Audio Notes App
Date of creation: 2024-10-03
Project description
The goal of the project was to create the first AI-powered application. To do this, I used two LLM models from OpenAI:
whisper-1 (speech -> text) and text-embeddings-3-large (text -> embeddings). Main functionalities
- Recording and listening to voice notes
- Transcription of voices into text using AI
- Ability to collect notes in the QDrant database
- Semantic data search using the text processing algorithm on embeddings and finding similarities based on Cosinus Similarity
Skills
- Python
- QDrant
- OpenAI embeddings
- OpenAI whisper-1
- Streamlit
- Dotenv
- PyDub
- io
- md5
Sample photos
Application usage
The application has been deployed on the Streamlit Community App helps me generate notes more easily and most importantly enables contextual search using AI.