Built a highly scalable Retrieval-Augmented Generation (RAG) chatbot designed to interact with private datasets/PDFs. Unlike standard LLMs, this system minimizes hallucinations by retrieving real-time context from a local knowledge base before generating responses.
Key Features:
Semantic Search: Implemented Vector Embeddings to perform high-speed similarity searches across thousands of document chunks.
Smart Retrieval: Integrated a retrieval pipeline using LangChain to fetch the most relevant context for user queries.
Source Citation: Configured the bot to provide source references from documents, ensuring data transparency and accuracy.
Optimized Performance: Used FAISS/Chromadb for efficient vector storage and retrieval.
1
20
Developed a high-precision Resume Parser using a custom-trained RoBERTa model, specifically fine-tuned for Named Entity Recognition (NER) tasks. This tool automates the extraction of critical information from unstructured resumes with deep learning accuracy.
Key Features:
NER-Based Extraction: Accurately identifies entities like Name, Experience, Skills, Education, and Contact Info.
RoBERTa Architecture: Leverages Transformer-based embeddings for superior contextual understanding compared to traditional parsers.
JSON Output: Seamlessly converts complex resume layouts into structured JSON format for easy database integration and ATS (Applicant Tracking System) workflows.
High Accuracy: Trained to handle diverse formatting and professional jargon.
0
22
Developed an automated pipeline to handle bulk recruitment workflows. This AI-powered tool processes multiple PDF resumes simultaneously, using advanced parsing to extract candidate details with high accuracy. It intelligently structures unstructured resume data into a clean, downloadable CSV format, capturing essential metrics like skills, experience, and contact info without manual data entry.
0
92
Built an intelligent RAG-based chatbot designed to simplify complex financial analysis. In the project demo, the AI deep-dives into Apple’s annual reports, extracting key fiscal metrics and providing real-time insights through natural language queries. It transforms dense financial filings into actionable data using advanced document retrieval
0
102