Ollama is a fast, open-source, and lightweight model server for running large language models (LLMs) on commodity hardware.

With HoneyHive, you can trace all your operations using a single line of code. Find a list of all supported integrations here.

​
HoneyHive Setup

Follow the HoneyHive Installation Guide to get your API key and initialize the tracer.

​
Ollama Setup

Go to Ollama Quickstart to get your Ollama model up and running locally using ollama run llama3.2:1b for example.

Note: please use version ollama==0.2.0 for Python.

​
Example

Here is an example of how to trace your code in HoneyHive.

import ollama
from honeyhive import HoneyHiveTracer

HoneyHiveTracer.init(
    api_key="MY_HONEYHIVE_API_KEY",
    project="MY_HONEYHIVE_PROJECT_NAME",
    session_name="ollama",
)


response = ollama.chat(
    model="llama3.2:1b",
    messages=[{"role": "user", "content": "Why is the sky blue? Respond in one sentence."}],
    options={"temperature": 1},
)

print(response["message"]["content"])

​
View your Traces

Once you run your code, you can view your execution trace in the HoneyHive UI by clicking the Data Store tab on the left sidebar.