Jina AI ORG

☁️ Build multimodal AI applications with cloud-native stack

Python framework for turning AI models into production services with built-in scaling, orchestration, and cloud deployment.

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

A Python client-server tool that converts images and text into numerical embeddings using the CLIP model, letting you compare images to text captions and rank which description best matches a photo.

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

An open-source tool that converts any web page, PDF, or Office document into clean markdown by prepending a URL prefix, so AI models can read and reason about real content without noise or login required.

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

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

Set Your Goals, AI Achieves Them.

Official Jina AI Remote MCP Server

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

No description.

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

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

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

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

No description.

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

Input text or image, get back matching image fashion results, using Jina, DocArray, and CLIP

LLM finetuning

Streamlit component for Jina neural search

A collection of GGUF and quantizations for jina-embeddings-v4

Jina VDR is a multilingual, multi-domain benchmark for visual document retrieval

No description.

Jina V1 Official Documentation. For the latest one, please check out https://docs.jina.ai

internal-only

distill chatGPT coding ability into small model (1b)

A production-ready, scalable Indexer for the Jina neural search framework, based on HNSW and PSQL

BIG: Back In the Game of Creative AI

No description.

This is an example of search videos using jina

Meme search engine built with Jina neural search framework. Search with captions or image files to find matching memes.

Identify which embedding model produced a vector using digit-level tokenization and a tiny transformer

An example of building a speech to image generation pipeline with Jina, Whisper and StableDiffusion

An open source implementation of CLIP

Jina Executor used for extracting images and text as chunks from PDF data

App store search example, using Jina as backend and Streamlit as frontend

Golang Client for Jina (https://github.com/jina-ai/jina)

Find out job opportunities at Jina AI

No description.

An executor that wraps 3D mesh models and encodes 3D content documents to d-dimension vector.

Jina Embedding Models on AWS SageMaker

API schema of Jina command line interface exposed as JSON and YAML files.

Benchmark environment and results of different versions of Jina.

LLM inference in C/C++

Simple Indexer

Access Jina AI news via ssh [email protected]

No description.

This repository stores github actions templates as described https://docs.github.com/en/actions/learn-github-actions/sharing-workflows-with-your-organization

No description.

No description.

An example of graph embeddings for wikipedia page recommendations

MTEB: Massive Text Embedding Benchmark

No description.

Encoder that embeds documents using either the CLIP vision encoder or the CLIP text encoder, depending on the content type of the document.

This is an example of building a video QA with jina

No description.

**TransformerTorchEncoder** wraps the torch-version of transformers from huggingface. It encodes text data into dense vectors.

No description.

CLIPImageEncoder is an image encoder that wraps the image embedding functionality using the CLIP

No description.

Issues that don't fit under Jina's other repos!

Heart mosaics of your GitHub contributors

No description.

DPRReaderRanker

Monorepo for JinaJS and frontend projects

极纳 x 百度飞桨 黑客马拉松

Integration test for hub

Support repo for Jina X Hackathon - Sep 2020

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

Jina executor package normalizer

An executor that performs image segmentation on fashion items

No description.

Summarize all Executor patterns for Hubble

An Indexer that works out-of-the-box when you have less than 100K stored Documents

An executor that performs standard pre-processing and normalization on images.

No description.

No description.

Air-gapped deployment toolkit for Jina AI models

No description.

No description.

⚡ Building applications with LLMs through composability ⚡

Encode text into embeddings using the CLIP model.

FeatureHasher

A collection of shared function for Jina Executor

The ImageTorchEncoder encodes Document content from a ndarray to an d-dimensional vector.

MTEB: Massive Text Embedding Benchmark

Python tool for converting files and office documents to Markdown.

No description.

Nov. 7 EMNLP2025 BoF: Embeddings, Rerankers, Small LMs for Better Search

An executor that loads ONNX models and embeds documents using the ONNX runtime.

A similarity search indexer based on Faiss. https://hub.jina.ai/executor/8gsd0tts

Executor wraps the sentence_encoder library and computes sentence embeddings.

**TransformerQAExecutor* wraps a question-answering model from huggingface and return relevant answers given questions and contexts/paragraphs.

A Jina Executor for spelling correction, based on BKTree

A Jina Executor for loading Powerpoint files

No description.

No description.

[CVPR 2025] A Comprehensive Benchmark for Document Parsing and Evaluation

MTEB: Massive Text Embedding Benchmark with Spanish datasets

Additional module to use with 'puppeteer' for setting proxies per page basis.

A high-throughput and memory-efficient inference and serving engine for LLMs

public presentations and infographics in the Jina community.

Wraps the AudioCLIP model for generating embeddings for audio data for the Jina framework

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Jina v2.x Official Documentation. For the latest one, please check out https://docs.jina.ai

some quiz for docarray

Encode text into embeddings using the DPR model.

Storing CI/CD yaml files for Executors

**MatchMerger** Merges the results of shards by appending all matches.

**SimpleRanker** is a class aggregates the score of the matched doc from the matched chunks.

No description.

No description.

No description.

Indexer Executors for Jina

MTEB: Massive Text Embedding Benchmark

No description.

An indexer leverages hnswlib for vector search and DocumentArrayMemmap for storing full Documents

No description.

Legal statements apply to services and products that Jina AI Limited offers.

JCloud terraform modules for AWS

No description.

A production-ready, scalable Indexer for the Jina neural search framework, based on FAISS and PSQL

An executor that wraps trimesh for loading and using triangular meshes

An executor to encode images using comparable hashing techniques. Useful for duplicate detection

No description.

This example demonstrates the use of a convolutional neural network.

No description.

An executor that extract the frames from videos with `ffmpeg`

Find all the examples with changed code and run the docker test in that directory

AudioCLIPTextEncoder - Encodes text using the AudioCLIP model

No description.

No description.

This repo is to test the sync functionality of readme.com

A collection of GGUF and quantizations for jina-embeddings-v4

A place to submit conda recipes before they become fully fledged conda-forge feedstocks

No description.

SQL databases in Python, designed for simplicity, compatibility, and robustness.

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

Typer, build great CLIs. Easy to code. Based on Python type hints.

1.4B latent diffusion model fine tuning

Docker compose file to use prometheus and grafana with Jina

WordLift Documentation

🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.

Pydantic DocsQA integration

Doing dirty (but extremely useful) things with equals.

A similarity search Executor based on Faiss and LMDB

Open Source Differentiable Computer Vision Library

JuiceFS is a distributed POSIX file system built on top of Redis and S3.

No description.

No description.

No description.

No description.

Rich is a Python library for rich text and beautiful formatting in the terminal.

Encode text into embeddings using the drp model.

Jina Official Documentation (staging, until it becomes prod)

TagsHasher

No description.

This executor loads audio files into the Document blobs.

No description.

No description.

No description.

Push the executor to hubble

😎 swag opportunities for developers

This executor splits long texts into sentence chunks.

AudioCLIPImageEncoder - Encodes images using the AudioCLIP model

No description.

Executor that uses pytorch transformer NLP models (e.g. BERT).

No description.

No description.

No description.

No description.

No description.

No description.

No description.

MTEB: Massive Text Embedding Benchmark

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

No description.

samples to evaluate a multimodal neural reranker

A setuptools extension for building cpython extensions written in golang.