Worked on an RLHF (Reinforcement Learning from Human Feedback) pipeline focused on dataset creation, data annotation, and model evaluation. My role involved designing and curating high-quality prompt datasets, reviewing AI-generated responses, and providing structured feedback based on accuracy, relevance, safety, and helpfulness. Contributed to improving model performance by ensuring consistent evaluation standards and high-quality human feedback for training alignment and refinement.
1
181
Intelligent Q&A assistant for farmers, powered by retrieval-augmented generation.
Curated 100+ agricultural documents and generated 1,000+ semantic knowledge chunks
Embedded using Sentence Transformers and indexed in ChromaDB for vector retrieval
Integrated Groq-hosted Llama models for accurate, context-grounded responses
Built and deployed a publicly accessible Streamlit application
Optimized retrieval through chunk-size tuning and prompt engineering
Validated retrieval and response quality against a curated test question set
0
33
AI-Powered PDF Data Extraction
Organizations often face challenges in extracting useful information from a large volume of unstructured data in PDF format.
The lack of standardized data formats makes it difficult to efficiently retrieve relevant information, when dealing with documents.
The goal of this solution was to develop a flexible automated solution that allows users to specify entities to extract, enabling quick and accurate data retrieval from diverse PDFs.
The demo is available on request.
AuraExtract — Intelligent Invoice & Receipt Data Extractor
The extraction engine uses intelligent regex pattern matching that handles real-world invoice layouts — column-per-line PDF formats, inline tabular formats, and plain text documents. It detects 10 fields automatically and parses up to 20 line items per invoice.
Supports PDF, TXT, and DOCX formats. Includes a raw text preview panel so users can verify exactly what the engine is reading. CSV export includes both the summary fields and full line items table — ready to open directly in Excel.
Pure Python. Zero external dependencies beyond pypdf for PDF reading.