Cohere

Connect your Cohere-powered application to Latitude for observability.

Work in progress: Telemetry documentation is still being updated. Integration steps and APIs may be incomplete or out of date. Verify against your SDK versions and check back for revisions.

Overview

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

You’ll keep calling Cohere exactly as you do today. Telemetry simply observes and enriches those calls.

---

Requirements

• A Latitude account and API key
• A Latitude project slug
• A project that uses the Cohere SDK

---

Steps

1. Install

   TypeScript

   npm

   npm install @latitude-data/telemetry
   

   Python

   pip

   pip install latitude-telemetry
   
2. Initialize and use

   TypeScript

   import { initLatitude, capture } from "@latitude-data/telemetry"
   import { CohereClient } from "cohere-ai"
   
   const latitude = initLatitude({
     apiKey: process.env.LATITUDE_API_KEY!,
     projectSlug: process.env.LATITUDE_PROJECT_SLUG!,
     instrumentations: ["cohere"],
   })
   
   await latitude.ready
   
   const client = new CohereClient({ token: process.env.COHERE_API_KEY })
   
   await capture("generate-reply", async () => {
     const response = await client.chat({
       model: "command-a-03-2025",
       message: "Hello",
     })
     return response.text
   })
   
   await latitude.shutdown()
   

   Python

   from latitude_telemetry import init_latitude, capture
   import cohere
   
   latitude = init_latitude(
       api_key="your-api-key",
       project_slug="your-project-slug",
       instrumentations=["cohere"],
   )
   
   client = cohere.Client()
   
   def generate_reply():
       response = client.chat(
           model="command-a-03-2025",
           message="Hello",
       )
       return response.text
   
   capture("generate-reply", generate_reply)
   
   latitude.shutdown()
   

---

Streaming

When streaming, consume the stream inside capture() so the span covers the full operation:

TypeScript

await capture("stream-reply", async () => {
  const stream = await 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()
})

Python

def stream_reply():
    for event in client.chat_stream(
        model="command-a-03-2025",
        message=input,
    ):
        if event.event_type == "text-generation":
            yield event.text

capture("stream-reply", stream_reply)

---

Seeing Your Traces

Once connected, traces appear automatically in Latitude:

1. Open your project in the Latitude dashboard
2. Each execution shows input/output messages, model, token usage, latency, and errors

---

That’s It

No changes to your Cohere calls: just initialize Latitude and your LLM calls are traced.