sdf

- Add validateToken() method to userService to check if refresh token is valid
- Automatically redirect to chat if user already has valid session
- Show 'Checking authentication...' loading state during validation
- Prevents unnecessary login if user is already authenticated
- Improves UX by skipping login screen when not needed

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

.dockerignore

@@ -0,0 +1,16 @@
+.git
+.gitignore
+README.md
+.env
+.DS_Store
+chromadb/
+chroma_db/
+raggr-frontend/node_modules/
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+.Python
+.venv/
+venv/
+.pytest_cache/

.env.example

@@ -0,0 +1,28 @@
+# Database Configuration
+# Use DATABASE_PATH for simple relative/absolute paths (e.g., "database/raggr.db" or "dev.db")
+# Or use DATABASE_URL for full connection strings (e.g., "sqlite://database/raggr.db")
+DATABASE_PATH=database/raggr.db
+# DATABASE_URL=sqlite://database/raggr.db
+
+# JWT Configuration
+JWT_SECRET_KEY=your-secret-key-here
+
+# Paperless Configuration
+PAPERLESS_TOKEN=your-paperless-token
+BASE_URL=192.168.1.5:8000
+
+# Ollama Configuration
+OLLAMA_URL=http://192.168.1.14:11434
+OLLAMA_HOST=http://192.168.1.14:11434
+
+# ChromaDB Configuration
+CHROMADB_PATH=/path/to/chromadb
+
+# OpenAI Configuration
+OPENAI_API_KEY=your-openai-api-key
+
+# Immich Configuration
+IMMICH_URL=http://192.168.1.5:2283
+IMMICH_API_KEY=your-immich-api-key
+SEARCH_QUERY=simba cat
+DOWNLOAD_DIR=./simba_photos

.python-version

@@ -0,0 +1 @@
+3.13

Dockerfile

@@ -0,0 +1,48 @@
+FROM python:3.13-slim
+
+WORKDIR /app
+
+# Install system dependencies, Node.js, Yarn, and uv
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    curl \
+    && curl -fsSL https://deb.nodesource.com/setup_20.x | bash - \
+    && apt-get install -y nodejs \
+    && npm install -g yarn \
+    && rm -rf /var/lib/apt/lists/* \
+    && curl -LsSf https://astral.sh/uv/install.sh | sh
+
+# Add uv to PATH
+ENV PATH="/root/.local/bin:$PATH"
+
+# Copy dependency files
+COPY pyproject.toml ./
+
+# Install Python dependencies using uv
+RUN uv pip install --system -e .
+
+# Copy application code
+COPY *.py ./
+COPY blueprints ./blueprints
+COPY migrations ./migrations
+COPY startup.sh ./
+RUN chmod +x startup.sh
+
+# Copy frontend code and build
+COPY raggr-frontend ./raggr-frontend
+WORKDIR /app/raggr-frontend
+RUN yarn install && yarn build
+WORKDIR /app
+
+# Create ChromaDB and database directories
+RUN mkdir -p /app/chromadb /app/database
+
+# Expose port
+EXPOSE 8080
+
+# Set environment variables
+ENV PYTHONPATH=/app
+ENV CHROMADB_PATH=/app/chromadb
+
+# Run the startup script
+CMD ["./startup.sh"]

MIGRATIONS.md

@@ -0,0 +1,54 @@
+# Database Migrations with Aerich
+
+## Initial Setup (Run Once)
+
+1. Install dependencies:
+```bash
+uv pip install -e .
+```
+
+2. Initialize Aerich:
+```bash
+aerich init-db
+```
+
+This will:
+- Create a `migrations/` directory
+- Generate the initial migration based on your models
+- Create all tables in the database
+
+## When You Add/Change Models
+
+1. Generate a new migration:
+```bash
+aerich migrate --name "describe_your_changes"
+```
+
+Example:
+```bash
+aerich migrate --name "add_user_profile_model"
+```
+
+2. Apply the migration:
+```bash
+aerich upgrade
+```
+
+## Common Commands
+
+- `aerich init-db` - Initialize database (first time only)
+- `aerich migrate --name "description"` - Generate new migration
+- `aerich upgrade` - Apply pending migrations
+- `aerich downgrade` - Rollback last migration
+- `aerich history` - Show migration history
+- `aerich heads` - Show current migration heads
+
+## Docker Setup
+
+In Docker, migrations run automatically on container startup via the startup script.
+
+## Notes
+
+- Migration files are stored in `migrations/models/`
+- Always commit migration files to version control
+- Don't modify migration files manually after they're created

