AI Projects

Generates questions that answer a chunk, and stores embeddings with text location for precise citations. Uses Python, OpenAI, embeddings, RAG using PineCone vector database, and FastAPI. Enables fine-grained, citation-accurate QA by indexing embeddings with exact source text offsets, improving trust and explainability.

Nov 2025|  View on GitHub

Implemented RAG. Tuned retrieval precision/recall using re-ranker models, and handled citations. Uses Python, LangChain, embeddings, PineCone vector database, re-ranker model, StreamLit, & FastAPI. Improves financial QA reliability through optimized RAG pipeline for investment education.

Nov 2025|  View on GitHub

An AI agent tool search engine for scalable agents using tool selection based on contextual relevance. Achieved 95% reduction in token usage, latency, and input token cost during evaluation.

Dec 2025|  View on GitHub

Introduces an Agent Safety benchmark, a metric, a dataset, and a classifier model. Authored a paper. Classifies the actions of an AI agent as harmful or safe using Deep Learning, NLP, and PyTorch. Supervises Agents for Data Privacy, Security, Ethical Considerations, Compliance, regulations. Provides a measurable, model-driven safety layer for autonomous agents with research-backed validation.

Dec 2025|  View on GitHub

Streamlines the development and deployment of large-scale Generative AI projects, ensuring best practices in code structure and documentation. Accelerates enterprise GenAI adoption by standardizing architecture, scalability, and maintainability.

Dec 2025|  View on GitHub

Leverages LangChain and LangGraph to dynamically route reasoning tasks to the most appropriate LLMs’ reasoning strategy based on user prompts. Uses LangSmith for LLM observability, monitoring. Enhances reasoning quality and cost efficiency by adaptive strategy selection at inference time.

Oct 2025|  View on GitHub

Classifies large datasets into relevant and irrelevant data using NLP and Transformers, creating a pure dataset for LLM training or fine-tuning.

Oct 2025|  View on GitHub

Evaluates LLMs using manipulated prompts to stress-test the robustness of LLMs using Python. Systematically stress-tests LLMs to uncover failure modes beyond standard benchmark evaluations.

Sep 2025|  View on GitHub

A full-stack AI+Web3 system that is a blockchain-based decentralized social platform for gamers that includes AI-generated images for games and minting NFTs for active users.

Sep 2025|  View on GitHub

Used re-planning and controlled retrieval to gain accuracy over CoT and RAG by implementing prompting, Transformer-based LLMs, NLP, evaluation and integration of LLM capabilities. Authored a research paper. Uses Python, OpenAI API, Transformers, a fine-tuned LLM, NLP, CoT, reasoning, RAG, and APIs. Demonstrates superior reasoning accuracy via structured replanning and retrieval control using re-rankers.

July 2025|  View on GitHub

A framework that enables versioning for agents, which allows the updation of versions.

Nov 2024|  View on GitHub

Trend-based SEO to make the content stay relevant to the users despite rapid changes in trends.

Oct 2024|  View on GitHub

Instead of ML, the paper uses the process of an LLM learning a dataset for context-aware classification decisions based on relevant data like RAG. Outcome: The predictions were accurate and transparent, as the system generates the reason behind each prediction.

Oct 2024|  View on GitHub

Enables dynamic set of tools for agents using a database.

Sep 2024|  View on GitHub

Filters unwanted text using LLMs and uses Vector DB and Retrieval-Augmented Generation (RAG).

July 2024|  View on GitHub

Uses multimodal LLMs to monitor camera footage and create alerts on detection of suspicious threats.

May 2024|  View on GitHub

Investigates the impact of three message roles, "system," "user," and "assistant," on responses.

Mar 2024|  View on GitHub

Automated Prompt Engineering and testing to ensure perfect prompts are crafted.

Jan 2024|  View on GitHub

Flags harmful actions by agents before execution.

Dec 2023|  View on GitHub

Utilizes a large LLM to answer complex queries and supervise a smaller LLM.

Oct 2023|  View on GitHub

Investigates the influence of the seed value that is used to control the randomness of an LLM.

Aug 2023|  View on GitHub

Investigates the impact of errors such as grammatical errors and spelling errors on LLM accuracy.

Jun 2023|  View on GitHub

Automates the Prompt Engineering of hard prompts and the testing process to ensure perfect prompts are crafted.

Apr 2023|  View on GitHub

Since the training data of LLM is mostly in English, the experiments finds the accuracy of various tasks using prompts in different languages.

Feb 2023|  View on GitHub

Used LangChain, RAG, and ChainLit (to host web page)

View on GitHub

Used LangChain, Selenium, and Gradio (for hosting)

View on GitHub

Used LangChain, and StreamLit (for hosting)

View on GitHub

Used LangChain and Gradio (for hosting)

View on GitHub

Used LangChain Agents for various tasks like searching online, fetching weather, math operations, running python code, etc.

View on GitHub

Useful to chat with data to get useful insights to increase the profitability of the companies. Generated synthetic data using LLMs

View on GitHub

Used LMDeploy and FastAPI to deploy the model by emulating OpenAI API

View on GitHub

Used embeddings and neural networks to classify the sentiment of IMDB comments (positive/negative) using PyTorch.

May 2025| View on GitHub