> ## Documentation Index
> Fetch the complete documentation index at: https://docs-v1.latitude.so/llms.txt
> Use this file to discover all available pages before exploring further.

# Ollama

> Connect your Ollama-powered application to Latitude Telemetry for feature-level observability and evaluations.

<Note>
  This integration is only available in the **Python SDK**.
</Note>

## Overview

This guide shows you how to integrate **Latitude Telemetry** into an existing application that uses the official **Ollama SDK**.

After completing these steps:

* Every Ollama call (e.g. `chat`, `generate`) can be captured as a log in Latitude.
* Logs are grouped under a **prompt**, identified by a `path`, inside a Latitude **project**.
* You can inspect inputs/outputs, measure latency, and debug Ollama-powered features from the Latitude dashboard.

<Check>
  You'll keep calling Ollama exactly as you do today — Telemetry simply observes
  and enriches those calls.
</Check>

***

## Requirements

Before you start, make sure you have:

* A **Latitude account** and **API key**
* A **Latitude project ID**
* A Python-based project that uses the **Ollama SDK**
* A running Ollama instance (local or remote)

That's it — prompts do **not** need to be created ahead of time.

***

## Steps

<Steps>
  <Step title="Install requirements">
    Add the Latitude Telemetry package to your project:

    <CodeGroup>
      ```bash pip theme={null}
      pip install latitude-telemetry
      ```

      ```bash uv theme={null}
      uv add latitude-telemetry
      ```

      ```bash poetry theme={null}
      poetry add latitude-telemetry
      ```
    </CodeGroup>
  </Step>

  <Step title="Wrap your Ollama-powered feature">
    Initialize Latitude Telemetry and wrap the code that calls Ollama using <code>telemetry.capture</code>.

    You can use the `capture` method as a decorator (recommended) or as a context manager:

    ```python Using decorator (recommended) theme={null}
    import os
    import ollama
    from latitude_telemetry import Telemetry, Instrumentors, TelemetryOptions

    telemetry = Telemetry(
        os.environ["LATITUDE_API_KEY"],
        TelemetryOptions(instrumentors=[Instrumentors.Ollama]),
    )

    @telemetry.capture(
        project_id=123,  # The ID of your project in Latitude
        path="generate-support-reply",  # Add a path to identify this prompt in Latitude
    )
    def generate_support_reply(input: str) -> str:
        response = ollama.chat(
            model="llama3.2",
            messages=[{"role": "user", "content": input}],
        )
        return response["message"]["content"]
    ```

    ```python Using context manager theme={null}
    import os
    import ollama
    from latitude_telemetry import Telemetry, Instrumentors, TelemetryOptions

    telemetry = Telemetry(
        os.environ["LATITUDE_API_KEY"],
        TelemetryOptions(instrumentors=[Instrumentors.Ollama]),
    )

    def generate_support_reply(input: str) -> str:
        with telemetry.capture(
            project_id=123,  # The ID of your project in Latitude
            path="generate-support-reply",  # Add a path to identify this prompt in Latitude
        ):
            response = ollama.chat(
                model="llama3.2",
                messages=[{"role": "user", "content": input}],
            )
            return response["message"]["content"]
    ```

    <Info>
      The `path`:

      * Identifies the prompt in Latitude
      * Can be new or existing
      * Should not contain spaces or special characters (use letters, numbers, `- _ / .`)
    </Info>
  </Step>
</Steps>

***

## Streaming responses

When using streaming (`stream=True`), use a generator function with the decorator. The SDK keeps the span open until all chunks are yielded:

```python theme={null}
@telemetry.capture(project_id=123, path="generate-support-reply")
async def stream_support_reply(input: str):
    stream = ollama.chat(
        model="llama3.2",
        messages=[{"role": "user", "content": input}],
        stream=True,
    )
    for chunk in stream:
        if chunk["message"]["content"]:
            yield chunk["message"]["content"]
```

***

## Seeing your logs in Latitude

Once your feature is wrapped, logs will appear automatically.

1. Open the **prompt** in your Latitude dashboard (identified by `path`)
2. Go to the **Traces** section
3. Each execution will show:
   * Input and output messages
   * Model and token usage
   * Latency and errors
   * One trace per feature invocation

Each Ollama call appears as a child span under the captured prompt execution, giving you a full, end-to-end view of what happened.

***

## That's it

No changes to your Ollama calls, no special return values, and no extra plumbing — just wrap the feature you want to observe.