add_user.py

@@ -0,0 +1,146 @@
+# GENERATED BY CLAUDE
+
+import os
+import sys
+import uuid
+import asyncio
+from tortoise import Tortoise
+from blueprints.users.models import User
+
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# Database configuration with environment variable support
+DATABASE_PATH = os.getenv("DATABASE_PATH", "database/raggr.db")
+DATABASE_URL = os.getenv("DATABASE_URL", f"sqlite://{DATABASE_PATH}")
+
+print(DATABASE_URL)
+
+
+async def add_user(username: str, email: str, password: str):
+    """Add a new user to the database"""
+    await Tortoise.init(
+        db_url=DATABASE_URL,
+        modules={
+            "models": [
+                "blueprints.users.models",
+                "blueprints.conversation.models",
+            ]
+        },
+    )
+
+    try:
+        # Check if user already exists
+        existing_user = await User.filter(email=email).first()
+        if existing_user:
+            print(f"Error: User with email '{email}' already exists!")
+            return False
+
+        existing_username = await User.filter(username=username).first()
+        if existing_username:
+            print(f"Error: Username '{username}' is already taken!")
+            return False
+
+        # Create new user
+        user = User(
+            id=uuid.uuid4(),
+            username=username,
+            email=email,
+        )
+        user.set_password(password)
+        await user.save()
+
+        print("✓ User created successfully!")
+        print(f"  Username: {username}")
+        print(f"  Email: {email}")
+        print(f"  ID: {user.id}")
+        return True
+
+    except Exception as e:
+        print(f"Error creating user: {e}")
+        return False
+    finally:
+        await Tortoise.close_connections()
+
+
+async def list_users():
+    """List all users in the database"""
+    await Tortoise.init(
+        db_url=DATABASE_URL,
+        modules={
+            "models": [
+                "blueprints.users.models",
+                "blueprints.conversation.models",
+            ]
+        },
+    )
+
+    try:
+        users = await User.all()
+        if not users:
+            print("No users found in database.")
+            return
+
+        print(f"\nFound {len(users)} user(s):")
+        print("-" * 60)
+        for user in users:
+            print(f"Username: {user.username}")
+            print(f"Email: {user.email}")
+            print(f"ID: {user.id}")
+            print(f"Created: {user.created_at}")
+            print("-" * 60)
+
+    except Exception as e:
+        print(f"Error listing users: {e}")
+    finally:
+        await Tortoise.close_connections()
+
+
+def print_usage():
+    """Print usage instructions"""
+    print("Usage:")
+    print("  python add_user.py add <username> <email> <password>")
+    print("  python add_user.py list")
+    print("\nExamples:")
+    print("  python add_user.py add ryan ryan@example.com mypassword123")
+    print("  python add_user.py list")
+    print("\nEnvironment Variables:")
+    print("  DATABASE_PATH  - Path to database file (default: database/raggr.db)")
+    print("  DATABASE_URL   - Full database URL (overrides DATABASE_PATH)")
+    print("\n  Example with custom database:")
+    print("  DATABASE_PATH=dev.db python add_user.py list")
+
+
+async def main():
+    if len(sys.argv) < 2:
+        print_usage()
+        sys.exit(1)
+
+    command = sys.argv[1].lower()
+
+    if command == "add":
+        if len(sys.argv) != 5:
+            print("Error: Missing arguments for 'add' command")
+            print_usage()
+            sys.exit(1)
+
+        username = sys.argv[2]
+        email = sys.argv[3]
+        password = sys.argv[4]
+
+        success = await add_user(username, email, password)
+        sys.exit(0 if success else 1)
+
+    elif command == "list":
+        await list_users()
+        sys.exit(0)
+
+    else:
+        print(f"Error: Unknown command '{command}'")
+        print_usage()
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

aerich_config.py

@@ -0,0 +1,20 @@
+import os
+
+# Database configuration with environment variable support
+# Use DATABASE_PATH for relative paths or DATABASE_URL for full connection strings
+DATABASE_PATH = os.getenv("DATABASE_PATH", "database/raggr.db")
+DATABASE_URL = os.getenv("DATABASE_URL", f"sqlite://{DATABASE_PATH}")
+
+TORTOISE_ORM = {
+    "connections": {"default": DATABASE_URL},
+    "apps": {
+        "models": {
+            "models": [
+                "blueprints.conversation.models",
+                "blueprints.users.models",
+                "aerich.models",
+            ],
+            "default_connection": "default",
+        },
+    },
+}

app.py

@@ -0,0 +1,137 @@
+import os
+
+from quart import Quart, request, jsonify, render_template, send_from_directory
+from tortoise.contrib.quart import register_tortoise
+
+from quart_jwt_extended import JWTManager, jwt_refresh_token_required, get_jwt_identity
+
+from main import consult_simba_oracle
+
+import blueprints.users
+import blueprints.conversation
+import blueprints.conversation.logic
+import blueprints.users.models
+
+app = Quart(
+    __name__,
+    static_folder="raggr-frontend/dist/static",
+    template_folder="raggr-frontend/dist",
+)
+
+app.config["JWT_SECRET_KEY"] = os.getenv("JWT_SECRET_KEY", "SECRET_KEY")
+jwt = JWTManager(app)
+
+# Register blueprints
+app.register_blueprint(blueprints.users.user_blueprint)
+app.register_blueprint(blueprints.conversation.conversation_blueprint)
+
+
+# Database configuration with environment variable support
+DATABASE_PATH = os.getenv("DATABASE_PATH", "database/raggr.db")
+
+TORTOISE_CONFIG = {
+    "connections": {"default": f"sqlite://{DATABASE_PATH}"},
+    "apps": {
+        "models": {
+            "models": [
+                "blueprints.conversation.models",
+                "blueprints.users.models",
+                "aerich.models",
+            ]
+        },
+    },
+}
+
+# Initialize Tortoise ORM
+register_tortoise(
+    app,
+    config=TORTOISE_CONFIG,
+    generate_schemas=False,  # Disabled - using Aerich for migrations
+)
+
+
+# Serve React static files
+@app.route("/static/<path:filename>")
+async def static_files(filename):
+    return await send_from_directory(app.static_folder, filename)
+
+
+# Serve the React app for all routes (catch-all)
+@app.route("/", defaults={"path": ""})
+@app.route("/<path:path>")
+async def serve_react_app(path):
+    if path and os.path.exists(os.path.join(app.template_folder, path)):
+        return await send_from_directory(app.template_folder, path)
+    return await render_template("index.html")
+
+
+@app.route("/api/query", methods=["POST"])
+@jwt_refresh_token_required
+async def query():
+    current_user_uuid = get_jwt_identity()
+    user = await blueprints.users.models.User.get(id=current_user_uuid)
+    data = await request.get_json()
+    query = data.get("query")
+    conversation_id = data.get("conversation_id")
+    conversation = await blueprints.conversation.logic.get_conversation_by_id(
+        conversation_id
+    )
+    await conversation.fetch_related("messages")
+    await blueprints.conversation.logic.add_message_to_conversation(
+        conversation=conversation,
+        message=query,
+        speaker="user",
+        user=user,
+    )
+
+    transcript = await blueprints.conversation.logic.get_conversation_transcript(
+        user=user, conversation=conversation
+    )
+
+    response = consult_simba_oracle(input=query, transcript=transcript)
+    await blueprints.conversation.logic.add_message_to_conversation(
+        conversation=conversation,
+        message=response,
+        speaker="simba",
+        user=user,
+    )
+    return jsonify({"response": response})
+
+
+@app.route("/api/messages", methods=["GET"])
+@jwt_refresh_token_required
+async def get_messages():
+    current_user_uuid = get_jwt_identity()
+    user = await blueprints.users.models.User.get(id=current_user_uuid)
+
+    conversation = await blueprints.conversation.logic.get_conversation_for_user(
+        user=user
+    )
+    # Prefetch related messages
+    await conversation.fetch_related("messages")
+
+    # Manually serialize the conversation with messages
+    messages = []
+    for msg in conversation.messages:
+        messages.append(
+            {
+                "id": str(msg.id),
+                "text": msg.text,
+                "speaker": msg.speaker.value,
+                "created_at": msg.created_at.isoformat(),
+            }
+        )
+
+    return jsonify(
+        {
+            "id": str(conversation.id),
+            "name": conversation.name,
+            "messages": messages,
+            "created_at": conversation.created_at.isoformat(),
+            "updated_at": conversation.updated_at.isoformat(),
+        }
+    )
+
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=8080, debug=True)

