Tropir TypeScript Client

A thin client for tracing LLM calls, designed for TypeScript/JavaScript applications.

Installation

npm install tropir

Usage

Using with Fetch API

import { prepareRequestHeaders, createTropirFetch } from 'tropir';

// Option 1: Use prepareRequestHeaders with your own headers
const headers = new Headers({
  'Content-Type': 'application/json',
  'Authorization': `Bearer ${process.env.OPENAI_API_KEY}`
});

prepareRequestHeaders(headers);

fetch('https://api.tropir.com/openai/v1/chat/completions', {
  method: 'POST',
  headers,
  body: JSON.stringify({
    model: 'gpt-4o',
    messages: [{ role: 'user', content: 'Hello' }]
  })
});

// Option 2: Use the createTropirFetch helper
const tropirFetch = createTropirFetch();

tropirFetch('https://api.tropir.com/openai/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': `Bearer ${process.env.OPENAI_API_KEY}`
  },
  body: JSON.stringify({
    model: 'gpt-4o',
    messages: [{ role: 'user', content: 'Hello' }]
  })
});

Using with LangChain

import { ChatOpenAI } from '@langchain/openai';
import { createTropirFetch } from 'tropir';

const model = new ChatOpenAI({
  openAIApiKey: process.env.OPENAI_API_KEY,
  modelName: 'gpt-4o',
  temperature: 0.7,
  configuration: {
    baseURL: 'https://api.tropir.com/openai/v1',
    fetch: createTropirFetch()
  }
});

Session Management

You can manage tracing sessions:

import { setSessionId, getSessionId, clearSessionId } from 'tropir';

// Set a custom session ID
setSessionId('my-custom-session-id');

// Get current session ID
const sessionId = getSessionId();

// Clear session ID (reverts to default)
clearSessionId();