Docling is a popular open-source project contributed by IBM. It supports easy and fast parsing of PDFs and several other file types including images. Docling can be run via containers and deployed ...

Custom Python code for agentic applications can be deployed on watsonx.ai so that various agentic applications can be managed consistently and accessed securely. There are templates to help develop...

Agentic applications, model inference stacks and other Python based code can be deployed on watsonx.ai. For maximal flexibility custom images can be built and deployed to watsonx.ai which is based ...

Custom Python code can be deployed on IBM watsonx.ai via Python Functions and AI Services. This post describes how resources like memory can be defined for custom execution environments. watsonx.a...

IBM has open-sourced another great tool for Generative AI engineers and developers. With the Data Prep Kit data can be prepared for Fine-tuning and Retrieval Augmented Generation. Data Prep Kit is...

Agentic systems leverage multiple agents and multiple tools. These agents and tools can be developed and hosted by different providers. To allow inter-agent communication and to access different da...

SmolDocling is an ultra-compact, open-source Vision Language Model for document conversion including OCR. This post summarizes the key features and demonstrates how to get started. SmolDocling is ...

My colleague Thomas Harrer interviewed me about agentic systems and fine-tuning. Below is the recording and the transcript. Watch Let’s Create Technology Talk with Niklas Heidloff about Artificial...

Watsonx.ai provides various Large Language Models and Embedding Models out of the box. Models that are not supported by the watsonx.ai inference stack can be deployed via Python Functions. Watsonx...

Recently watsonx Orchestrate has added support for agentic capabilities. Orchestration agents can route to assistants, skills and agents. This post focusses on the routing to agents and their tools...