An end-to-end LLM-powered text translation application built with LangChain Expression Language (LCEL), featuring a FastAPI backend for high-performance inference, LangServe for seamless model deployment, and a Streamlit client for an intuitive user interface.
- LCEL pipeline — declarative, composable LangChain Expression Language chains
- Multi-language translation — translate between multiple language pairs
- Groq-powered inference — high-speed LLM inference via Groq's LLaMA models
- FastAPI backend — async, production-ready API server
- LangServe deployment — automatic REST API generation from LCEL chains
- Streamlit client — clean, responsive translation interface
- Configurable models — swap between different LLM providers and models
- Python 3 — Core programming language
- LangChain + LCEL — Declarative LLM pipeline framework
- FastAPI — High-performance API server
- LangServe — LCEL chain deployment infrastructure
- Streamlit — Web client interface
- Groq — LLaMA model inference API
git clone https://github.com/giovanniromero-dev/lcel-llm-translator.git
cd lcel-llm-translator
pip install -r requirements.txt
# Configure your .env with Groq API key
python server.py # Start FastAPI + LangServe server
streamlit run client.py # In a separate terminal, start the UIBuilt with dedication by Giovanni Romero