Choosing the Smallest LLM That Won’t Completely Fail You en

Bigger isn’t always better, especially when it comes to running language models locally. In this session, we’ll explore how to evaluate and benchmark Small Language Models (SLMs) using Go, Docker, and Testcontainers.

You’ll learn how to build a framework in Go that leverages Docker's Model Runner as inference engine to automatically spin up SLMs, run controlled evaluation scenarios, and collect observability metrics. We’ll define an Evaluator Agent that executes a battery of standard prompts across multiple models, an approach that helps you understand performance, accuracy, and resource trade-offs in practical developer setups.

We’ll move from building a reusable evaluation harness to defining and orchestrating prompts as tests for different models. You’ll see how to instrument Go benchmarks with metrics and traces to visualize behavior instantly and make informed decisions. And of course, you’ll walk away with practical insights on selecting the smallest model that won’t fail you.

By the end, you’ll have a repeatable approach for testing and comparing language models.

Warm up your GPUs, but less than you think.

Testing GenAI applications in Go en

The evolution of GenAI applications brings with it the challenge of developing testing methods that can effectively evaluate the complexity and subtlety of responses generated by advanced artificial intelligences.

The proposal to use an LLM as a Validator Agent represents a promising approach, paving the way towards a new era of software development and evaluation in the field of artificial intelligence. Over time, we hope to see more innovations that allow us to overcome the current challenges and maximize the potential of these transformative technologies.

This proposal involves defining detailed validation criteria and using an LLM as an “Evaluator” to determine if the responses meet the specified requirements. This approach can be applied to validate answers to specific questions, drawing on both general knowledge and especialised information. By incorporating detailed instructions and examples, an Evaluator can provide accurate and justified evaluations, offering clarity on why a response is considered correct or incorrect.

In this session we’ll leverage langchaingo to interact with LLMs, and Testcontainers Go to provision the runtime dependencies to use RAG.

Accepted in Gophercon SG 2025

Delightful integration tests in Go applications en es

Dockerized services are an excellent tool for creating repeatable, isolated environments ideal for integration tests. In this session, we’ll look at the Testcontainers libraries which provide flexible and intuitive API for programmatically controlling lifecycle of your service dependencies in Docker containers.

Running databases, Kafka, Elasticsearch, and even cloud technologies, straight from your test code ensures environment config is always up-to-date and consistent during local development and in CI pipelines.

You’ll learn everything necessary to start adding powerful integration tests to your codebase without the headache of managing external service dependencies manually!

Preferred session duration: 30-45 mins
Target audience: Introductory and Overview

Deliciosos tests de integración en aplicaciones Go en es

Los servicios en contenedores Docker son una excelente herramienta para crear entornos repetibles y aislados ideales para pruebas de integración. En esta sesión, veremos la librería Testcontainers para Go, que ofrece un API flexible e intuitiva para controlar programáticamente el ciclo de vida de las dependencias de tus servicios en contenedores Docker en tu lenguaje de programación favorito: Go.

Ejecutar bases de datos, Kafka, Elasticsearch e incluso tecnologías en la nube directamente desde tu código de test asegura que la configuración del entorno esté siempre actualizada y sea consistente durante el desarrollo local y en los flujos de trabajo de integración continua (CI).

Aprenderás todo lo necesario para comenzar a añadir pruebas de integración potentes a tu código sin la molestia de gestionar manualmente las dependencias de servicios externos.

Duración preferida: 30-45 mins
Audiencia: Introducción