Docker introduced a brand new GenAI Stack in partnership with Neo4j, LangChain, and Ollama throughout its annual DockerCon developer convention keynote. This GenAI Stack is designed to assist builders shortly and simply construct generative AI functions with out trying to find and configuring numerous applied sciences.
It consists of pre-configured elements like massive language fashions (LLMs) from Ollama, vector and graph databases from Neo4j, and the LangChain framework. Docker additionally launched its first AI-powered product, Docker AI.
The GenAI Stack addresses in style use instances for generative AI and is out there within the Docker Studying Middle and on GitHub. It gives pre-configured open-source LLMs, help from Ollama for establishing LLMs, Neo4j because the default database for improved AI/ML mannequin efficiency, data graphs to boost GenAI predictions, LangChain orchestration for context-aware reasoning functions, and numerous supporting instruments and assets. This initiative goals to empower builders to leverage AI/ML capabilities of their functions effectively and securely.
“Builders are excited by the chances of GenAI, however the price of change, variety of distributors, and vast variation in expertise stacks makes it difficult to know the place and find out how to begin,” stated Scott Johnston, CEO of Docker CEO Scott Johnston. “Right this moment’s announcement eliminates this dilemma by enabling builders to get began shortly and safely utilizing the Docker instruments, content material, and providers they already know and love along with associate applied sciences on the slicing fringe of GenAI app improvement.”
Builders are supplied with straightforward setup choices that provide numerous capabilities, together with easy information loading and vector index creation. This enables builders to import information, create vector indices, add questions and solutions, and retailer them inside the vector index.
This setup allows enhanced querying, consequence enrichment, and the creation of versatile data graphs. Builders can generate various responses in several codecs, akin to bulleted lists, chain of thought, GitHub points, PDFs, poems, and extra. Moreover, builders can evaluate outcomes achieved between completely different configurations, together with LLMs on their very own, LLMs with vectors, and LLMs with vector and data graph integration.
