There are multiple ways to log Threads in your Python applications.

​
Using the @literal_client.thread decorator

Use this decorator before a function to initiate a Thread. This method is a simple and straighforward way of logging Threads.

import os
from literalai import LiteralClient

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

@literal_client.step(type="run")
def my_assistant(input: str):
    response = "My assistant response"
    literal_client.message(content=response, type="assistant_message", name="Assistant")
    return response

@literal_client.thread
def main():
    user_query = "Hello World"
    literal_client.message(content=user_query, type="user_message", name="User")
    my_assistant(user_query)

main()

​
Using the with statement

If you prefer to have more flexibility in logging Threads, you can use the with statement. You can create a thread and execute code within it using the with statement:

with literal_client.thread() as thread:
    # do something

You can also continue a thread by passing the thread id to the thread method:


previous_thread_id = "UUID"

with literal_client.thread(thread_id=previous_thread_id) as thread:
    # do something

​
Using the Literal AI API client

You can also create Threads using the literal_client.api.create_thread() method.

thread = literal_client.api.create_thread(
    participant_id="<PARTICIPANT_UUID>",
    environment="production",
    tags=["tag1", "tag2"],
    metadata={"key": "value"},
)

​
Using Chainlit

If you built your LLM application with Chainlit, you don’t need to specify Threads in your code. Chainlit logs Threads for you by default.

​
Thread API

Thread API

Manipulate threads directly using the API.

Was this page helpful?

InstallationStep