From 46e53dfe665d39844ef40360dffcc4043a68fe84 Mon Sep 17 00:00:00 2001
From: reanhehe <rehanmehta2000@gmail.com>
Date: Sun, 15 Feb 2026 16:23:13 +0530
Subject: [PATCH 1/6] Add TravelGenie submission

---
 submissions/BittenByPython_TravelGenie.md | 144 ++++++++++++++++++++++
 1 file changed, 144 insertions(+)
 create mode 100644 submissions/BittenByPython_TravelGenie.md

diff --git a/submissions/BittenByPython_TravelGenie.md b/submissions/BittenByPython_TravelGenie.md
new file mode 100644
index 0000000..d08d80c
--- /dev/null
+++ b/submissions/BittenByPython_TravelGenie.md
@@ -0,0 +1,144 @@
+<h1 align="center">
+  <a href="https://github.com/CommunityOfCoders/Inheritance2k25">
+    CoC Inheritance 2025
+  </a>
+  <br>
+  TravelGenie: AI-Powered Smart Travel Planning System
+</h1>
+
+<div align="center">
+By Bitten By Python
+</div>
+<hr>
+
+<details>
+<summary>Table of Contents</summary>
+
+- [Description](#description)
+- [Links](#links)
+- [Tech Stack](#tech-stack)
+- [Progress](#progress)
+- [Future Scope](#future-scope)
+- [Applications](#applications)
+- [Project Setup](#project-setup)
+- [Team Members](#team-members)
+- [Mentors](#mentors)
+
+</details>
+
+## 📝 Description
+
+TravelGenie is an AI-powered smart travel planning system that generates personalized, structured, and optimized travel itineraries using a locally deployed Large Language Model. The system solves the problem of generic and unrealistic travel suggestions by combining structured dataset filtering with context-aware LLM generation. Built using React, FastAPI, and Mistral 7B Instruct with GPU acceleration, TravelGenie delivers realistic, budget-aware, and city-restricted travel plans.
+
+## 🔗 Links
+
+- [GitHub Repository](https://github.com/Rehan1604/Travel_Genie-Inheritance-)
+- [Demo Video]https://drive.google.com/file/d/17rnifMKwYDJi85VA_xYY3rXyMjG5T3Hy/view?usp=drive_link
+- [Project Screenshots/Drive] https://drive.google.com/drive/folders/1NHrsDFPxkjYD7yWH67OHcHFVX3k0ld5h?usp=drive_link
+- [Hosted Website](Not Deployed Yet)
+
+## 🤖 Tech-Stack
+
+### 🏗️ System Architecture
+
+```mermaid
+graph LR
+    A[User Input] --> B[React Frontend (Vite)]
+    B --> C[Axios API Request]
+    C --> D[FastAPI Backend]
+    D --> E[CSV Dataset Filtering]
+    E --> F[Structured Prompt Injection]
+    F --> G[Mistral 7B Instruct (4-bit Quantized)]
+    G --> H[RTX 4060 GPU - CUDA 12.7]
+    H --> I[Day-wise Structured Itinerary Output]
+    I --> B
+Front-end
+React.js (Vite)
+
+Axios
+
+Dynamic Chat Interface
+
+localStorage for itinerary persistence
+
+Back-end
+FastAPI
+
+HuggingFace Transformers
+
+Accelerate
+
+Mistral 7B Instruct
+
+Database / ML
+Structured CSV dataset (Cities from India, USA, Iran)
+
+Includes climate data, pricing ranges, and category metadata
+
+4-bit quantization for optimized inference
+
+NVIDIA RTX 4060 GPU with CUDA 12.7
+
+📈 Progress
+Fully Implemented Features
+Personalized Day-wise Itinerary Generation: Automatically generates structured travel plans divided by day.
+
+Budget-Aware Dataset Filtering: Filters attractions based on user-defined budget constraints.
+
+City-Restricted Recommendation System: Ensures no cross-city or irrelevant outputs are generated.
+
+Partially Implemented Features / Work in Progress
+Cloud Deployment: Currently running locally; deployment to cloud environment planned.
+
+External API Integrations: Weather, hotel, and flight APIs to enhance itinerary realism.
+
+🔮 Future Scope
+Integration of real-time weather APIs.
+
+Expansion to multi-city itinerary planning.
+
+User authentication and persistent trip storage.
+
+Cloud-based LLM deployment.
+
+Advanced retrieval mechanisms for scalable systems.
+
+💸 Applications
+Personalized Travel Planning - Generates realistic, budget-aware, and structured travel itineraries.
+
+AI Travel Assistant Systems - Demonstrates practical local LLM deployment for smart recommendation engines.
+
+🛠 Project Setup
+Clone the GitHub repo.
+
+git clone https://github.com/Rehan1604/Travel_Genie-Inheritance-.git
+Enter the project directory and install dependencies.
+
+Backend Setup:
+
+cd Travel_Genie-Inheritance-/backend
+pip install -r requirements.txt
+uvicorn main:app --reload
+Frontend Setup:
+
+cd ../frontend
+npm install
+npm run dev
+Start the application.
+
+Frontend runs on local development server after npm run dev.
+Backend runs via uvicorn main:app --reload.
+
+👨‍💻 Team Members
+Rehan Mehta: https://github.com/Rehan1604
+
+Devansh Mehta: https://github.com/Devansh270
+
+Bhavya Gothi: https://github.com/Bhavya4523
+
+Jehan Bheda: https://github.com/jehanbheda
+
+👨‍🏫 Mentors
+Harsh Ogale: https://github.com/harshogale04
+
+Piyush Patil: https://github.com/MAVERICK-111
\ No newline at end of file

