multimodal-search

The codebase for the book "AI-Powered Search" (Manning Publications, 2025) and associated "AI-Powered Search: Modern Retrieval for Humans & Agents" Maven course

LitePali is a minimal, efficient implementation of ColPali for image retrieval and indexing, optimized for cloud deployment.

Knowledge pills on Neural Search

An Effective and Scalable Framework for Multimodal Search of Target Modality

3D Medical Image Retrieval in Radiology

PostgreSQL-native semantic search engine with multi-modal capabilities. Add AI-powered search to your existing database without separate vector databases, vendor fees, or complex setup. Features text + image search using CLIP embeddings, native SQL joins, and 10-minute Docker deployment.

Collections of multimodal search libraries, service and research papers

Genomics Visualization Retrieval for Authoring with Multimodality

本地嵌入式多模态混合检索：COS + 豆包 Embedding + BM25 + zvec/SQLite，无需单独部署数据库。

Multimodal saree search app built using Amazon Titan Multimodal Embeddings model

Local multimodal RAG for PDFs: MinerU, Jina CLIP, FAISS, BM25, BGE reranking and Ollama. Runs on your hardware via CLI, web and desktop.

OpenAI-compatible multimodal embedding server for Qwen3-VL-Embedding-2B — embed text, images, or both via a simple REST API.

Leverage vector databases to swiftly construct a diverse range of applications through "Building Applications with Vector Databases" course!

An Effective and Scalable Framework for Multimodal Search with Target Modality

Personal search for technical screenshots and notes. Hybrid vector and full-text retrieval on Amazon EKS, with Firn and S3 as the storage and index layer, and GPU capacity that scales to zero.

Low-Latency Multimodal Search Web App with MCP Architecture 🔌🛠️🧠 #StrandsAgentSDK #FasterWhisper #Multilingual #MultimodalSearch #ChromaDB # DockerCompose

Smart search engine for Habr articles with Elasticsearch, ML reranking, LLM-based relevance labeling, and AI tag prediction

A powerful multimodal document search engine that converts PDF documents into searchable vector embeddings using OpenAI's CLIP model. Enables cross-modal search across text and images with natural language queries through a modern Streamlit interface.

Local-first multimodal Graph RAG with Qwen3-VL embeddings, Neo4j vector search, and a lightweight visual retrieval console.

Multi-Modal Search over fashion datasets. Information Retrieval Tasks optimised using Spotify's Annoy, using text embeddings over captions and words generated from image via classifiers. Experimentation and Optimisation of hyper-parameters