blueprints/__init__.py

@@ -0,0 +1 @@
+# Blueprints package

blueprints/conversation/__init__.py

@@ -0,0 +1,72 @@
+import datetime
+
+from quart_jwt_extended import (
+    jwt_refresh_token_required,
+    get_jwt_identity,
+)
+
+from quart import Blueprint, jsonify
+from .models import (
+    Conversation,
+    PydConversation,
+    PydListConversation,
+)
+
+import blueprints.users.models
+
+conversation_blueprint = Blueprint(
+    "conversation_api", __name__, url_prefix="/api/conversation"
+)
+
+
+@conversation_blueprint.route("/<conversation_id>")
+async def get_conversation(conversation_id: str):
+    conversation = await Conversation.get(id=conversation_id)
+    await conversation.fetch_related("messages")
+
+    # Manually serialize the conversation with messages
+    messages = []
+    for msg in conversation.messages:
+        messages.append(
+            {
+                "id": str(msg.id),
+                "text": msg.text,
+                "speaker": msg.speaker.value,
+                "created_at": msg.created_at.isoformat(),
+            }
+        )
+
+    return jsonify(
+        {
+            "id": str(conversation.id),
+            "name": conversation.name,
+            "messages": messages,
+            "created_at": conversation.created_at.isoformat(),
+            "updated_at": conversation.updated_at.isoformat(),
+        }
+    )
+
+
+@conversation_blueprint.post("/")
+@jwt_refresh_token_required
+async def create_conversation():
+    user_uuid = get_jwt_identity()
+    user = await blueprints.users.models.User.get(id=user_uuid)
+    conversation = await Conversation.create(
+        name=f"{user.username} {datetime.datetime.now().timestamp}",
+        user=user,
+    )
+
+    serialized_conversation = await PydConversation.from_tortoise_orm(conversation)
+    return jsonify(serialized_conversation.model_dump())
+
+
+@conversation_blueprint.get("/")
+@jwt_refresh_token_required
+async def get_all_conversations():
+    user_uuid = get_jwt_identity()
+    user = await blueprints.users.models.User.get(id=user_uuid)
+    conversations = Conversation.filter(user=user)
+    serialized_conversations = await PydListConversation.from_queryset(conversations)
+
+    return jsonify(serialized_conversations.model_dump())

blueprints/conversation/logic.py

@@ -0,0 +1,60 @@
+import tortoise.exceptions
+
+from .models import Conversation, ConversationMessage
+
+import blueprints.users.models
+
+
+async def create_conversation(name: str = "") -> Conversation:
+    conversation = await Conversation.create(name=name)
+    return conversation
+
+
+async def add_message_to_conversation(
+    conversation: Conversation,
+    message: str,
+    speaker: str,
+    user: blueprints.users.models.User,
+) -> ConversationMessage:
+    print(conversation, message, speaker)
+    message = await ConversationMessage.create(
+        text=message,
+        speaker=speaker,
+        conversation=conversation,
+    )
+
+    return message
+
+
+async def get_the_only_conversation() -> Conversation:
+    try:
+        conversation = await Conversation.all().first()
+        if conversation is None:
+            conversation = await Conversation.create(name="simba_chat")
+    except Exception as _e:
+        conversation = await Conversation.create(name="simba_chat")
+
+    return conversation
+
+
+async def get_conversation_for_user(user: blueprints.users.models.User) -> Conversation:
+    try:
+        return await Conversation.get(user=user)
+    except tortoise.exceptions.DoesNotExist:
+        await Conversation.get_or_create(name=f"{user.username}'s chat", user=user)
+
+        return await Conversation.get(user=user)
+
+
+async def get_conversation_by_id(id: str) -> Conversation:
+    return await Conversation.get(id=id)
+
+
+async def get_conversation_transcript(
+    user: blueprints.users.models.User, conversation: Conversation
+) -> str:
+    messages = []
+    for message in conversation.messages:
+        messages.append(f"{message.speaker} at {message.created_at}: {message.text}")
+
+    return "\n".join(messages)

