Thread - Literal Doc

A Thread represents a group of interactions between a user and an AI app. It can be, for example, a conversation between a human and one or several assistants, or an agent generating a document piece by piece from a user input. A Thread is composed of Steps. A Step can be a message, or an intermediate AI step like an LLM call.

Log a Thread

import os
import time
from literalai import LiteralClient

client = LiteralClient(api_key=os.getenv("LITERAL_API_KEY"))

@client.step(type="run")
def my_assistant(input: str):
    # Implement your assistant logic here
    time.sleep(1)
    response = "My assistant response"
    client.message(content=response, type="assistant_message", name="Assistant")
    return response

def main():
    # You can also continue a thread by passing the thread id
    with client.thread(name="Thread Example") as thread:
      print(thread.id)
      user_query = "Hello World"
      client.message(content=user_query, type="user_message", name="User")
      my_assistant(user_query)

      # Let's say the user has a follow up question
      follow_up_query = "Follow up!"
      client.message(content=follow_up_query, type="user_message", name="User")
      my_assistant(user_query)

main()
# Network requests by the SDK are performed asynchronously.
# Invoke flush_and_stop() to guarantee the completion of all requests prior to the process termination.
# WARNING: If you run a continuous server, you should not use this method.
client.flush_and_stop()

import { LiteralClient, Thread } from '@literalai/client';

const client = new LiteralClient(process.env['LITERAL_API_KEY']);

async function myAssistant(thread: Thread, query: string) {
  const run = thread.step({
    type: "run",
    name: "My Assistant",
    input: { content: query },
  });

  // Implement your assistant logic here
  await new Promise((r) => setTimeout(r, 1000));
  const response = { content: "My assistant response" };

  run.output = response;
  await run.send();

  await run
    .step({
      type: "assistant_message",
      name: "Assistant",
      output: response,
    })
    .send();
}

async function main() {
  // You can also continue a thread by passing the thread id
  const thread = await client.thread({ name: "Thread Example" }).upsert();
  console.log(thread.id);

  const userQuery = "Hello World";
  thread
    .step({
      type: "user_message",
      name: "User",
      output: { content: userQuery },
    })
    .send();

  await myAssistant(thread, userQuery);

  const followUpQuery = "Follow up!";
  thread
    .step({
      type: "user_message",
      name: "User",
      output: { content: followUpQuery },
    })
    .send();

  await myAssistant(thread, userQuery);
}

main()
  .then(() => process.exit(0))
  .catch((error) => console.error(error));

Visualize the Thread on Literal

Navigate to the Threads page on the platform to see the thread you just created.

A thread on the platform — Output on the platform