Query Expension for Better Query Embedding using LLMs
-
Updated
Feb 18, 2025 - Python
Query Expension for Better Query Embedding using LLMs
Embedding Inversion via Conditional Masked Diffusion: recover original text from embedding vectors using parallel denoising. Live demo + training pipeline + technical report.
Collective AI memory for multi-agent teams. 10-stage GAMR search engine, knowledge graph (Apache AGE), document ingestion, 32+ MCP tools.
The repo provides the code for Qdrant for efficient image indexing and retrieval using models such as ColPali, ColQwen, and VDR-2B-Multi-V1, jina embeddings v4 etc enhancing multimodal search capabilities across various applications.
Self-hosted MCP server for hybrid semantic code search and repository intelligence.
Semantic code-search (semcode) MCP. Indexes code symbols and commit history. Combines dense embeddings with sparse BM25 vectors for hybrid search that balances semantic understanding with keyword precision.
A Model Context Protocol (MCP) server that provides semantic search over AWS Cloudscape Design System documentation.
🛠 Reconstruct original text from text embeddings using conditional masked diffusion to reveal reversible embedding representations efficiently and accurately
Oh My Repos: Semantic search for GitHub starred repositories.
End-to-End Python implementation of Beck et al.'s (2025) economic sentiment analysis framework for constructing a high-frequency economic sentiment indicator using 1024-dimensional Jina embeddings and LLM-generated training data. Features L2-regularized classification and rigorous POOS econometric validation with DM-HAC tests for GDP forecasting.
Intelligent arXiv paper discovery engine with hybrid BM25+vector search and agentic RAG: fetch, index, and interrogate AI research papers using a lightweight state-machine pipeline, OpenSearch, and local LLMs.
A production-grade Agentic RAG system for analyzing scientific literature. Built on LangGraph for stateful orchestration, featuring unified BM25 + Jina vector search via OpenSearch, Docling layout-aware PDF parsing, Upstash Redis caching, and OpenRouter LLM generation.
🌐 Enable seamless semantic search over AWS Cloudscape documentation for AI agents and coding assistants with this efficient MCP server.
Multi-model ML system for Twitter engagement prediction & content generation using embeddings, ensemble learning & LLMs
A real-time news chatbot application built with modern web technologies. It delivers intelligent, AI-powered responses, supports multiple chat sessions with persistent history, and provides a responsive, user-friendly interface across devices.
Serve Jina Embeddings v4 multi-vector (ColBERT-style) multimodal text+image embeddings from a stock vLLM OpenAI server via an out-of-tree plugin, with configurable image fidelity.
Self-hosted server for jinaai/jina-embeddings-v4 compatible with OpenAI's embeddings format.
Backend for a RAG-powered news chatbot providing real-time AI responses, semantic search, and news retrieval using Node.js, Socket.IO, PostgreSQL, Redis, and Qdrant.
Sec2ndBrain transforms your digital life into a chat-ready RAG knowledge base. Powered by Groq and Jina AI, you can instantly talk to your saved notes, YouTube videos, and Tweets.
Add a description, image, and links to the jina-embeddings topic page so that developers can more easily learn about it.
To associate your repository with the jina-embeddings topic, visit your repo's landing page and select "manage topics."