blueprints/conversation/models.py

@@ -0,0 +1,54 @@
+import enum
+
+from tortoise.models import Model
+from tortoise import fields
+from tortoise.contrib.pydantic import (
+    pydantic_queryset_creator,
+    pydantic_model_creator,
+)
+
+
+class Speaker(enum.Enum):
+    USER = "user"
+    SIMBA = "simba"
+
+
+class Conversation(Model):
+    id = fields.UUIDField(primary_key=True)
+    name = fields.CharField(max_length=255)
+    created_at = fields.DatetimeField(auto_now_add=True)
+    updated_at = fields.DatetimeField(auto_now=True)
+    user: fields.ForeignKeyRelation = fields.ForeignKeyField(
+        "models.User", related_name="conversations", null=True
+    )
+
+    class Meta:
+        table = "conversations"
+
+
+class ConversationMessage(Model):
+    id = fields.UUIDField(primary_key=True)
+    text = fields.TextField()
+    conversation = fields.ForeignKeyField(
+        "models.Conversation", related_name="messages"
+    )
+    created_at = fields.DatetimeField(auto_now_add=True)
+    speaker = fields.CharEnumField(enum_type=Speaker, max_length=10)
+
+    class Meta:
+        table = "conversation_messages"
+
+
+PydConversationMessage = pydantic_model_creator(ConversationMessage)
+PydConversation = pydantic_model_creator(
+    Conversation, name="Conversation", allow_cycles=True, exclude=("user",)
+)
+PydConversationWithMessages = pydantic_model_creator(
+    Conversation,
+    name="ConversationWithMessages",
+    allow_cycles=True,
+    exclude=("user",),
+    include=("messages",),
+)
+PydListConversation = pydantic_queryset_creator(Conversation)
+PydListConversationMessage = pydantic_queryset_creator(ConversationMessage)

blueprints/users/__init__.py

@@ -0,0 +1,40 @@
+from quart import Blueprint, jsonify, request
+from quart_jwt_extended import (
+    create_access_token,
+    create_refresh_token,
+    jwt_refresh_token_required,
+    get_jwt_identity,
+)
+from .models import User
+
+
+user_blueprint = Blueprint("user_api", __name__, url_prefix="/api/user")
+
+
+@user_blueprint.route("/login", methods=["POST"])
+async def login():
+    data = await request.get_json()
+    username = data.get("username")
+    password = data.get("password")
+
+    user = await User.filter(username=username).first()
+
+    if not user or not user.verify_password(password):
+        return jsonify({"msg": "Invalid credentials"}), 401
+
+    access_token = create_access_token(identity=str(user.id))
+    refresh_token = create_refresh_token(identity=str(user.id))
+
+    return jsonify(
+        access_token=access_token,
+        refresh_token=refresh_token,
+        user={"id": user.id, "username": user.username},
+    )
+
+
+@user_blueprint.route("/refresh", methods=["POST"])
+@jwt_refresh_token_required
+async def refresh():
+    user_id = get_jwt_identity()
+    new_token = create_access_token(identity=user_id)
+    return jsonify(access_token=new_token)

blueprints/users/models.py

@@ -0,0 +1,26 @@
+from tortoise.models import Model
+from tortoise import fields
+
+
+import bcrypt
+
+
+class User(Model):
+    id = fields.UUIDField(primary_key=True)
+    username = fields.CharField(max_length=255)
+    password = fields.BinaryField()  # Hashed
+    email = fields.CharField(max_length=100, unique=True)
+    created_at = fields.DatetimeField(auto_now_add=True)
+    updated_at = fields.DatetimeField(auto_now=True)
+
+    class Meta:
+        table = "users"
+
+    def set_password(self, plain_password: str):
+        self.password = bcrypt.hashpw(
+            plain_password.encode("utf-8"),
+            bcrypt.gensalt(),
+        )
+
+    def verify_password(self, plain_password: str):
+        return bcrypt.checkpw(plain_password.encode("utf-8"), self.password)

chunker.py

@@ -3,15 +3,20 @@ from math import ceil
 import re
 from typing import Union
 from uuid import UUID, uuid4
-
-from chromadb.utils.embedding_functions.ollama_embedding_function import (
-    OllamaEmbeddingFunction,
+from ollama import Client
+from chromadb.utils.embedding_functions.openai_embedding_function import (
+    OpenAIEmbeddingFunction,
 )
 from dotenv import load_dotenv
+from llm import LLMClient
 
 
 load_dotenv()
 
+ollama_client = Client(
+    host=os.getenv("OLLAMA_HOST", "http://localhost:11434"), timeout=1.0
+)
+
 
 def remove_headers_footers(text, header_patterns=None, footer_patterns=None):
     if header_patterns is None:
@@ -80,13 +85,16 @@ class Chunk:
 
 
 class Chunker:
-    embedding_fx = OllamaEmbeddingFunction(
-        url=os.getenv("OLLAMA_URL", ""),
-        model_name="mxbai-embed-large",
-    )
-
     def __init__(self, collection) -> None:
         self.collection = collection
+        self.llm_client = LLMClient()
+
+    def embedding_fx(self, inputs):
+        openai_embedding_fx = OpenAIEmbeddingFunction(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model_name="text-embedding-3-small",
+        )
+        return openai_embedding_fx(inputs)
 
     def chunk_document(
         self,
@@ -96,7 +104,7 @@ class Chunker:
     ) -> list[Chunk]:
         doc_uuid = uuid4()
 
-        chunk_size = min(chunk_size, len(document))
+        chunk_size = min(chunk_size, len(document)) or 1
 
         chunks = []
         num_chunks = ceil(len(document) / chunk_size)

cleaner.py

@@ -12,6 +12,9 @@ from request import PaperlessNGXService
 
 load_dotenv()
 
+# Configure ollama client with URL from environment or default to localhost
+ollama_client = ollama.Client(host=os.getenv("OLLAMA_URL", "http://localhost:11434"))
+
 parser = argparse.ArgumentParser(description="use llm to clean documents")
 parser.add_argument("document_id", type=str, help="questions about simba's health")
 