From efcb1d81001d9ae6215c63898514984c1d3c3f97 Mon Sep 17 00:00:00 2001
From: reanhehe <rehanmehta2000@gmail.com>
Date: Sun, 15 Feb 2026 16:37:47 +0530
Subject: [PATCH 2/6] Fix Mermaid syntax

---
 submissions/BittenByPython_TravelGenie.md | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/submissions/BittenByPython_TravelGenie.md b/submissions/BittenByPython_TravelGenie.md
index d08d80c..9ac4724 100644
--- a/submissions/BittenByPython_TravelGenie.md
+++ b/submissions/BittenByPython_TravelGenie.md
@@ -43,15 +43,16 @@ TravelGenie is an AI-powered smart travel planning system that generates persona
 
 ```mermaid
 graph LR
-    A[User Input] --> B[React Frontend (Vite)]
+    A[User Input] --> B[React Frontend Vite]
     B --> C[Axios API Request]
     C --> D[FastAPI Backend]
     D --> E[CSV Dataset Filtering]
     E --> F[Structured Prompt Injection]
-    F --> G[Mistral 7B Instruct (4-bit Quantized)]
-    G --> H[RTX 4060 GPU - CUDA 12.7]
+    F --> G[Mistral 7B Instruct 4bit Quantized]
+    G --> H[RTX 4060 GPU CUDA 12.7]
     H --> I[Day-wise Structured Itinerary Output]
     I --> B
+
 Front-end
 React.js (Vite)
 

From 3185420a8e0afff3428f1a4e720de68b3f5a24a9 Mon Sep 17 00:00:00 2001
From: reanhehe <rehanmehta2000@gmail.com>
Date: Sun, 15 Feb 2026 16:42:06 +0530
Subject: [PATCH 3/6] Final fix formatting

---
 submissions/BittenByPython_TravelGenie.md | 69 ++++++++++++-----------
 1 file changed, 37 insertions(+), 32 deletions(-)

diff --git a/submissions/BittenByPython_TravelGenie.md b/submissions/BittenByPython_TravelGenie.md
index 9ac4724..6c2125f 100644
--- a/submissions/BittenByPython_TravelGenie.md
+++ b/submissions/BittenByPython_TravelGenie.md
@@ -33,9 +33,9 @@ TravelGenie is an AI-powered smart travel planning system that generates persona
 ## 🔗 Links
 
 - [GitHub Repository](https://github.com/Rehan1604/Travel_Genie-Inheritance-)
-- [Demo Video]https://drive.google.com/file/d/17rnifMKwYDJi85VA_xYY3rXyMjG5T3Hy/view?usp=drive_link
-- [Project Screenshots/Drive] https://drive.google.com/drive/folders/1NHrsDFPxkjYD7yWH67OHcHFVX3k0ld5h?usp=drive_link
-- [Hosted Website](Not Deployed Yet)
+- [Demo Video](https://drive.google.com/file/d/17rnifMKwYDJi85VA_xYY3rXyMjG5T3Hy/view?usp=drive_link)
+- [Project Screenshots/Drive](https://drive.google.com/drive/folders/1NHrsDFPxkjYD7yWH67OHcHFVX3k0ld5h?usp=drive_link)
+- Hosted Website: Not Deployed Yet
 
 ## 🤖 Tech-Stack
 
@@ -43,16 +43,25 @@ TravelGenie is an AI-powered smart travel planning system that generates persona
 
