Ollama

​

Setup

pnpm add braintrust ollama

npm install braintrust ollama

BRAINTRUST_API_KEY=<your-braintrust-api-key>

# For organizations on the EU data plane, use https://api-eu.braintrust.dev
# For self-hosted deployments, use your data plane URL
# BRAINTRUST_API_URL=<your-braintrust-api-url-here>

​

Auto-instrumentation

import { initLogger } from "braintrust";
import { Ollama } from "ollama";

initLogger({
  projectName: "My Project",
  apiKey: process.env.BRAINTRUST_API_KEY,
});

const ollama = new Ollama();

const response = await ollama.chat({
  model: "llama3.2",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(response.message.content);

node --import braintrust/hook.mjs trace-ollama-auto.js

​

Manual instrumentation

import { initLogger, wrapOllama } from "braintrust";
import { Ollama } from "ollama";

initLogger({
  projectName: "My Project",
  apiKey: process.env.BRAINTRUST_API_KEY,
});

const ollama = wrapOllama(new Ollama());

const response = await ollama.chat({
  model: "llama3.2",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(response.message.content);

​

What Braintrust traces

• Chat spans (ollama.chat), with messages and request parameters as input and the response message as output. Tool calls are normalized to the OpenAI function-call format.
• Generate spans (ollama.generate), with the prompt (plus optional system prompt and images) as input and the generated text as output. Thinking content is captured as reasoning.
• Embedding spans (ollama.embed), with the input text as input and the first embedding’s vector length as output.
• Token usage metrics (prompt_tokens and completion_tokens) from Ollama’s prompt_eval_count and eval_count response fields.
• Model name and request options (temperature, top_p, max_tokens, and others) as span metadata.
• Image inputs are captured as attachments.
• Errors captured on every span.

​

Resources

• ollama on npm
• Ollama documentation
• Braintrust JavaScript SDK