Large language models (LLMs)

Models that can understand and generate natural language

LLMs are a class of foundation models that are designed to understand and generate text (and other forms of content) like a human, based on the vast amount of data used to train them.

02 February 2026

Tutorial

Build a GraphRAG agent using watsonx Orchestrate and DataStax Astra db

Learn how to build a high‑accuracy GraphRAG agent using watsonx Orchestrate, watsonx.ai embeddings, and DataStax Astra db with this hands‑on developer tutorial that covers vector search, knowledge graphs, web crawling, semantic retrieval, and agentic AI workflows.

29 January 2026

Article

From prompt engineering to fine‑tuning: Transforming document validation

Learn how fine‑tuning a small language model (Mistral 7B) and using a Granite 3.3 8B orchestrator solves the consistency challenges of large‑scale business document evaluation.

12 January 2026

Tutorial

Build an AI-powered customer care assistant with IBM Sterling OMS and n8n

Build an AI-powered customer care assistant using IBM Sterling OMS, n8n, and Large Language Models to automate order tracking, enable real-time order status, improve omnichannel customer support, and modernize enterprise order management with agentic AI workflows and OMS APIs.

19 December 2025

Tutorial

Integrate crewAI multi-agent framework into IBM watsonx Orchestrate

Deploy crewAI microservice on IBM Code Engine and integrate with watsonx Orchestrate for custom AI logic, multi-agent workflows, and automation.

15 December 2025

Tutorial

Developing a voice-first, multi-domain AI assistant using watsonx Orchestrate and Apple Siri

Create intelligent RAG pipelines using Siri shortcuts and watsonx Orchestrate. Upload PDFs, generate API keys, and test queries in minutes.

11 December 2025

Tutorial

Automate ESG reporting with watsonx Orchestrate and Envizi

Automate ESG reporting by integrating watsonx Orchestrate with Envizi to retrieve, process, and deliver sustainability data, insights, and compliance metrics efficiently.

31 October 2025

Article

JSON prompting for LLMs

Discover universal JSON prompt templates for extraction, generation, and analysis, plus best‑practice automation and error‑handling techniques for production‑grade AI pipelines.

29 October 2025

Tutorial

Build a local AI co-pilot using IBM Granite 4, Ollama, and Continue

In this tutorial, learn how to set up a local AI co-pilot in Visual Studio Code using IBM Granite 4, Ollama, and Continue, overcoming common enterprise challenges such as data privacy, licensing, and cost. The setup includes open-source LLMs, Ollama for model serving, and Continue for in-editor AI assistance.

15 October 2025

Tutorial

Create your first generative AI Java application with Quarkus and LangChain4j

In this tutorial, learn how to build a Java and Quarkus REST API that uses LangChain4j to call an LLM and generate custom poems on any topic.

24 September 2025

Article

Evaluating generic phrases using Granite models

In this article, we demonstrate using different prompts with different contexts to analyze how LLMs behave when asked generic-related questions. We show how the Granite 3.3-2b model is good at identifying associated quantifiers in generic phrases and the model's responses are context-driven too.

17 September 2025

Tutorial

Extend Your AI Agents with External LLMs Using watsonx Orchestrate and AI Gateway

Learn how to use external LLMs with watsonx Orchestrate AI Gateway, which allows for more flexibility and choice in building AI-powered agents.

08 September 2025

Tutorial

AgentOps in watsonx Orchestrate: Observability for Agents with Langfuse and IBM Telemetry

Learn AgentOps in watsonx Orchestrate with IBM Telemetry and Langfuse for AI observability, agent monitoring, debugging, and performance optimization.

Items per page:

1–12 of 126 items

of 11 pages

Topics

Languages

Products

Open Source

Large language models (LLMs)

Models that can understand and generate natural language

Build a GraphRAG agent using watsonx Orchestrate and DataStax Astra db

From prompt engineering to fine‑tuning: Transforming document validation

Build an AI-powered customer care assistant with IBM Sterling OMS and n8n

Integrate crewAI multi-agent framework into IBM watsonx Orchestrate

Developing a voice-first, multi-domain AI assistant using watsonx Orchestrate and Apple Siri

Automate ESG reporting with watsonx Orchestrate and Envizi

JSON prompting for LLMs

Build a local AI co-pilot using IBM Granite 4, Ollama, and Continue

Create your first generative AI Java application with Quarkus and LangChain4j

Evaluating generic phrases using Granite models

Extend Your AI Agents with External LLMs Using watsonx Orchestrate and AI Gateway

AgentOps in watsonx Orchestrate: Observability for Agents with Langfuse and IBM Telemetry