ReactJS Learning Assistant Created with ReactJS Typescript Chromadb by FlaskArchitect

ReactJS Learning Assistant Created with ReactJS Typescript Chromadb by FlaskArchitect now available on GitHub JupyterJones message for Link
cd reactjs-learning-assistant
This application serves as an intelligent learning assistant focused on ReactJS, FastAPI, testing (Jest, Postman), and potentially finance concepts, leveraging AI and persistent storage.
Core Features:
AI-Powered Q&A:
Ask questions related to ReactJS, FastAPI, testing tools, and other relevant topics directly to the Gemini AI model.
Receive concise explanations, context-aware answers, and code examples from the AI.
Persistent Knowledge Base & History:
History Tracking: Every question asked via the primary "ask" feature and its corresponding AI answer is automatically saved to a historical log (SQLite database).
History Browse: View the complete Q&A history, sorted chronologically.
History Management: View and update specific Q&A pairs stored in the history.
Vector Storage: Questions and answers are also embedded and stored in a ChromaDB vector database, enabling semantic understanding and retrieval.
File Archive: AI-generated answers are automatically saved as individual text files for easy reference outside the app.

Semantic Search & Summarization:
Search the entire knowledge base (built from saved Q&A and seeded text files) using natural language queries.
The system retrieves the most relevant paragraphs or Q&A entries from the vector store based on semantic similarity.
The retrieved information is then synthesized by the Gemini AI into a comprehensive summary or direct answer to the user's search query.
Contextual Conversation Generation:
Initiate a simulated conversation (between characters "Jack" and "Esperanza") based on a specific starting prompt or question.
The AI uses relevant information retrieved from the vector knowledge base (ChromaDB) to generate a natural-sounding and informative dialogue related to the prompt.
Generated conversations are saved separately for review.
Note Taking & File Management:
Create, read, update, and delete simple text files directly within the application – useful for taking notes or storing code snippets.
List all available notes/text files, conveniently sorted by modification date (newest first).
Knowledge Base Seeding:
Populate the vector knowledge base (ChromaDB) by "seeding" the content of selected text files from the notes/file management section.
The system automatically splits the selected file(s) into paragraphs and adds each paragraph as a searchable document to ChromaDB.
Financial Data Display:
Retrieve and display historical stock market data (Open, High, Low, Close, Volume) for specific stock tickers from a dedicated database. (Assumes this database is populated separately).
Debugging Tools:
Provides an endpoint to check the status of the ChromaDB vector store, showing the number of items and a sample of the stored data.
Essentially, it's a tool to facilitate learning by allowing users to ask questions, get AI-powered answers, build a searchable knowledge base from those interactions and external notes, and explore concepts through generated conversations and financial data lookup.