Fine-tuning of Large Language Models allows customizations of AI models for specific tasks and data. While Fine-tuning used to require a lot of compute, technologies like InstructLab, QLoRA and lam...
watsonx Platform Demos
watsonx is IBM’s AI & data platform that’s built for business. It supports the complete AI lifecycle including Large Language Models, developer tools, governance and more. This post describes a...
Deploying Docling on watsonx.ai
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 ...
Agentic Templates for watsonx.ai
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...
Deploying Custom Images in watsonx.ai
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 ...
Resource Specifications for Custom Code in watsonx.ai
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...
Unstructured Data Preparation for Generative AI
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...
Why Agents and Agentic Systems can fail
At the ChatBot Summit in Berlin I gave a talk ‘How to understand why Agents fail’. Below is a transcript and the slides. As you all know there is a lot of innovation and buzz around agents and age...
Evolving Standards for agentic Systems: MCP and ACP
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: Vision-Language Model for Document Conversion
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 ...