Update README.md

README.md

@@ -1,65 +1,70 @@
-# 👁 Stranger Things RAG — Hawkins Archive Chatbot
+---
+title: Hawkins Archive RAG (Stranger Things)
+emoji: 👁
+colorFrom: green
+colorTo: red
+sdk: docker
+sdk_version: "3.10"
+app_file: app.py
+pinned: true
+---
 
-Welcome to **Hawkins Archive RAG**, a Retrieval-Augmented Generation (RAG) chatbot that answers questions from the **Stranger Things universe** using **context-based retrieval** and a themed interface inspired by **Hawkins National Laboratory**.
+# 👁 Hawkins Archive RAG — Stranger Things Chatbot
+
+A **Retrieval-Augmented Generation (RAG)** chatbot that answers questions about the **Stranger Things universe** using **semantic search + context-grounded generation**.
 
 🔗 **Live Demo:** https://huggingface.co/spaces/siddheshrj/Stranger_things_rag
 
 ---
 
-## 🚀 What this project does
-
-This Space is a **RAG-based chatbot** that:
+## 🚀 What this Space does
 
-✅ Retrieves relevant information from a Stranger Things knowledge base  
-✅ Uses the retrieved context to generate grounded answers  
-✅ Produces natural & structured character summaries including:  
-- key relationships (friends/family/romantic)  
-- role / passion (leader, journalist, sheriff, etc.)  
-- iconic traits & personality
-
-Example query:  
-> **"Who is Mike Wheeler?"**
+This chatbot:
+- Takes your question (example: **"Who is Mike Wheeler?"**)  
+- Retrieves the most relevant context from the Stranger Things knowledge base  
+- Generates a natural response using an LLM  
+- Ensures answers are structured with **relationships, role/passion, and iconic traits**
 
 ---
 
-## 🧠 How RAG Works (Simple Explanation)
+## ✨ Features
 
-RAG = **Search + Answer**
+✅ Context-aware answers using RAG (reduces hallucination)  
+✅ Stranger Things themed UI (Hawkins Lab vibe)  
+✅ Fast retrieval using embeddings + similarity search  
+✅ Character-focused response formatting  
+✅ Hosted & deployed on Hugging Face Spaces (Docker)
 
-1. You ask a question  
-2. The system searches the most relevant text chunks using embeddings  
-3. The LLM generates the final response using that context
+---
 
-This makes answers more **reliable**, **context-aware**, and reduces hallucinations.
+## 🧠 How RAG Works (Simple)
 
----
+RAG = **Retrieve + Generate**
 
-## ✨ Features
+1. **Retrieve:** find relevant context chunks using embeddings  
+2. **Generate:** pass context + question to LLM for final answer  
 
-✅ Stranger Things themed UI (Hawkins Lab terminal style)  
-✅ Fast semantic search (retrieval)  
-✅ Context-grounded answers  
-✅ Character-based response formatting  
-✅ Hosted on Hugging Face Spaces
+This makes responses more accurate and grounded compared to plain chatbots.
 
 ---
 
 ## 🛠️ Tech Stack
 
-- **LangChain** (RAG orchestration)
-- **Vector Store** (for similarity search)
+- **LangChain** (RAG pipeline)
 - **Embeddings**
-- **LLM API / Hugging Face inference**
-- **Docker** deployment on Hugging Face Spaces
+- **Vector Database / Similarity Search**
+- **LLM API**
+- **Docker**
+- **Hugging Face Spaces**
 
 ---
 
-## 🧪 Try these questions
+## ✅ Example Questions to Try
 
 ### Easy
 - Who is Eleven?
 - What is the Upside Down?
-- Who are Mike’s friends?
+- Who are Mike’s best friends?
 
 ### Medium
 - Explain Hawkins Lab in short
@@ -71,32 +76,17 @@ This makes answers more **reliable**, **context-aware**, and reduces hallucinati
 
 ---
 
-## 📌 Project Goal
-
-The goal of this project is to build a clean **RAG pipeline** and deploy it as an interactive chatbot,
-showing practical skills in:
-
-✅ Prompt engineering  
-✅ LangChain pipelines  
-✅ Retrieval + embeddings  
-✅ Deployment (Docker + Hugging Face Spaces)
-
----
-
 ## 🔮 Future Improvements
 
 - Add chat memory (multi-turn conversation)
 - Add citations / sources in answers
-- Improve retrieval accuracy
-- Add multi-agent + MCP agent integration
-- Multimodal support (image + text)
+- Improve retrieval accuracy (better chunking + reranking)
+- Multi-agent support (MCP + tools)
+- Multimodal extension (image + text)
 
 ---
 
 ## 👤 Author
 
 **Siddhesh Jajurley**  
-🔗 Hugging Face: https://huggingface.co/siddheshrj  
----
-
-⭐ If you like this Space, give it a **Like** on Hugging Face!
+Hugging Face: https://huggingface.co/siddheshrj