@@ -131,7 +134,7 @@ Someone will kill the innocent kittens if you don't extract the text exactly. So
 
 
 def summarize_pdf_image(filepaths: list[str]):
-    res = ollama.chat(
+    res = ollama_client.chat(
         model="gemma3:4b",
         messages=[
             {

docker-compose.yml

@@ -0,0 +1,19 @@
+version: "3.8"
+
+services:
+  raggr:
+    image: torrtle/simbarag:latest
+    network_mode: host
+    environment:
+      - PAPERLESS_TOKEN=${PAPERLESS_TOKEN}
+      - BASE_URL=${BASE_URL}
+      - OLLAMA_URL=${OLLAMA_URL:-http://localhost:11434}
+      - CHROMADB_PATH=/app/chromadb
+      - OPENAI_API_KEY=${OPENAI_API_KEY}
+    volumes:
+      - chromadb_data:/app/chromadb
+      - database_data:/app/database
+
+volumes:
+  chromadb_data:
+  database_data:

image_process.py

@@ -0,0 +1,83 @@
+from ollama import Client
+import argparse
+import os
+import logging
+from PIL import Image, ExifTags
+from pillow_heif import register_heif_opener
+from pydantic import BaseModel
+
+from dotenv import load_dotenv
+
+load_dotenv()
+
+register_heif_opener()
+
+logging.basicConfig(level=logging.INFO)
+
+
+parser = argparse.ArgumentParser(
+    prog="SimbaImageProcessor",
+    description="What the program does",
+    epilog="Text at the bottom of help",
+)
+
+parser.add_argument("filepath")
+
+client = Client(host=os.getenv("OLLAMA_HOST", "http://localhost:11434"))
+
+
+class SimbaImageDescription(BaseModel):
+    image_date: str
+    description: str
+
+
+def describe_simba_image(input):
+    logging.info("Opening image of Simba ...")
+    if "heic" in input.lower() or "heif" in input.lower():
+        new_filepath = input.split(".")[0] + ".jpg"
+        img = Image.open(input)
+        img.save(new_filepath, "JPEG")
+        logging.info("Extracting EXIF...")
+        exif = {
+            ExifTags.TAGS[k]: v for k, v in img.getexif().items() if k in ExifTags.TAGS
+        }
+        img = Image.open(new_filepath)
+        input = new_filepath
+    else:
+        img = Image.open(input)
+
+        logging.info("Extracting EXIF...")
+        exif = {
+            ExifTags.TAGS[k]: v for k, v in img.getexif().items() if k in ExifTags.TAGS
+        }
+
+    if "MakerNote" in exif:
+        exif.pop("MakerNote")
+
+    logging.info(exif)
+
+    prompt = f"Simba is an orange cat belonging to Ryan Chen. In 2025, they lived in New York. In 2024, they lived in California. Analyze the following image and tell me what Simba seems to be doing. Be extremely descriptive about Simba, things in the background, and the setting of the image. I will also include the EXIF data of the image, please use it to help you determine information about Simba. EXIF: {exif}. Put the notes in the description field and the date in the image_date field."
+
+    logging.info("Sending info to Ollama ...")
+    response = client.chat(
+        model="gemma3:4b",
+        messages=[
+            {
+                "role": "system",
+                "content": "you are a very shrewd and descriptive note taker. all of your responses will be formatted like notes in bullet points. be very descriptive. do not leave a single thing out.",
+            },
+            {"role": "user", "content": prompt, "images": [input]},
+        ],
+        format=SimbaImageDescription.model_json_schema(),
+    )
+
+    result = SimbaImageDescription.model_validate_json(response["message"]["content"])
+
+    return result
+
+
+if __name__ == "__main__":
+    args = parser.parse_args()
+    if args.filepath:
+        logging.info
+        describe_simba_image(input=args.filepath)

index_immich.py

@@ -0,0 +1,115 @@
+import httpx
+import os
+from pathlib import Path
+import logging
+import tempfile
+
+from image_process import describe_simba_image
+from request import PaperlessNGXService
+import sqlite3
+
+logging.basicConfig(level=logging.INFO)
+
+
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# Configuration from environment variables
+IMMICH_URL = os.getenv("IMMICH_URL", "http://localhost:2283")
+API_KEY = os.getenv("IMMICH_API_KEY")
+PERSON_NAME = os.getenv("PERSON_NAME", "Simba")  # Name of the tagged person/pet
+DOWNLOAD_DIR = os.getenv("DOWNLOAD_DIR", "./simba_photos")
+
+# Set up headers
+headers = {"x-api-key": API_KEY, "Content-Type": "application/json"}
+
+VISITED = {}
+
+if __name__ == "__main__":
+    conn = sqlite3.connect("./database/visited.db")
+    c = conn.cursor()
+    c.execute("select immich_id from visited")
+    rows = c.fetchall()
+    for row in rows:
+        VISITED.add(row[0])
+
+    ppngx = PaperlessNGXService()
+    people_url = f"{IMMICH_URL}/api/search/person?name=Simba"
+    people = httpx.get(people_url, headers=headers).json()
+
+    simba_id = people[0]["id"]
+
+    ids = {}
+
+    asset_search = f"{IMMICH_URL}/api/search/smart"
+    request_body = {"query": "orange cat"}
+    results = httpx.post(asset_search, headers=headers, json=request_body)
+
+    assets = results.json()["assets"]
+    for asset in assets["items"]:
+        if asset["type"] == "IMAGE" and asset["id"] not in VISITED:
+            ids[asset["id"]] = asset.get("originalFileName")
+    nextPage = assets.get("nextPage")
+
+    # while nextPage != None:
+    # logging.info(f"next page: {nextPage}")
+    # request_body["page"] = nextPage
+    # results = httpx.post(asset_search, headers=headers, json=request_body)
+    # assets = results.json()["assets"]
+
+    # for asset in assets["items"]:
+    # if asset["type"] == "IMAGE":
+    # ids.add(asset['id'])
+
+    # nextPage = assets.get("nextPage")
+
+    asset_search = f"{IMMICH_URL}/api/search/smart"
+    request_body = {"query": "simba"}
+    results = httpx.post(asset_search, headers=headers, json=request_body)
+    for asset in results.json()["assets"]["items"]:
+        if asset["type"] == "IMAGE":
+            ids[asset["id"]] = asset.get("originalFileName")
+
+    for immich_asset_id, immich_filename in ids.items():
+        try:
+            response = httpx.get(
+                f"{IMMICH_URL}/api/assets/{immich_asset_id}/original", headers=headers
+            )
+
+            path = os.path.join("/Users/ryanchen/Programs/raggr", immich_filename)
+            file = open(path, "wb+")
+            for chunk in response.iter_bytes(chunk_size=8192):
+                file.write(chunk)
+
+            logging.info("Processing image ...")
+            description = describe_simba_image(path)
+
+            image_description = description.description
+            image_date = description.image_date
+
+            description_filepath = os.path.join(
+                "/Users/ryanchen/Programs/raggr", f"SIMBA_DESCRIBE_001.txt"
+            )
+            file = open(description_filepath, "w+")
+            file.write(image_description)
+            file.close()
+
+            file = open(description_filepath, "rb")
+            ppngx.upload_description(
+                description_filepath=description_filepath,
+                file=file,
+                title="SIMBA_DESCRIBE_001.txt",
+                exif_date=image_date,
+            )
+            file.close()
+
+            c.execute("INSERT INTO visited (immich_id) values (?)", (immich_asset_id,))
+            conn.commit()
+            logging.info("Processing complete. Deleting file.")
+            os.remove(file.name)
+        except Exception as e:
+            logging.info(f"something went wrong for {immich_filename}")
+            logging.info(e)
+
+    conn.close()

