watsonx Assistant and watsonx Orchestrate can access Large Language Models from watsonx.ai to build conversational experiences utilizing Generative AI capabilities via state-of-the-art models from ...

Agents are the next step in the evolution of AI. Via tools AI agents can not only generate text, but invoke business logic and access real time data. Sophisticated tasks can be solved by multiple a...

watsonx Orchestrate supports multi-turn conversations as beta. This post shows an example how this new functionality works. Multi-turn conversations are useful in RAG scenarios (Retrieval Augmente...

InstructLab is an open-source framework to fine-tune smaller generative AI models via a new alignment technique. Models can be fine-tuned with relative little real data. This post describe how Inst...

The OpenAI API can be considered as de-facto standard for accessing Large Language Models for generations. This post describes how to run a proxy which accepts OpenAI API requests to run models on ...

watsonx.governance is IBM’s governance offering to manage and monitor (Generative) AI solutions. This post demonstrates how to monitor metrics for models that are not provided by watsonx.ai but hos...

Watsonx.ai is IBM’s AI platform built for business. It is provided as SaaS and as software which can be deployed on multiple clouds and on-premises. This post describes how to deploy custom models ...

watsonx.governance is IBM’s AI governance offering to manage and monitor (Generative) AI solutions. It is available as SaaS or as software to be run everywhere. This post demonstrates how to do thi...

LLM Agents and Function Calling are powerful techniques to build modern AI applications. IBM Research open sourced the Bee Agent Framework. This post describes how custom tools can be developed in ...

watsonx.governance is IBM’s AI governance offering to manage and monitor (Generative) AI solutions. It is available as SaaS or as software to be run everywhere. This post demonstrates how to do thi...