Movie-Knowledge-Search-Bot-RAG-LangChain-FAISS-

(RAG + LangChain + FAISS + Kaggle API)This project implements a Retrieval-Augmented Generation (RAG) system that answers natural language questions about movies using their plot summaries.

“I built a RAG-based movie knowledge assistant using LangChain and FAISS, powered by Kaggle data and deployed in Google Colab.”

This project implements a Retrieval-Augmented Generation (RAG) system that answers natural language questions about movies using their plot summaries.

---

👉 Open the notebook in Colab: Click here to run the project

🔧 Tech Stack

• Python
• LangChain
• FAISS (Vector Database)
• Sentence-Transformers
• OpenAI LLM
• KaggleHub API
• Google Colab

---

📊 Dataset

Wikipedia Movie Plots Dataset from Kaggle

---

🚀 How It Works

1. Movie plot summaries are converted into vector embeddings
2. FAISS stores and retrieves semantically similar plots
3. Retrieved context is passed to an LLM
4. The LLM generates grounded, accurate answers

---

🧠 Key Concepts Demonstrated

• Retrieval-Augmented Generation (RAG)
• Vector databases
• Prompt engineering
• Semantic search
• Large Language Models (LLMs)

---

📌 Example Questions

• What is the plot of Inception?
• Which movies are about artificial intelligence?
• Tell me about mafia-related movies

---

▶️ How to Run

1. Open the Google Colab notebook
2. Upload your kaggle.json API key
3. Run cells sequentially
4. Enter natural language movie questions

---

💡 Conclusion

This project shows how RAG systems can significantly improve LLM reliability by grounding responses in real data. It is scalable, efficient, and suitable for real-world applications.

---

movie-rag-langchain-faiss/ │ ├── notebook/

│ └── movie_rag_colab.ipynb

│ ├── README.md

└── requirements.txt

📎 Demo

Run the Colab notebook for an interactive demo.