Threads

A guide to track multi-turn conversation chat logs.

What is Threads?

Threads are conversation groupings for chatlogs. You can easily track multi-turn conversations by passing in a Thread ID when logging.

You will love it when you want to:

• Track multi-turn conversations.
• Check the whole conversation history instead of a single log.

Quick start

In your API payload, pass thread_identifier to group the chatlogs into a thread. Every log with the same thread_identifier will be grouped into the same thread.

Python

payload = {
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Tell me a long story"}],
    "thread_identifier": "thread_id"
}

The Thread feature allows you to group related chat logs together by using a common thread_identifier. This approach is particularly useful for conversational AI applications, as it organizes chat history into a single thread.

OpenAI Python SDK

from openai import OpenAI

client = OpenAI(
    base_url="https://api.keywordsai.co/api/",
    api_key="YOUR_KEYWORDSAI_API_KEY",
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "user", "content": "Tell me a long story"}
    ],
    extra_body={
        "thread_identifier": "the_first_thread"
    }
)

OpenAI TypeScript SDK

To implement threading in the OpenAI TypeScript SDK, add the thread_identifier parameter to your request. Note: You’ll need to include // @ts-expect-error before the thread_identifier field to handle TypeScript type checking.

import { OpenAI } from "openai";

const client = new OpenAI({
  baseURL: "https://api.keywordsai.co/api",
  apiKey: "YOUR_KEYWORDSAI_API_KEY",
});

const response = await client.chat.completions
  .create({
    messages: [{ role: "user", content: "Say this is a test" }],
    model: "gpt-4o-mini",
    // @ts-expect-error
    thread_identifier: "the_first_thread"
  })
  .asResponse();

console.log(await response.json());

Standard API

LLM proxy

import requests
def demo_call(input, 
              model="gpt-4o-mini",
              token="YOUR_KEYWORDS_AI_API_KEY",
              ):
    headers = {
        'Content-Type': 'application/json',
        'Authorization': f'Bearer {token}',
    }

    data = {
        'model': model,
        'messages': [{'role': 'user', 'content': input}],
        'thread_identifier': "the_first_thread"
    }

    response = requests.post('https://api.keywordsai.co/api/chat/completions', headers=headers, json=data)
    return response

messages = "Say 'Hello World'"
print(demo_call(messages).json())

Other SDKs

We also support adding credentials in other SDKs or languages, please check out our integrations.

View threads on the platform

Go to Threads

There’s a Threads page on the platform where you can view all the threads you’ve created.

Open a Thread in Logs

To view the detailed logs within a thread:

1. Click the Open in Logs button in the side panel to access the thread’s complete log history.

2. Browse through all logs associated with the thread. Select any individual log entry to view its complete details.