 ```mermaid
 graph LR
-    A[User Input] --> B[React Frontend Vite]
-    B --> C[Axios API Request]
-    C --> D[FastAPI Backend]
-    D --> E[CSV Dataset Filtering]
-    E --> F[Structured Prompt Injection]
-    F --> G[Mistral 7B Instruct 4bit Quantized]
-    G --> H[RTX 4060 GPU CUDA 12.7]
-    H --> I[Day-wise Structured Itinerary Output]
+    A --> B
+    B --> C
+    C --> D
+    D --> E
+    E --> F
+    F --> G
+    G --> H
+    H --> I
     I --> B
 
+    A[User_Input]
+    B[React_Frontend]
+    C[Axios_API]
+    D[FastAPI_Backend]
+    E[CSV_Filtering]
+    F[Prompt_Injection]
+    G[Mistral_7B]
+    H[GPU_Inference]
+    I[Itinerary_Output]
 Front-end
 React.js (Vite)
 
@@ -74,7 +83,7 @@ Mistral 7B Instruct
 Database / ML
 Structured CSV dataset (Cities from India, USA, Iran)
 
-Includes climate data, pricing ranges, and category metadata
+Climate data, pricing ranges, and category metadata
 
 4-bit quantization for optimized inference
 
@@ -82,16 +91,16 @@ NVIDIA RTX 4060 GPU with CUDA 12.7
 
 📈 Progress
 Fully Implemented Features
-Personalized Day-wise Itinerary Generation: Automatically generates structured travel plans divided by day.
+Personalized Day-wise Itinerary Generation – Automatically generates structured travel plans divided by day.
 
-Budget-Aware Dataset Filtering: Filters attractions based on user-defined budget constraints.
+Budget-Aware Dataset Filtering – Filters attractions based on user-defined budget constraints.
 
-City-Restricted Recommendation System: Ensures no cross-city or irrelevant outputs are generated.
+City-Restricted Recommendation System – Ensures no cross-city or irrelevant outputs are generated.
 
 Partially Implemented Features / Work in Progress
-Cloud Deployment: Currently running locally; deployment to cloud environment planned.
+Cloud Deployment – Currently running locally; deployment to cloud environment planned.
 
-External API Integrations: Weather, hotel, and flight APIs to enhance itinerary realism.
+External API Integrations – Weather, hotel, and flight APIs to enhance itinerary realism.
 
 🔮 Future Scope
 Integration of real-time weather APIs.
@@ -105,16 +114,14 @@ Cloud-based LLM deployment.
 Advanced retrieval mechanisms for scalable systems.
 
 💸 Applications
-Personalized Travel Planning - Generates realistic, budget-aware, and structured travel itineraries.
+Personalized Travel Planning – Generates realistic, budget-aware, and structured travel itineraries.
 
-AI Travel Assistant Systems - Demonstrates practical local LLM deployment for smart recommendation engines.
+AI Travel Assistant Systems – Demonstrates practical local LLM deployment for smart recommendation engines.
 
 🛠 Project Setup
-Clone the GitHub repo.
+Clone the GitHub repository:
 
 git clone https://github.com/Rehan1604/Travel_Genie-Inheritance-.git
-Enter the project directory and install dependencies.
-
 Backend Setup:
 
 cd Travel_Genie-Inheritance-/backend
@@ -125,21 +132,19 @@ Frontend Setup:
 cd ../frontend
 npm install
 npm run dev
-Start the application.
-
-Frontend runs on local development server after npm run dev.
-Backend runs via uvicorn main:app --reload.
+Frontend runs using npm run dev.
+Backend runs using uvicorn main:app --reload.
 
