My Journal AI

A chatbot built specifically for personal journals and diary entries. You upload your journal files, and then you can ask questions about your own writing — like "how was I feeling last week?", "what did I write about work in June?", or "what goals did I set this month?"

This is not a general-purpose chatbot. It is built around journaling — it understands emotions, dates, and entry types (reflections, goals, memories, dreams, etc.) in your journal.

What it does

• Upload your journal or diary files (PDF, DOCX, DOC, TXT)
• Ask questions about your own entries in plain language
• Detects emotions in each journal entry (joy, anxiety, sadness, etc.)
• Understands time-based queries like "last week", "yesterday", "this month"
• Classifies entries by type: reflection, goal, gratitude, memory, dream, event, insight
• Supports semantic search so you can find entries by meaning, not just keywords

How it works

1. You upload a document
2. The system splits it into chunks and converts them into vectors
3. When you ask a question, it finds the most relevant chunks
4. An AI model generates an answer based on those chunks

Requirements

• Python 3.9 or higher
• Ollama installed locally with the Mistral model
• Qdrant running locally or on a remote server
• Docker (to run Qdrant)
• Tesseract OCR (only needed for scanned PDFs)

Setup

1. Clone the repo:

   git clone <your-repo-url>
   cd Chatbot
   

2. Create and activate a virtual environment:

   python -m venv venv
   

   On Windows:

   venv\Scripts\activate
   

   On macOS or Linux:

   source venv/bin/activate
   

3. Install dependencies:

   pip install -r requirements.txt
   

4. Create a .env file in the root folder with these values:

   OLLAMA_BASE_URL=http://localhost:11434
   QDRANT_URL=http://localhost:6333
   

5. Start Qdrant using Docker:

   docker run -p 6333:6333 -p 6334:6334 qdrant/qdrant
   

6. Pull and start the embedding model in Ollama:

   ollama run nomic-embed-text
   

7. Start the server from the project root:

   uvicorn rag_chatbot.backend.main:app --reload
   

Open http://127.0.0.1:8000/docs in your browser to see and test all API endpoints.

Project structure

Chatbot/
├── rag_chatbot/
│   └── backend/
│       ├── api/               # API endpoints (chat, upload, search, status)
│       ├── generation/        # Response generation logic
│       ├── ingestion/         # Document processing pipeline
│       ├── query_processing/  # Query preprocessing (LLM and rule-based)
│       ├── retrieval/         # Search and retrieval logic
│       └── utils/             # Helper functions
├── requirements.txt
└── setup_project.py

API endpoints

Endpoint	Method	Description
/upload/	POST	Upload a document
/chat/	POST	Ask a question
/search/semantic	POST	Search by meaning
/search/metadata	POST	Filter by document properties
/search/hybrid	POST	Combine semantic and metadata search
/health	GET	Check if the server is running
/database	GET	Database stats
/system	GET	Full system status

Running tests

pytest