Techniques and Tools for Generative AI

Large Language Models (LLMs) are powerful but have inherent limitations in areas like real-time data access, mathematical computations, and specialized domain knowledge. To overcome these constraints, you can use certain tools and techniques to extend LLM capabilities through external functions, structured workflows, and integrations with other systems.

This section explores key approaches for enhancing LLM performance, from basic tool integration to complex agentic behaviors, enabling more accessible and even more powerful AI applications.

Agents

LLM Mesh agentic applications

This tutorial series demonstrates how to build agentic applications using the LLM Mesh in Dataiku.

Langchain agents

In addition, you could also build agents in Dataiku using the Langchain framework. Langchain enhances LLM capabilities by integrating planning, memory, and tools modules. This allows LLMs to perform more complex tasks like accessing databases or interfacing with other software.

You can find the tutorial here.

Prompt

Auto Prompt Strategies with DSPy

This tutorial demonstrates the usage of an auto-prompting library and its usage.