 👨‍💻 Team Members
-Rehan Mehta: https://github.com/Rehan1604
+Rehan Mehta – https://github.com/Rehan1604
 
-Devansh Mehta: https://github.com/Devansh270
+Devansh Mehta – https://github.com/Devansh270
 
-Bhavya Gothi: https://github.com/Bhavya4523
+Bhavya Gothi – https://github.com/Bhavya4523
 
-Jehan Bheda: https://github.com/jehanbheda
+Jehan Bheda – https://github.com/jehanbheda
 
 👨‍🏫 Mentors
-Harsh Ogale: https://github.com/harshogale04
+Harsh Ogale – https://github.com/harshogale04
 
-Piyush Patil: https://github.com/MAVERICK-111
\ No newline at end of file
+Piyush Patil – https://github.com/MAVERICK-111
\ No newline at end of file

From 2cd0bfc701c8dd2244465a54e4091bdf1cc2f961 Mon Sep 17 00:00:00 2001
From: reanhehe <rehanmehta2000@gmail.com>
Date: Sun, 15 Feb 2026 16:48:42 +0530
Subject: [PATCH 4/6] Final corrected structured version

---
 submissions/BittenByPython_TravelGenie.md | 154 ++++++++++++++--------
 1 file changed, 96 insertions(+), 58 deletions(-)

diff --git a/submissions/BittenByPython_TravelGenie.md b/submissions/BittenByPython_TravelGenie.md
index 6c2125f..4263320 100644
--- a/submissions/BittenByPython_TravelGenie.md
+++ b/submissions/BittenByPython_TravelGenie.md
@@ -3,7 +3,7 @@
     CoC Inheritance 2025
   </a>
   <br>
-  TravelGenie: AI-Powered Smart Travel Planning System
+  TravelGenie : AI-Powered Smart Travel Planning System
 </h1>
 
 <div align="center">
@@ -26,9 +26,17 @@ By Bitten By Python
 
 </details>
 
+<a name="description"></a>
+
 ## 📝 Description
 
-TravelGenie is an AI-powered smart travel planning system that generates personalized, structured, and optimized travel itineraries using a locally deployed Large Language Model. The system solves the problem of generic and unrealistic travel suggestions by combining structured dataset filtering with context-aware LLM generation. Built using React, FastAPI, and Mistral 7B Instruct with GPU acceleration, TravelGenie delivers realistic, budget-aware, and city-restricted travel plans.
+TravelGenie is an AI-powered smart travel planning system that generates personalized, structured, and optimized travel itineraries using a locally deployed Large Language Model.
+
+It bridges the gap between generic travel suggestions and realistic, budget-aware planning by combining structured dataset filtering with contextual LLM generation. Built with React, FastAPI, and Mistral 7B Instruct running locally with GPU acceleration, TravelGenie delivers city-restricted and logically sequenced day-wise travel plans.
+
+---
+
+<a name="links"></a>
 
 ## 🔗 Links
 
@@ -37,114 +45,144 @@ TravelGenie is an AI-powered smart travel planning system that generates persona
 - [Project Screenshots/Drive](https://drive.google.com/drive/folders/1NHrsDFPxkjYD7yWH67OHcHFVX3k0ld5h?usp=drive_link)
 - Hosted Website: Not Deployed Yet
 