llm.py

@@ -0,0 +1,73 @@
+import os
+
+from ollama import Client
+from openai import OpenAI
+
+import logging
+from dotenv import load_dotenv
+
+load_dotenv()
+
+logging.basicConfig(level=logging.INFO)
+
+TRY_OLLAMA = os.getenv("TRY_OLLAMA", False)
+
+
+class LLMClient:
+    def __init__(self):
+        try:
+            self.ollama_client = Client(
+                host=os.getenv("OLLAMA_URL", "http://localhost:11434"), timeout=1.0
+            )
+            self.ollama_client.chat(
+                model="gemma3:4b", messages=[{"role": "system", "content": "test"}]
+            )
+            self.PROVIDER = "ollama"
+            logging.info("Using Ollama as LLM backend")
+        except Exception as e:
+            print(e)
+            self.openai_client = OpenAI()
+            self.PROVIDER = "openai"
+            logging.info("Using OpenAI as LLM backend")
+
+    def chat(
+        self,
+        prompt: str,
+        system_prompt: str,
+    ):
+        # Instituting a fallback if my gaming PC is not on
+        if self.PROVIDER == "ollama":
+            try:
+                response = self.ollama_client.chat(
+                    model="gemma3:4b",
+                    messages=[
+                        {
+                            "role": "system",
+                            "content": system_prompt,
+                        },
+                        {"role": "user", "content": prompt},
+                    ],
+                )
+                output = response.message.content
+                return output
+            except Exception as e:
+                logging.error(f"Could not connect to OLLAMA: {str(e)}")
+
+        response = self.openai_client.responses.create(
+            model="gpt-4o-mini",
+            input=[
+                {
+                    "role": "system",
+                    "content": system_prompt,
+                },
+                {"role": "user", "content": prompt},
+            ],
+        )
+        output = response.output_text
+
+        return output
+
+
+if __name__ == "__main__":
+    client = Client()
+    client.chat(model="gemma3:4b", messages=[{"role": "system", "promp": "hack"}])

main.py

@@ -1,24 +1,33 @@
 import datetime
 import logging
 import os
-from typing import Any, Union
+import sqlite3
 
 import argparse
 import chromadb
 import ollama
 
+import time
+
 
 from request import PaperlessNGXService
 from chunker import Chunker
-from query import QueryGenerator
 from cleaner import pdf_to_image, summarize_pdf_image
+from llm import LLMClient
+from query import QueryGenerator
+
 
 from dotenv import load_dotenv
 
-load_dotenv()
+_dotenv_loaded = load_dotenv()
+
+# Configure ollama client with URL from environment or default to localhost
+ollama_client = ollama.Client(
+    host=os.getenv("OLLAMA_URL", "http://localhost:11434"), timeout=10.0
+)
 
 client = chromadb.PersistentClient(path=os.getenv("CHROMADB_PATH", ""))
-simba_docs = client.get_or_create_collection(name="simba_docs")
+simba_docs = client.get_or_create_collection(name="simba_docs2")
 feline_vet_lookup = client.get_or_create_collection(name="feline_vet_lookup")
 
 parser = argparse.ArgumentParser(
@@ -29,25 +38,30 @@ parser.add_argument("query", type=str, help="questions about simba's health")
 parser.add_argument(
     "--reindex", action="store_true", help="re-index the simba documents"
 )
+parser.add_argument("--classify", action="store_true", help="test classification")
+parser.add_argument("--index", help="index a file")
 
 ppngx = PaperlessNGXService()
 
+llm_client = LLMClient()
 
-def index_using_pdf_llm():
+
+def index_using_pdf_llm(doctypes):
+    logging.info("reindex data...")
     files = ppngx.get_data()
     for file in files:
-        document_id = file["id"]
+        document_id: int = file["id"]
         pdf_path = ppngx.download_pdf_from_id(id=document_id)
         image_paths = pdf_to_image(filepath=pdf_path)
+        logging.info(f"summarizing {file}")
         generated_summary = summarize_pdf_image(filepaths=image_paths)
         file["content"] = generated_summary
 
-    chunk_data(files, simba_docs)
+    chunk_data(files, simba_docs, doctypes=doctypes)
 
 
 def date_to_epoch(date_str: str) -> float:
     split_date = date_str.split("-")
-    print(split_date)
     date = datetime.datetime(
         int(split_date[0]),
         int(split_date[1]),
@@ -60,44 +74,123 @@ def date_to_epoch(date_str: str) -> float:
     return date.timestamp()
 
 
-def chunk_data(docs: list[dict[str, Union[str, Any]]], collection):
+def chunk_data(docs, collection, doctypes):
     # Step 2: Create chunks
     chunker = Chunker(collection)
 
