Together AI

Connect your Together AI-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 Integration steps and APIs may be incomplete or out of date.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 Together AI SDK.

You’ll keep calling Together AI 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 Together AI 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 Together from "together-ai"
   
   const latitude = initLatitude({
     apiKey: process.env.LATITUDE_API_KEY!,
     projectSlug: process.env.LATITUDE_PROJECT_SLUG!,
     instrumentations: ["togetherai"],
   })
   
   await latitude.ready
   
   const client = new Together()
   
   await capture("generate-reply", async () => {
     const response = await client.chat.completions.create({
       model: "meta-llama/Llama-3-70b-chat-hf",
       messages: [{ role: "user", content: "Hello" }],
     })
     return response.choices[0].message.content
   })
   
   await latitude.shutdown()
   

   Python

   from latitude_telemetry import init_latitude, capture
   from together import Together
   
   latitude = init_latitude(
       api_key="your-api-key",
       project_slug="your-project-slug",
       instrumentations=["togetherai"],
   )
   
   client = Together()
   
   def generate_reply():
       response = client.chat.completions.create(
           model="meta-llama/Llama-3-70b-chat-hf",
           messages=[{"role": "user", "content": "Hello"}],
       )
       return response.choices[0].message.content
   
   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.chat.completions.create({
    model: "meta-llama/Llama-3-70b-chat-hf",
    messages: [{ role: "user", content: input }],
    stream: true,
  })

  for await (const chunk of stream) {
    const content = chunk.choices[0]?.delta?.content
    if (content) res.write(content)
  }
  res.end()
})

Python

def stream_reply():
    stream = client.chat.completions.create(
        model="meta-llama/Llama-3-70b-chat-hf",
        messages=[{"role": "user", "content": input}],
        stream=True,
    )
    for chunk in stream:
        if chunk.choices[0].delta.content:
            yield chunk.choices[0].delta.content

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 Together AI calls: just initialize Latitude and your LLM calls are traced.