jina-ai

☁️ Build multimodal AI applications with cloud-native stack

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)

🪩 Create Disco Diffusion artworks in one line

🌊 A Human-in-the-Loop workflow for creating HD images from text

Your Virtual Development Team

⚡ Langchain apps in production using Jina & FastAPI

Agent techniques to augment your LLM and push it beyong its limits

Task-oriented embedding tuning for BERT, CLIP, etc.

Official Jina AI Remote MCP Server

Set Your Goals, AI Achieves Them.

A Python vector database you just need - no more, no less.

Chain together LLMs for reasoning & orchestrate multiple large models for accomplishing complex tasks

Code for explaining and evaluating late chunking (chunked pooling)

Jina examples and demos to help you get started

Simple UI for debugging correlations of text embeddings

Simplify deploying and managing Jina projects on Jina Cloud

Semantic grep powered by Jina embeddings v5 (MLX on Apple Silicon)

⚡ A fast embedded library for approximate nearest neighbor search

A lightweight, customizable omnibox in Javascript, for use with a Jina backend.

Train embedding and reranker models for retrieval tasks on Apple Silicon with MLX

For LLMs to better code with Jina API

All Jina AI APIs as Unix CLI commands. Search, read, embed, rerank - with pipes.

An open-source cloud-native of large multi-modal models (LMMs) serving framework.

FastAPI to the Cloud, Batteries Included! ☁️🔋🚀

Jina DeepSearch UI

Interactive UI for analyzing Jina logs, designing Flows and viewing Hub images

An open-registry for hosting Jina executors via container images

Compression for unit-norm embedding vectors using spherical coordinates

Submodular optimization for context engineering: query fan-out, text selection, passage reranking

Query Expension for Better Query Embedding using LLMs

LLM-as-SERP

Create and host retrieval plugins for ChatGPT in one click

Google Summer of Code

Embedding Inversion via Conditional Masked Diffusion: recover original text from embedding vectors using parallel denoising. Live demo + training pipeline + technical report.