+---
+
+<a name="tech-stack"></a>
+
 ## 🤖 Tech-Stack
 
 ### 🏗️ System Architecture
 
 ```mermaid
-graph LR
-    A --> B
-    B --> C
-    C --> D
-    D --> E
-    E --> F
-    F --> G
-    G --> H
-    H --> I
-    I --> B
-
-    A[User_Input]
-    B[React_Frontend]
-    C[Axios_API]
-    D[FastAPI_Backend]
-    E[CSV_Filtering]
-    F[Prompt_Injection]
-    G[Mistral_7B]
-    H[GPU_Inference]
-    I[Itinerary_Output]
+graph TD
+    User[User Input] --> Frontend
+    Frontend[React Frontend] --> Backend
+    Backend[FastAPI Backend] --> Dataset
+    Dataset[CSV Dataset Filtering] --> LLM
+    LLM[Mistral 7B Instruct] --> GPU
+    GPU[RTX 4060 GPU CUDA 12.7] --> Output
+    Output[Day-wise Structured Itinerary]
 Front-end
-React.js (Vite)
+The user interface is built for clarity and interactivity, ensuring seamless itinerary generation.
 
-Axios
+Framework: React.js (Vite)
+Communication: Axios
+Storage: Browser localStorage
 
-Dynamic Chat Interface
+Key Features
+Dynamic chat-based input interface
 
-localStorage for itinerary persistence
+Real-time itinerary rendering
+
+Editable travel plans
+
+Persistent storage of generated itineraries
 
 Back-end
-FastAPI
+The backend handles dataset filtering, LLM orchestration, and structured output formatting.
+
+Framework: FastAPI
+Model Runtime: HuggingFace Transformers + Accelerate
+
+Core Components
+Dataset filtering engine (CSV-based)
+
+Prompt construction logic
 
-HuggingFace Transformers
+LLM inference pipeline
 
-Accelerate
+Structured response formatter
 
+Database & Machine Learning
+Data Layer: Structured CSV dataset (India, USA, Iran cities)
+Includes: Climate data, pricing ranges, category metadata
+
+AI Infrastructure
 Mistral 7B Instruct
 
-Database / ML
-Structured CSV dataset (Cities from India, USA, Iran)
+4-bit quantization
 
-Climate data, pricing ranges, and category metadata
+NVIDIA RTX 4060 GPU
 
-4-bit quantization for optimized inference
+CUDA 12.7
 
-NVIDIA RTX 4060 GPU with CUDA 12.7
+<a name="progress"></a>
 
 📈 Progress
 Fully Implemented Features
-Personalized Day-wise Itinerary Generation – Automatically generates structured travel plans divided by day.
+Personalized Day-wise Itinerary Generation: Automatically generates structured travel plans divided by day.
+
+Budget-Aware Filtering: Ensures recommendations align with user budget constraints.
+
+City-Restricted Recommendations: Prevents cross-city irrelevant suggestions.
 
-Budget-Aware Dataset Filtering – Filters attractions based on user-defined budget constraints.
+Climate Summary Integration: Displays contextual weather information.
 
-City-Restricted Recommendation System – Ensures no cross-city or irrelevant outputs are generated.
+Local GPU Inference: Efficient 4-bit quantized LLM execution.
 
 Partially Implemented Features / Work in Progress
-Cloud Deployment – Currently running locally; deployment to cloud environment planned.
+Cloud Deployment: Currently optimized for local GPU execution.
+
+External API Integrations: Planned integration with weather, hotel, and flight APIs.
+
+Multi-city Route Optimization: Under development.
 
-External API Integrations – Weather, hotel, and flight APIs to enhance itinerary realism.
+<a name="future-scope"></a>
 
 🔮 Future Scope
-Integration of real-time weather APIs.
+Integration of real-time travel APIs
 
-Expansion to multi-city itinerary planning.
+Multi-city itinerary optimization
 
-User authentication and persistent trip storage.
+User authentication and cloud-based trip saving
 
-Cloud-based LLM deployment.
+Deployment of scalable LLM infrastructure
 
-Advanced retrieval mechanisms for scalable systems.
+Advanced retrieval and personalization mechanisms
+
+<a name="applications"></a>
 
 💸 Applications
-Personalized Travel Planning – Generates realistic, budget-aware, and structured travel itineraries.
+Personalized Travel Planning - Structured, budget-aware itinerary generation.
+
+AI Travel Assistant Systems - Demonstrates practical local LLM deployment.
+
+Academic AI Demonstration - Showcases prompt engineering and GPU optimization.
 
-AI Travel Assistant Systems – Demonstrates practical local LLM deployment for smart recommendation engines.
+<a name="project-setup"></a>
 
 🛠 Project Setup
 Clone the GitHub repository:
 
 git clone https://github.com/Rehan1604/Travel_Genie-Inheritance-.git
-Backend Setup:
+cd Travel_Genie-Inheritance-
+Backend setup:
 
-cd Travel_Genie-Inheritance-/backend
+cd backend
 pip install -r requirements.txt
 uvicorn main:app --reload
-Frontend Setup:
+Frontend setup:
 
-cd ../frontend
+cd frontend
 npm install
 npm run dev
-Frontend runs using npm run dev.
-Backend runs using uvicorn main:app --reload.
+Frontend runs via npm run dev.
+Backend runs via uvicorn main:app --reload.
+
+<a name="team-members"></a>
 
 👨‍💻 Team Members
-Rehan Mehta – https://github.com/Rehan1604
+Rehan Mehta: https://github.com/Rehan1604
+
+Devansh Mehta: https://github.com/Devansh270
 
-Devansh Mehta – https://github.com/Devansh270
+Bhavya Gothi: https://github.com/Bhavya4523
 
-Bhavya Gothi – https://github.com/Bhavya4523
+Jehan Bheda: https://github.com/jehanbheda
 
-Jehan Bheda – https://github.com/jehanbheda
+<a name="mentors"></a>
 
 👨‍🏫 Mentors
-Harsh Ogale – https://github.com/harshogale04
+Harsh Ogale: https://github.com/harshogale04
 
-Piyush Patil – https://github.com/MAVERICK-111
\ No newline at end of file
+Piyush Patil: https://github.com/MAVERICK-111
\ No newline at end of file

From 37222d4fe15fda065f31d4903ed92f010f44d34f Mon Sep 17 00:00:00 2001
From: reanhehe <rehanmehta2000@gmail.com>
Date: Sun, 15 Feb 2026 17:07:43 +0530
Subject: [PATCH 5/6] Final formatting fix

---
 submissions/BittenByPython_TravelGenie.md | 178 +++++++++++++---------
 1 file changed, 105 insertions(+), 73 deletions(-)

diff --git a/submissions/BittenByPython_TravelGenie.md b/submissions/BittenByPython_TravelGenie.md
index 4263320..03ced45 100644
--- a/submissions/BittenByPython_TravelGenie.md
+++ b/submissions/BittenByPython_TravelGenie.md
@@ -54,135 +54,167 @@ It bridges the gap between generic travel suggestions and realistic, budget-awar
 ### 🏗️ System Architecture
 
