Streamlit_Toolkit

This is a repository created by Google Developer Students Club tech gurus demonstrating examples of using a Streamlit library for different tasks. If you wish to go beyond what's here we suggest you visit Streamlit documentation which is also amazing! https://docs.streamlit.io/

• What is streamlit? Streamlit is an open-source Python framework designed to rapidly build and share beautiful web applications for data science and machine learning. It allows you to create interactive, user-friendly dashboards and apps with minimal effort, all in pure Python.

In order to try using all the different functionalities (without the struggle of installing different libraries one at a time), we suggest you run

pip install -r requirements.txt

Markdown and HTML Elements:

Introducing Markdown and HTML support. Add headers, bullet points, and images to provide context. Enhancing app content.

To use it run

streamlit run markdown_and_html.py

Interactive Widgets:

Showcasing Streamlit widgets (sliders, dropdowns). Users interact with widgets to adjust values.

• Focus: Creating responsive user interfaces.

To use it run

streamlit run widgets.py

Image Capturing and Hand detection:

Extending Streamlit to handle images. Users upload an image, and the app detects hand landmark. Can be repurposed to process images in any other way.

• Focus: Image processing and display.

To use it run

streamlit run image_capturing_hand_detection.py

Chatbot Interface (genAI):

An interactive chatbot using Streamlit and OpenAI. Users type messages, and the chatbot responds with dynamically generated answers.

• Focus: Real-time conversational UI with genAI UI

To use it run

streamlit run chatbot_interface.py

Sentiment Analysis Dashboard:

An app that predicts sentiment (positive, negative, neutral) from user input text.

• Focus: Integrating sentiment analysis libraries (e.g., TextBlob) with Streamlit.

To use it run

streamlit run sentiment_analysis.py

Session State and caching (several tabs open):

Keeping session state variables.

To use it run

streamlit run session_state_and_chaching.py

Named Entity Recognition (NER) Explorer - work in progress..:

• Task: Develop an app that highlights entities (names, dates, locations) in user-provided text.
• Focus: Using NLP libraries (e.g., spaCy) with Streamlit.