Documentation Index
Fetch the complete documentation index at: https://docs.latitude.so/llms.txt
Use this file to discover all available pages before exploring further.
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
Install
npm install @latitude-data/telemetry
pip install latitude-telemetry
Initialize and use
import { Latitude, capture } from "@latitude-data/telemetry"
import { CohereClient } from "cohere-ai"
import * as CohereSDK from "cohere-ai"
const latitude = new Latitude({
apiKey: process.env.LATITUDE_API_KEY!,
project: process.env.LATITUDE_PROJECT_SLUG!,
instrumentations: { cohere: CohereSDK },
})
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()
import cohere
from latitude_telemetry import Latitude, capture
latitude = Latitude(
api_key="your-api-key",
project="your-project-slug",
instrumentations={"cohere": 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:
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()
})
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:
- Open your project in the Latitude dashboard
- 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.
