🌍 Groq AI Translator — Llama 3.1 + LangChain

This notebook demonstrates how to build a fast, accurate AI Translator using:

Groq Llama 3.1 8B Instant

LangChain LCEL pipeline

ChatPromptTemplate

System & Human Messages

OpenAI + Groq setup

You can translate ANY text into ANY target language.

🚀 Features ✔ Translate English → Turkish ✔ Translate any text → any language ✔ Dynamic LCEL pipeline: prompt → model → parser

✔ Uses high-speed Groq inference ✔ Demonstrates real LangChain constructs

SystemMessage

HumanMessage

ChatPromptTemplate

StrOutputParser

model.invoke()

model | parser

📂 Project Structure groq-ai-translator/ │ ├── translator.ipynb ├── README.md ├── requirements.txt ├── .env.example └── .gitignore

🔧 Installation

Create a virtual environment (optional):

python -m venv venv source venv/bin/activate # Mac/Linux venv\Scripts\activate # Windows

Install dependencies:

pip install -r requirements.txt

🔐 Environment Setup

Duplicate .env.example → rename to .env

Add your keys:

OPENAI_API_KEY=your_openai_key GROQ_API_KEY=your_groq_key

▶️ Run the Notebook jupyter notebook

Open translator.ipynb

🧠 Example Usage 🔸 Using message objects messages = [ SystemMessage(content="Translate this from English to Turkish"), HumanMessage(content="This is an AI translator app"), ] response = model.invoke(messages)

🔸 Using LCEL pipeline chain = model | parser chain.invoke(messages)

🔸 Using PromptTemplate (Dynamic Translation) chain = prompt | model | parser chain.invoke({"language": "french", "text": "Hello"})

👨‍💻 Author

Shehjad Patel AI Engineer | LangChain | LLMs | Groq