Unified AI Conversational Platform Using Streamlit, this project basically uses Gemini API key as the base model, where user can upload an image, document or audio file(WAV). Based on the extracted content, user can chat and get the results, this project a conversational chatbot where user can ask related to the uploaded files.
The "Unified AI Conversational Platform" is an integrated solution designed to simplify the interaction between users and diverse types of data through advanced AI technologies. The platform features three core modules: (1) Text Extraction—allowing users to upload PDF or text files, from which relevant text is automatically extracted for further processing; (2) Speech-to-Text Conversion—enabling users to record or upload audio, which is then converted into text; and (3) Chatbot Interface—a conversational agent powered by the Google Gemini model that responds to user queries based on the extracted text. The platform is built using Streamlit for seamless user experience and interaction. Once the text is extracted from either the file or audio, it is passed to the Google Gemini API, where the AI model processes the data and provides relevant answers to user queries. This unified approach to text and audio processing offers an intuitive and efficient method for leveraging AI-powered conversation across a wide range of data sources.
Keywords: AI, Conversational Platform, Text Extraction, Speech-to-Text, Google Gemini, Streamlit, Chatbot, Audio Processing, PDF Parsing.
NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.

H/W CONFIGURATION:
Hard Disk - 160GB
Key Board - Standard Windows Keyboard
Mouse - Two or Three Button Mouse
Monitor - SVGA
RAM - 8GB
S/W CONFIGURATION:
• Operating System : Windows 7/8/10
• Server side Script : HTML, CSS, Bootstrap & JS
• Programming Language : Python
• Libraries : Streamlit, Google gemini, PyPDF2.
• IDE/Workbench : VS Code
• Technology : Python 3.8+
• Server Deployment : Xampp Server