-    print(f"chunking {len(docs)} documents")
-    print(docs)
+    logging.info(f"chunking {len(docs)} documents")
     texts: list[str] = [doc["content"] for doc in docs]
+    with sqlite3.connect("database/visited.db") as conn:
+        to_insert = []
+        c = conn.cursor()
+        for index, text in enumerate(texts):
+            metadata = {
+                "created_date": date_to_epoch(docs[index]["created_date"]),
+                "filename": docs[index]["original_file_name"],
+                "document_type": doctypes.get(docs[index]["document_type"], ""),
+            }
+
+            if doctypes:
+                metadata["type"] = doctypes.get(docs[index]["document_type"])
+
+            chunker.chunk_document(
+                document=text,
+                metadata=metadata,
+            )
+            to_insert.append((docs[index]["id"],))
+
+        c.executemany(
+            "INSERT INTO indexed_documents (paperless_id) values (?)", to_insert
+        )
+        conn.commit()
+
+
+def chunk_text(texts: list[str], collection):
+    chunker = Chunker(collection)
+
     for index, text in enumerate(texts):
-        metadata = {
-            "created_date": date_to_epoch(docs[index]["created_date"]),
-        }
+        metadata = {}
         chunker.chunk_document(
             document=text,
             metadata=metadata,
         )
 
 
-def consult_oracle(input: str, collection):
-    # Ask
+def classify_query(query: str, transcript: str) -> bool:
+    logging.info("Starting query generation")
+    qg_start = time.time()
     qg = QueryGenerator()
-    metadata_filter = qg.get_query("input")
-    print(metadata_filter)
-    embeddings = Chunker.embedding_fx(input=[input])
+    query_type = qg.get_query_type(input=query, transcript=transcript)
+    logging.info(query_type)
+    qg_end = time.time()
+    logging.info(f"Query generation took {qg_end - qg_start:.2f} seconds")
+    return query_type == "Simba"
+
+
+def consult_oracle(
+    input: str,
+    collection,
+    transcript: str = "",
+):
+    chunker = Chunker(collection)
+
+    start_time = time.time()
+
+    # Ask
+    logging.info("Starting query generation")
+    qg_start = time.time()
+    qg = QueryGenerator()
+    doctype_query = qg.get_doctype_query(input=input)
+    # metadata_filter = qg.get_query(input)
+    metadata_filter = {**doctype_query}
+    logging.info(metadata_filter)
+    qg_end = time.time()
+    logging.info(f"Query generation took {qg_end - qg_start:.2f} seconds")
+
+    logging.info("Starting embedding generation")
+    embedding_start = time.time()
+    embeddings = chunker.embedding_fx(inputs=[input])
+    embedding_end = time.time()
+    logging.info(
+        f"Embedding generation took {embedding_end - embedding_start:.2f} seconds"
+    )
+
+    logging.info("Starting collection query")
+    query_start = time.time()
     results = collection.query(
         query_texts=[input],
         query_embeddings=embeddings,
         where=metadata_filter,
     )
-
-    print(results)
+    query_end = time.time()
+    logging.info(f"Collection query took {query_end - query_start:.2f} seconds")
 
     # Generate
-    output = ollama.generate(
-        model="gemma3n:e4b",
-        prompt=f"You are a helpful assistant that understandings veterinary terms. Using the following data, help answer the user's query by providing as many details as possible.  Using this data: {results}. Respond to this prompt: {input}",
-    )
+    logging.info("Starting LLM generation")
+    llm_start = time.time()
+    system_prompt = "You are a helpful assistant that understands veterinary terms."
+    transcript_prompt = f"Here is the message transcript thus far {transcript}."
+    prompt = f"""Using the following data, help answer the user's query by providing as many details as possible.
+    Using this data: {results}. {transcript_prompt if len(transcript) > 0 else ""}
+    Respond to this prompt: {input}"""
+    output = llm_client.chat(prompt=prompt, system_prompt=system_prompt)
+    llm_end = time.time()
+    logging.info(f"LLM generation took {llm_end - llm_start:.2f} seconds")
 
-    print(output["response"])
+    total_time = time.time() - start_time
+    logging.info(f"Total consult_oracle execution took {total_time:.2f} seconds")
+
+    return output
+
+
+def llm_chat(input: str, transcript: str = "") -> str:
+    system_prompt = "You are a helpful assistant that understands veterinary terms."
+    transcript_prompt = f"Here is the message transcript thus far {transcript}."
+    prompt = f"""Answer the user in  as if you were a cat named Simba. Don't act too catlike. Be assertive.
+    {transcript_prompt if len(transcript) > 0 else ""}
+    Respond to this prompt: {input}"""
+    output = llm_client.chat(prompt=prompt, system_prompt=system_prompt)
+    return output
 
 
 def paperless_workflow(input):
@@ -109,24 +202,83 @@ def paperless_workflow(input):
     consult_oracle(input, simba_docs)
 