 ```mermaid
-graph TD
-    User[User Input] --> Frontend
-    Frontend[React Frontend] --> Backend
-    Backend[FastAPI Backend] --> Dataset
-    Dataset[CSV Dataset Filtering] --> LLM
-    LLM[Mistral 7B Instruct] --> GPU
-    GPU[RTX 4060 GPU CUDA 12.7] --> Output
-    Output[Day-wise Structured Itinerary]
-Front-end
+flowchart TD
+    U[User Preferences<br/>Destination | Days | Budget | Category]
+    FE[React Frontend (Vite)]
+    API[Axios API Communication]
+    BE[FastAPI Backend]
+    FILTER[CSV Dataset Filtering]
+    PROMPT[Structured Prompt Construction]
+    LLM[Mistral 7B Instruct<br/>4-bit Quantized]
+    GPU[RTX 4060 GPU - CUDA 12.7]
+    OUT[Day-wise Structured Itinerary Output]
+
+    U --> FE
+    FE --> API
+    API --> BE
+    BE --> FILTER
+    FILTER --> PROMPT
+    PROMPT --> LLM
+    LLM --> GPU
+    GPU --> OUT
+    OUT --> FE
+```
+
+---
+
+## Front-end
+
 The user interface is built for clarity and interactivity, ensuring seamless itinerary generation.
 
-Framework: React.js (Vite)
-Communication: Axios
-Storage: Browser localStorage
+**Framework:** React.js (Vite)  
+**Communication:** Axios  
+**Storage:** Browser localStorage  
 
-Key Features
-Dynamic chat-based input interface
+### Key Features
 
-Real-time itinerary rendering
+- Dynamic chat-based input interface  
+- Real-time itinerary rendering  
+- Editable travel plans  
+- Persistent storage of generated itineraries  
 
-Editable travel plans
+---
 
-Persistent storage of generated itineraries
+## Back-end
 
-Back-end
 The backend handles dataset filtering, LLM orchestration, and structured output formatting.
 
