Design a planning agent that can synthesize a pipeline from a natural language specification primarily targeting data engineer persona. In progress
Feedback forms could be descriptive and sometimes difficult to read through all the document and see the result, here we will use generative AI to summarize the result with Positive or negative feedback score to make it easy to understand. In progress
Any project document, HLD or a Contract document are quite a big and difficult to go through all the pages. Also difficult to search if we are looking for any specific answer from multiple sections. Hence requirement is to generate a summarize which will include the pictures in the document if any. Require to use generative AI model and train with some set of specific document to get better accuracy. User typed question and Answer will be fed to SVM model to generate prediction score. In progress
Organizations are serious on software that are use by employees as Unauthorized software might lead to huge fine from the client, hence identifying software valid License, cost, if safe to use is very important for any organization to know. Currently there is no such tool to generate prediction in bulk or individual in compact way. So this Project will Predict software license and other additional details using generative AI from a given software name with minimum details either from a csv or from the UI. In progress
This module is designed to automatically remove license headers and commented code from source code files. It will support multiple programming languages and can be easily extended to accommodate new ones. The module will be integrated into the data preprocessing pipeline to generate a clean code datasets to train Code LLM. In progress
Monitoring applications on the cloud provides a stream of irregularly occurring events. These streams often involve events multiple types of events to co-occur. For example, a disk utilisation event, followed by a database query execution event and so on. In this work, we explore the possibilities of using large language models to infer patterns in the stream of events and predict future steam of event. The goal is to identify if there is a possibility of anomalous events in the future to take proactive actions. In progress
To determine the Handwriting of a user to analyze PSYCHOLOGICAL behaviour In progress
To develop techniques using state-of-the-art AI methods to enrich the experience around LLM usage. Skills Required: Python, ML, DL, LLMs, Hugging Face, exposure to UI development In progress
Experiment with Java Mircroservice and create reusable flows using Watson X prompt engineering In progress
Sentiment analysis to identify emotional tone behind a body of text. In progress