Web app enabling users to either record or upload audio files. Then utilizing OpenAI API (Whisper, GPT4) generates transcriptions, summaries, fact checks, sentiment analysis, and text metrics. Users can also intelligently chat about their transcriptions with a GPT4 chatbot. Data is stored relationally in SQLite and also vectorized in Pinecone.
Python
OpenAI Whisper Audio Transcription and Summarization Chatbot
Description
Web app enabling users to record or upload audio files, utilizing OpenAI API (Whisper, GPT-4) and custom agents/ tools with LangChain to generate transcriptions, summaries, fact checks, sentiment analysis, and text metrics. Additionally, users can interact with a GPT4 chatbot about their transcriptions. Data is stored in an SQLite DB for user authentication and later retrieval. Data is also embedded into a Pinecone vector DB, for LLM purposes.
Technologies Utilized
Programming Languages: Python, HTML, CSS
Web Framework: Streamlit
Audio Transcription: OpenAI API (Whisper)
LLM: OpenAI API (GPT-4), LangChain
Text Analysis: NLTK
Vector DB: Pinecone
Relational DB and User Auth: SQLite
App V12: Implemented Sidebar for LLM Temperature and Model Selection & Much Improved Code Modularity
App V10: Implemented a Pinecone DB utilizing OpenAI Embedding, and and implemented as optional reference tool for LangChain Zero Shot React Description agent.