> ## 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.

# Cohere

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

## Overview

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

After completing these steps:

* Every Cohere call (e.g. `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 Cohere-powered features from the Latitude dashboard.

<Check>
  You'll keep calling Cohere 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 Node.js or Python-based project that uses the **Cohere SDK**

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:

    <Tabs>
      <Tab title="TypeScript">
        <CodeGroup>
          ```bash npm theme={null}
          npm add @latitude-data/telemetry
          ```

          ```bash pnpm theme={null}
          pnpm add @latitude-data/telemetry
          ```

          ```bash yarn theme={null}
          yarn add @latitude-data/telemetry
          ```

          ```bash bun theme={null}
          bun add @latitude-data/telemetry
          ```
        </CodeGroup>
      </Tab>

      <Tab title="Python">
        <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>
      </Tab>
    </Tabs>
  </Step>

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

    <Tabs>
      <Tab title="TypeScript">
        ```ts theme={null}
        import { LatitudeTelemetry } from '@latitude-data/telemetry'
        import * as Cohere from 'cohere-ai'

        const telemetry = new LatitudeTelemetry(
          process.env.LATITUDE_API_KEY,
          { instrumentations: { cohere: Cohere } }
        )

        async function generateSupportReply(input: string) {
          return telemetry.capture(
            {
              projectId: 123, // The ID of your project in Latitude
              path: 'generate-support-reply', // Add a path to identify this prompt in Latitude
            },
            async () => {
              const client = new Cohere.CohereClient({
                token: process.env.COHERE_API_KEY,
              })
              const response = await client.chat({
                model: 'command-a-03-2025',
                message: input,
              })
              return response.text
            }
          )
        }
        ```
      </Tab>

      <Tab title="Python">
        You can use the `capture` method as a decorator (recommended) or as a context manager:

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

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

        @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:
            client = cohere.Client(api_key=os.environ["COHERE_API_KEY"])
            response = client.chat(
                model="command-a-03-2025",
                message=input,
            )
            return response.text
        ```

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

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

        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
            ):
                client = cohere.Client(api_key=os.environ["COHERE_API_KEY"])
                response = client.chat(
                    model="command-a-03-2025",
                    message=input,
                )
                return response.text
        ```
      </Tab>
    </Tabs>

    <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, consume the stream inside your capture block so the span covers the entire operation.

<Tabs>
  <Tab title="TypeScript">
    **Consume the stream inside** your `capture()` callback:

    ```typescript theme={null}
    async function streamSupportReply(input: string, res: Response) {
      await telemetry.capture(
        { projectId: 123, path: 'generate-support-reply' },
        async () => {
          const client = new Cohere.CohereClient({
            token: process.env.COHERE_API_KEY,
          })
          const stream = client.chatStream({
            model: 'command-a-03-2025',
            message: input,
          })

          for await (const event of stream) {
            if (event.eventType === 'text-generation') {
              res.write(event.text)
            }
          }
          res.end()
        }
      )
    }
    ```
  </Tab>

  <Tab title="Python">
    **Use a generator function** with the decorator:

    ```python theme={null}
    @telemetry.capture(project_id=123, path="generate-support-reply")
    async def stream_support_reply(input: str):
        client = cohere.Client(api_key=os.environ["COHERE_API_KEY"])
        stream = client.chat_stream(
            model="command-a-03-2025",
            message=input,
        )
        for event in stream:
            if event.event_type == "text-generation":
                yield event.text
    ```
  </Tab>
</Tabs>

***

## 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 Cohere 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 Cohere calls, no special return values, and no extra plumbing — just wrap the feature you want to observe.