Quick Start

Instrument your Code

Install the Literal AI SDK and get your API key.

Create your first Prompt from the Playground

Create, version and A/B test your prompts in the Prompt Playground.

Logging LLM Generations, Agent Runs or Conversation Threads

Install the Literal AI package

pip install literalai

npm i @literalai/client

Instantiate the Literal AI client

import os
from literalai import LiteralClient

# Not compatible with gunicorn's --preload flag
literalai_client = LiteralClient(api_key=os.getenv("LITERAL_API_KEY")) # This is the default and can be omitted

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

const literalAiClient = new LiteralClient({apiKey: process.env["LITERAL_API_KEY"]}); // This is the default and can be omitted

Get your Literal AI API Key

Go to your project page and click on the Settings tab. You will find your API key in the API Key section.

Start logging LLM generations and agent runs

Literal AI provides

low-level SDKs in Python and TypeScript
integrations with LLM providers (OpenAI, etc.) and AI frameworks (LangChain, LlamaIndex, Vercel AI SDK, etc.)

Logging

Learn how to instrument your code with the Literal AI SDK.

Integrations

Browse the list of integrations available with Literal AI.

Important Notice

Get Started

Application

Evaluation

Settings

Guides

Integrations

Self Hosting

More

Instrument your Code

Create your first Prompt from the Playground

Logging LLM Generations, Agent Runs or Conversation Threads

Start logging LLM generations and agent runs

Logging

Integrations

Instrument your Code

Create your first Prompt from the Playground

​Logging LLM Generations, Agent Runs or Conversation Threads

​Start logging LLM generations and agent runs

Logging

Integrations

Logging LLM Generations, Agent Runs or Conversation Threads

Start logging LLM generations and agent runs