Jina is an open-source cloud-native project deep-learning powered search framework in Python, empowering developers to create cross-modal or multi-modal search systems for text, images, video, and audio.
Features:
- Time Saver - Bootstrap an AI-powered system in just a few minutes with cookiecutter.
- First-Class AI models - Jina is a new design pattern for neural search systems with first-class support for state-of-the-art AI models like Faiss, Annoy, Onnx, and more.
- Universal Search - Large-scale indexing and querying data of any kind on multiple platforms. Video, image, long/short text, music, source code, and more.
- Production Ready - Cloud-native features out-of-the-box, like containerization, microservice, distributing, scaling, sharding, python async IO, REST, gRPC.
- Plug & Play - With Jina Hub, you can extend Jina with simple Python scripts or Docker images optimized for your search domain.
Agenda:
Introduction to Jina - [2 min]
Core Jina concepts: Pythonic Flow, Pods in Jina, Jina Executors for Deep Learning models using Python - [6 min]
Jina Demo: Demo of neural search use cases like [5 min]
Multi modal search
Cross modal Search
Visual Semantic Search
Query Language Driver for filtering during search
Advanced Jina Concepts: [10 min]
Recursive Document Structure and Traversal
Compound Indexing with Key Value and Vector indexers
Text document segmentation
Depth levels
Q and A: [7 min]
Open forum for the audience to interact with the speaker