Menyiapkan Lingkungan Anda: LangChain, LangGraph & Chat LLMs

𝗦𝗲𝘁𝘁𝗶𝗻𝗴 𝗨𝗽 𝗬𝗼𝘂𝗿 𝗘𝗻𝘃𝗶𝗿𝗼𝗻𝗺𝗲𝗻𝘁: 𝗟𝗮𝗻𝗴𝗖𝗵𝗮𝗶𝗻, 𝗟𝗮𝗻𝗴𝗚𝗿𝗮𝗽𝗵 & 𝗖𝗵𝗮𝘁 𝗟𝗟𝗠𝘀

I once spent two hours debugging a LangChain project. The problem was one missing environment variable. My API key was in a .env file, but I forgot to load it.

I wrote this guide so you do not waste time like I did.

You will learn to set up a working Python environment with LangChain, LangGraph, and a Chat LLM.

Required Packages:

• langchain: Core framework for chains and agents
• langchain-openai: Integration with OpenAI models
• langchain-core: Shared primitives like messages
• langgraph: Graph-based agent workflows
• python-dotenv: Loads variables from a .env file
• openai: Official OpenAI Python SDK

Step 1: Check Python Version LangChain needs Python 3.9 or higher. Run this in your terminal: python --version

Step 2: Create a Virtual Environment Always use a virtual environment to avoid dependency conflicts.

mkdir langchain-agents-series cd langchain-agents-series python -m venv venv

To activate on Mac/Linux: source venv/bin/activate

To activate on Windows: venv\Scripts\activate

Step 3: Install Dependencies With your environment active, run: pip install langchain langchain-openai langchain-core langgraph python-dotenv openai

Step 4: Secure Your API Keys Never hardcode your API key in your code. This is dangerous. If you push it to GitHub, bots will steal it.

1. Create a .env file: touch .env
2. Add your key: OPENAI_API_KEY=your-key-here
3. Create a .gitignore file to hide your .env and venv folders.

Step 5: Your First Agent Create a file named hello_agent.py. Use the load_dotenv() function to read your keys.

Use temperature=0 when building agents. This makes the model output predictable and consistent.

Common Errors to Watch For:

• OPENAI_API_KEY not found: Check if your .env file is in the right folder and you called load_dotenv().
• ModuleNotFoundError: Your virtual environment is not active.
• AuthenticationError: Your API key is wrong.
• RateLimitError: You hit your limit or need to add credits to your OpenAI account.

Best Practices:

• Always use a virtual environment.
• Pin your versions with pip freeze > requirements.txt.
• Use temperature=0 for stability.
• Log your token usage to track costs.

Source: https://dev.to/ikram_khan/setting-up-your-environment-langchain-langgraph-chat-llms-43cf

Komunitas belajar opsional: https://t.me/GyaanSetuAi