Update README.md

README.md

@@ -16,9 +16,11 @@ This is an MVP AI chatbot built for the AML-3304 assignment:
 **"From Tokens to Transformers: Building AI Systems with Embeddings, Generative Models, and MLOps."**
 
 PromptPilot integrates:
-- 📊 Bayesian-style Q&A with top-k embedding inference  
+- 📊 Bayesian-style Q&A with top-k sampling  
 - 📘 General factual Q&A using FLAN-T5  
 - 🧑‍💻 Python code generation using CodeGen  
+- 💬 Semantic Q&A with DeepSeek-RAG (Retriever-Augmented Generation)  
+- 🧠 Sentence-based embedding search using Sentence-BERT + FAISS  
 
 Deployed on Hugging Face Spaces with lightweight, multi-model architecture.
 
@@ -26,11 +28,13 @@ Deployed on Hugging Face Spaces with lightweight, multi-model architecture.
 
 ## 🔄 Chat Modes
 
-| Mode             | Description                             | Model Used                     |
-|------------------|-----------------------------------------|--------------------------------|
-| 🧑‍💻 Code Generator| Generate Python code from user prompts  | `Salesforce/codegen-350M-mono` |
-| 📘 General Q&A   | Answer factual and reasoning questions  | `google/flan-t5-base`          |
-| 📊 Bayesian Q&A  | Top-k probabilistic Q&A using embeddings| Custom + `flan-t5-base`        |
+| Mode                | Description                                          | Model Used                             |
+|---------------------|------------------------------------------------------|----------------------------------------|
+| 🧑‍💻 Code Generator | Generate Python code from natural language prompts   | `Salesforce/codegen-350M-mono`         |
+| 📘 General Q&A      | Answer factual and reasoning questions               | `google/flan-t5-base`                  |
+| 📊 Bayesian Q&A     | Sample-based Q&A with top-k decoding                 | `google/flan-t5-base` + sampling       |
+| 🧠 DeepSeek RAG     | RAG-style answers grounded in retrieval              | `deepseek-ai/deepseek-coder-1.3b-base` |
+| 💬 Semantic Search  | Similarity-based answer generation using embeddings  | `sentence-transformers/all-MiniLM-L6-v2` + FAISS |
 
 ---