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 project provides an LLM Websearch Agent using a local SearXNG server for search functionality and includes Python scripts and a bash script for interacting with an LLM to summarize search results.
A tool to download, transcribe, summarize, and chat with media files like videos, audio, documents, web articles, and books, all locally and automated.
A small API that downloads and exposes access to NeuML's txtai-wikipedia and full wikipedia datasets, allowing for offline access and search functionality.
This article explores NDCG — Normalized Discounted Cumulative Gain, a rank-aware metric for evaluating recommendation system models.
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 pull request adds initial support for reranking to libllama, llama-embeddings, and llama-server using two models: BAAI/bge-reranker-v2-m3 and jinaai/jina-reranker-v1-tiny-en. The reranking is implemented as a classification head added to the model graph. Testing and benchmarking were performed with server integration.
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 web search extension for Oobabooga's text-generation-webui (now with nougat) that allows for web search integration with the AI.
