Scholarship RAG Chatbot

• 

  Analytics Dashboard

• 

  Show the Eligibility Criteria

• 

  Show the Language Support

• 

  Show the Gender

• 

  Show the Course

• 

  Show the Family income

• 

  Question (Expected Ans : English)

• 

  Click the Check Eligibiliy and Final Output

• 

  Chatbot Interface

• 

  Valid Answer (Tamil)

• 

  Searching the answer

• 

  Question (Expected Ans : Tamil)

• 

  Valid Answer (English)

Inspiration

Many students miss out on scholarships due to lack of awareness and difficulty in accessing reliable, up-to-date information. We wanted to build a smart system that provides real-time, accurate, and personalized scholarship guidance.

What it does

Scholarship RAG Chatbot is an AI-powered assistant that helps students discover scholarships in real time. It understands user queries, retrieves the most relevant and up-to-date scholarship data, and provides accurate, personalized responses to guide students through opportunities and application processes.

How we built it

We built the system using a Retrieval-Augmented Generation (RAG) architecture. Real-time scholarship data is processed and stored in a vector database using Sentence Transformers for semantic embeddings.

LangChain is used to manage the retrieval pipeline, ensuring that relevant scholarship information is fetched based on user queries. The retrieved data is then passed to a Groq-powered LLM, which generates accurate and context-aware responses.

This combination allows the chatbot to deliver fast, relevant, and up-to-date answers instead of relying only on static or pre-trained knowledge.

Challenges we ran into

Handling real-time scholarship data and ensuring its consistency was a major challenge. Optimizing semantic search using embeddings for accurate retrieval also required careful tuning. Another challenge was integrating LangChain with the Groq LLM efficiently to maintain low latency and high response quality.

Accomplishments that we're proud of

We successfully built a real-time AI chatbot that uses advanced RAG architecture to deliver accurate scholarship recommendations. The system provides faster and more relevant results compared to traditional search methods, making scholarship discovery easier and more efficient for students.

What we learned

We gained practical experience in building RAG-based systems, working with LangChain pipelines, and implementing semantic search using Sentence Transformers. We also learned how to integrate high-performance LLMs like Groq for fast and scalable AI responses.

What's next for Scholarship RAG Chatbot

We plan to enhance the system by integrating more real-time data sources, improving personalization using user profiles, and deploying it as a scalable web application. Future improvements include multilingual support, advanced filtering, and a mobile-friendly interface to reach a wider audience.

Built With

• chromadb
• dotenv
• groq
• langchain
• pandas
• pypdf
• python
• sentencetransformer
• streamlit