Capstone Web Design Project -- 2
Budget: ₹600 – ₹1,500 INR
1. Set up the project foundation – Initialize the project repository, environment
configuration, and basic application structure for the Generative AI system.
2. Design the user interaction layer – Create a simple interface or API that allows users
to upload documents and ask natural language questions.
3. Implement document ingestion – Enable uploading and processing of enterprise
documents in multiple formats such as PDF, TXT, CSV, or Excel.
4. Prepare data for semantic search – Convert processed document content into
chunks suitable for embedding and retrieval.
5. Build a vector-based knowledge store – Generate embeddings and store them in a
vector database to support semantic similarity search.
6. Implement intelligent document retrieval – Retrieve the most relevant document
content based on user queries using similarity search.
7. Develop a Retrieval-Augmented Generation pipeline – Combine retrieved document
context with an LLM to generate accurate, grounded responses.
8. Implement agent-based reasoning – Create one or more AI agents that plan,
retrieve, reason, and generate responses using available tools.
9. Add reliability and safety controls – Handle errors, validate inputs, and apply
guardrails to reduce hallucinations and unsafe outputs.
10. Deploy and document the solution – Deploy the application and provide
documentation explaining the architecture, workflow, and limitations.
configuration, and basic application structure for the Generative AI system.
2. Design the user interaction layer – Create a simple interface or API that allows users
to upload documents and ask natural language questions.
3. Implement document ingestion – Enable uploading and processing of enterprise
documents in multiple formats such as PDF, TXT, CSV, or Excel.
4. Prepare data for semantic search – Convert processed document content into
chunks suitable for embedding and retrieval.
5. Build a vector-based knowledge store – Generate embeddings and store them in a
vector database to support semantic similarity search.
6. Implement intelligent document retrieval – Retrieve the most relevant document
content based on user queries using similarity search.
7. Develop a Retrieval-Augmented Generation pipeline – Combine retrieved document
context with an LLM to generate accurate, grounded responses.
8. Implement agent-based reasoning – Create one or more AI agents that plan,
retrieve, reason, and generate responses using available tools.
9. Add reliability and safety controls – Handle errors, validate inputs, and apply
guardrails to reduce hallucinations and unsafe outputs.
10. Deploy and document the solution – Deploy the application and provide
documentation explaining the architecture, workflow, and limitations.