Tech Blog Distilled AI: Using Large Models to Teach Smaller Ones Better AI with smaller models and cheaper data costs! But only if you use AI to train AI.
Tech Blog Fine-Tuning Falcon40b for Code Generation Falcon40b is an open-source commercial-use friendly large language model. We've trained it to write code.
Tech Blog Cross-modal search with ImageBind and DocArray Combine ImageBind with DocArray to implement a cross-modal search system
Tech Blog AgentChain: Chain together models to perform complex tasks AgentChain uses LLMs for planning and orchestrating multiple Agents or Large Models for accomplishing sophisticated tasks. AgentChain is fully multimodal: it accepts text, image, audio, tabular data
Tech Blog Multimodal Visual Question Answering with BLIP-2 and Jina LLMs aren't great for working with anything beyond text. But now you can serve BLIP-2 with Jina and DocArray, enhancing LLMs with visual understanding
Tech Blog How to Deploy a Deep Learning Model with Jina (and design a kitten along the way) How to build and deploy an Executor that uses Stable Diffusion to generate images.
Knowledge Base How to Use Every Vector Database in Python with DocArray DocArray handles multimodal data and works with every vector database using a universal API. Here's how you can do it in Python.
Tech Blog Real-Time Product Recommendation via DocArray and Redis By using Redis backend inside DocArray, building a real-time product recommendation system via vector similarity search is easy and straightforward. Follow along to learn the essential steps and how it works.