Maxim Logo
How to/Log your application

Log multi-turn interactions as a session

Learn how to group related traces into sessions to track complete user interactions with your GenAI system.

Sessions are particularly useful for tracking multi-turn conversations or complex workflows that span multiple API calls or user interactions. Maintain context across multiple traces, analyze user behavior, and debug multi-interaction issues with sessions. Track the full lifecycle of user engagement by organizing traces into sessions.

Create a new session

const session = logger.session({
    id: "session-id",
    name: "session-name",
});

Add a trace to the session

After creating a session object, you can add multiple traces across the lifecycle of the conversation.

const trace = session.trace({
    id: "trace-id",
    name: "trace-name",
});

Linking traces using session IDs

const trace = logger.trace({
    id: "trace-id",
    name: "trace-name",
    sessionId: "session-id",
});

Capture your RAG pipeline

Retrieval-Augmented Generation (RAG) is a technique that enhances large language models by retrieving relevant information from external sources before generating responses.

Track tool calls

Track external system calls triggered by LLM responses in your agentic workflows. Tool calls represent interactions with external services, allowing you to monitor execution time and responses.

On this page