-Framework: FastAPI
-Model Runtime: HuggingFace Transformers + Accelerate
-
-Core Components
-Dataset filtering engine (CSV-based)
+**Framework:** FastAPI  
+**Model Runtime:** HuggingFace Transformers + Accelerate  
 
-Prompt construction logic
+### Core Components
 
-LLM inference pipeline
+- Dataset filtering engine (CSV-based)  
+- Prompt construction logic  
+- LLM inference pipeline  
+- Structured response formatter  
 
-Structured response formatter
+---
 
-Database & Machine Learning
-Data Layer: Structured CSV dataset (India, USA, Iran cities)
-Includes: Climate data, pricing ranges, category metadata
+## Database & Machine Learning
 
-AI Infrastructure
-Mistral 7B Instruct
+**Data Layer:** Structured CSV dataset (India, USA, Iran cities)  
+**Includes:** Climate data, pricing ranges, category metadata  
 
-4-bit quantization
+### AI Infrastructure
 
-NVIDIA RTX 4060 GPU
+- Mistral 7B Instruct  
+- 4-bit quantization  
+- NVIDIA RTX 4060 GPU  
+- CUDA 12.7  
 
-CUDA 12.7
+---
 
 <a name="progress"></a>
 
-📈 Progress
-Fully Implemented Features
-Personalized Day-wise Itinerary Generation: Automatically generates structured travel plans divided by day.
-
-Budget-Aware Filtering: Ensures recommendations align with user budget constraints.
+## 📈 Progress
 
-City-Restricted Recommendations: Prevents cross-city irrelevant suggestions.
+### Fully Implemented Features
 
-Climate Summary Integration: Displays contextual weather information.
+* Personalized Day-wise Itinerary Generation  
+* Budget-Aware Filtering  
+* City-Restricted Recommendations  
+* Climate Summary Integration  
+* Local GPU Inference  
 
-Local GPU Inference: Efficient 4-bit quantized LLM execution.
+---
 
-Partially Implemented Features / Work in Progress
-Cloud Deployment: Currently optimized for local GPU execution.
+### Partially Implemented Features / Work in Progress
 
-External API Integrations: Planned integration with weather, hotel, and flight APIs.
+* Cloud Deployment  
+* External API Integrations  
+* Multi-city Route Optimization  
 
-Multi-city Route Optimization: Under development.
+---
 
 <a name="future-scope"></a>
 
-🔮 Future Scope
-Integration of real-time travel APIs
-
-Multi-city itinerary optimization
+## 🔮 Future Scope
 
-User authentication and cloud-based trip saving
+- Real-time travel API integration  
+- Multi-city itinerary optimization  
+- User authentication and trip storage  
+- Scalable LLM deployment  
+- Advanced personalization mechanisms  
 
-Deployment of scalable LLM infrastructure
-
-Advanced retrieval and personalization mechanisms
+---
 
 <a name="applications"></a>
 
-💸 Applications
-Personalized Travel Planning - Structured, budget-aware itinerary generation.
+## 💸 Applications
 
-AI Travel Assistant Systems - Demonstrates practical local LLM deployment.
+1. Personalized Travel Planning  
+2. AI Travel Assistant Systems  
+3. Academic AI Demonstration  
 
-Academic AI Demonstration - Showcases prompt engineering and GPU optimization.
+---
 
 <a name="project-setup"></a>
 
-🛠 Project Setup
-Clone the GitHub repository:
+## 🛠 Project Setup
 
+### Clone Repository
+
+```bash
 git clone https://github.com/Rehan1604/Travel_Genie-Inheritance-.git
 cd Travel_Genie-Inheritance-
-Backend setup:
+```
+
+### Backend Setup
 
+```bash
 cd backend
 pip install -r requirements.txt
 uvicorn main:app --reload
-Frontend setup:
+```
+
+### Frontend Setup
 
+```bash
 cd frontend
 npm install
 npm run dev
-Frontend runs via npm run dev.
-Backend runs via uvicorn main:app --reload.
+```
 
-<a name="team-members"></a>
+Frontend runs via `npm run dev`.  
+Backend runs via `uvicorn main:app --reload`.
 
