Features include multilingual retrieval, code search, and a 6x speedup over the previous version.
A post discussing new techniques developed for parsing and searching PDFs, focusing on turning them into a hierarchical structure for RAG search. The approach involves dynamically generating chunks for searches, sending headers and sub-headers to the Language Model along with relevant chunks.
This article provides a step-by-step guide on building a generative search engine for local files using Qdrant, NVidia NIM API, or Llama 3. It includes system design, indexing local files, and creating a user interface.