-👨‍💻 Team Members
-Rehan Mehta: https://github.com/Rehan1604
+---
 
-Devansh Mehta: https://github.com/Devansh270
+<a name="team-members"></a>
 
-Bhavya Gothi: https://github.com/Bhavya4523
+## 👨‍💻 Team Members
 
-Jehan Bheda: https://github.com/jehanbheda
+* **Rehan Mehta** – https://github.com/Rehan1604  
+* **Devansh Mehta** – https://github.com/Devansh270  
+* **Bhavya Gothi** – https://github.com/Bhavya4523  
+* **Jehan Bheda** – https://github.com/jehanbheda  
+
+---
 
 <a name="mentors"></a>
 
-👨‍🏫 Mentors
-Harsh Ogale: https://github.com/harshogale04
+## 👨‍🏫 Mentors
 
-Piyush Patil: https://github.com/MAVERICK-111
\ No newline at end of file
+* **Harsh Ogale** – https://github.com/harshogale04  
+* **Piyush Patil** – https://github.com/MAVERICK-111  
\ No newline at end of file

From d5b2a6e5996a37e20d3ad66cb6da62a17d22b56d Mon Sep 17 00:00:00 2001
From: reanhehe <rehanmehta2000@gmail.com>
Date: Sun, 15 Feb 2026 17:39:17 +0530
Subject: [PATCH 6/6] Last fix

---
 submissions/BittenByPython_TravelGenie.md | 41 ++++++++++++-----------
 1 file changed, 21 insertions(+), 20 deletions(-)

diff --git a/submissions/BittenByPython_TravelGenie.md b/submissions/BittenByPython_TravelGenie.md
index 03ced45..4fb0064 100644
--- a/submissions/BittenByPython_TravelGenie.md
+++ b/submissions/BittenByPython_TravelGenie.md
@@ -55,25 +55,26 @@ It bridges the gap between generic travel suggestions and realistic, budget-awar
 
 ```mermaid
 flowchart TD
-    U[User Preferences<br/>Destination | Days | Budget | Category]
-    FE[React Frontend (Vite)]
-    API[Axios API Communication]
-    BE[FastAPI Backend]
-    FILTER[CSV Dataset Filtering]
-    PROMPT[Structured Prompt Construction]
-    LLM[Mistral 7B Instruct<br/>4-bit Quantized]
-    GPU[RTX 4060 GPU - CUDA 12.7]
-    OUT[Day-wise Structured Itinerary Output]
-
-    U --> FE
-    FE --> API
-    API --> BE
-    BE --> FILTER
-    FILTER --> PROMPT
-    PROMPT --> LLM
-    LLM --> GPU
-    GPU --> OUT
-    OUT --> FE
+U["User Preferences\nDestination | Days | Budget | Category"]
+FE["React Frontend (Vite)"]
+API["Axios API Communication"]
+BE["FastAPI Backend"]
+FILTER["CSV Dataset Filtering"]
+PROMPT["Structured Prompt Construction"]
+LLM["Mistral 7B Instruct\n4-bit Quantized"]
+GPU["RTX 4060 GPU - CUDA 12.7"]
+OUT["Day-wise Structured Itinerary Output"]
+
+U --> FE
+FE --> API
+API --> BE
+BE --> FILTER
+FILTER --> PROMPT
+PROMPT --> LLM
+
+LLM --- GPU
+LLM --> OUT
+OUT --> FE
 ```
 
 ---
@@ -217,4 +218,4 @@ Backend runs via `uvicorn main:app --reload`.
 ## 👨‍🏫 Mentors
 
 * **Harsh Ogale** – https://github.com/harshogale04  
-* **Piyush Patil** – https://github.com/MAVERICK-111  
\ No newline at end of file
+* **Piyush Patil** – https://github.com/MAVERICK-111
\ No newline at end of file