 
+def consult_simba_oracle(input: str, transcript: str = ""):
+    is_simba_related = classify_query(query=input, transcript=transcript)
+
+    if is_simba_related:
+        logging.info("Query is related to simba")
+        return consult_oracle(
+            input=input,
+            collection=simba_docs,
+            transcript=transcript,
+        )
+
+    logging.info("Query is NOT related to simba")
+
+    return llm_chat(input=input, transcript=transcript)
+
+
+def filter_indexed_files(docs):
+    with sqlite3.connect("database/visited.db") as conn:
+        c = conn.cursor()
+        c.execute(
+            "CREATE TABLE IF NOT EXISTS indexed_documents (id INTEGER PRIMARY KEY AUTOINCREMENT, paperless_id INTEGER)"
+        )
+        c.execute("SELECT paperless_id FROM indexed_documents")
+        rows = c.fetchall()
+        conn.commit()
+
+    visited = {row[0] for row in rows}
+    return [doc for doc in docs if doc["id"] not in visited]
+
+
+def reindex():
+    with sqlite3.connect("database/visited.db") as conn:
+        c = conn.cursor()
+        c.execute("DELETE FROM indexed_documents")
+        conn.commit()
+
+    # Delete all documents from the collection
+    all_docs = simba_docs.get()
+    if all_docs["ids"]:
+        simba_docs.delete(ids=all_docs["ids"])
+
+    logging.info("Fetching documents from Paperless-NGX")
+    ppngx = PaperlessNGXService()
+    docs = ppngx.get_data()
+    docs = filter_indexed_files(docs)
+    logging.info(f"Fetched {len(docs)} documents")
+
+    # Delete all chromadb data
+    ids = simba_docs.get(ids=None, limit=None, offset=0)
+    all_ids = ids["ids"]
+    if len(all_ids) > 0:
+        simba_docs.delete(ids=all_ids)
+
+    # Chunk documents
+    logging.info("Chunking documents now ...")
+    doctype_lookup = ppngx.get_doctypes()
+    chunk_data(docs, collection=simba_docs, doctypes=doctype_lookup)
+    logging.info("Done chunking documents")
+
+
 if __name__ == "__main__":
     args = parser.parse_args()
     if args.reindex:
-        # logging.info(msg="Fetching documents from Paperless-NGX")
-        # ppngx = PaperlessNGXService()
-        # docs = ppngx.get_data()
-        # logging.info(msg=f"Fetched {len(docs)} documents")
-        #
-        # logging.info(msg="Chunking documents now ...")
-        # chunk_data(docs, collection=simba_docs)
-        # logging.info(msg="Done chunking documents")
-        index_using_pdf_llm()
+        reindex()
+
+    if args.classify:
+        consult_simba_oracle(input="yohohoho testing")
+        consult_simba_oracle(input="write an email")
+        consult_simba_oracle(input="how much does simba weigh")
 
     if args.query:
         logging.info("Consulting oracle ...")
-        consult_oracle(
-            input=args.query,
-            collection=simba_docs,
+        print(
+            consult_oracle(
+                input=args.query,
+                collection=simba_docs,
+            )
         )
     else:
-        print("please provide a query")
+        logging.info("please provide a query")

migrations/models/0_20251025081744_init.py

@@ -0,0 +1,63 @@
+from tortoise import BaseDBAsyncClient
+
+RUN_IN_TRANSACTION = True
+
+
+async def upgrade(db: BaseDBAsyncClient) -> str:
+    return """
+        CREATE TABLE IF NOT EXISTS "conversations" (
+    "id" CHAR(36) NOT NULL PRIMARY KEY,
+    "name" VARCHAR(255) NOT NULL,
+    "created_at" TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP
+);
+CREATE TABLE IF NOT EXISTS "conversation_messages" (
+    "id" CHAR(36) NOT NULL PRIMARY KEY,
+    "text" TEXT NOT NULL,
+    "created_at" TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "speaker" VARCHAR(10) NOT NULL /* USER: user\nSIMBA: simba */,
+    "conversation_id" CHAR(36) NOT NULL REFERENCES "conversations" ("id") ON DELETE CASCADE
+);
+CREATE TABLE IF NOT EXISTS "users" (
+    "id" CHAR(36) NOT NULL PRIMARY KEY,
+    "username" VARCHAR(255) NOT NULL,
+    "password" BLOB NOT NULL,
+    "email" VARCHAR(100) NOT NULL UNIQUE,
+    "created_at" TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP
+);
+CREATE TABLE IF NOT EXISTS "aerich" (
+    "id" INTEGER PRIMARY KEY AUTOINCREMENT NOT NULL,
+    "version" VARCHAR(255) NOT NULL,
+    "app" VARCHAR(100) NOT NULL,
+    "content" JSON NOT NULL
+);"""
+
+
+async def downgrade(db: BaseDBAsyncClient) -> str:
+    return """
+        """
+
+
+MODELS_STATE = (
+    "eJztmG1v4jgQx79KlFddaa9q2W53VZ1OCpTecrvACcLdPtwqMskAVhMnazvboorvfrbJE4"
+    "kJpWq3UPGmhRkPtn8ztv/2nRmEHvjsuBWSn0AZ4jgk5oVxZxIUgPig9b82TBRFuVcaOBr7"
+    "KsAttFQeNGacIpcL5wT5DITJA+ZSHCWdkdj3pTF0RUNMprkpJvhHDA4Pp8BnQIXj23dhxs"
+    "SDW2Dp1+jamWDwvZVxY0/2rewOn0fKNhp1Lq9US9nd2HFDPw5I3jqa81lIsuZxjL1jGSN9"
+    "UyBAEQevMA05ymTaqWk5YmHgNIZsqF5u8GCCYl/CMH+fxMSVDAzVk/xz9oe5BR6BWqLFhE"
+    "sWd4vlrPI5K6spu2p9sAZHb85fqVmGjE+pcioi5kIFIo6WoYprDlL9r6BszRDVo0zbl2CK"
+    "gT4EY2rIOeY1lIJMAT2MmhmgW8cHMuUz8bXx9m0Nxn+sgSIpWimUoajrZdX3Eldj6ZNIc4"
+    "QuBTllB/EqyEvh4TgAPczVyBJSLwk9Tj/sKGAxB69P/HmyCGr42p1ue2hb3b/lTALGfvgK"
+    "kWW3paehrPOS9ei8lIrsR4x/O/YHQ341vvZ77XLtZ+3sr6YcE4p56JDwxkFeYb2m1hTMSm"
+    "LjyHtgYlcjD4l91sSqwcuTZHJd2AKlYYzc6xtEPWfFUzgdgTE0BVZNfzOJvPo4AD87NkuJ"
+    "1hyu3eUv7mbGF2kZp9YivLARrqNXdQWNoGxBRMzbS/qWPdXQ2aBQChDvJ1ScYiIPgmWvBQ"
+    "uHW812bAurHmXafl8ES9022/5sr+ywqSw56lqfX63ssp/6vT/T5gUZ0/rUbx7Uy0s85Krq"
+    "hUWAroHqxX2bxIHKakfgQMSFSnYL4c+8dMzRsD24MGIG9D8y7HSb1oXBcDBG5gNuAKcn97"
+    "gAnJ6s1f/SVVpAxYNmu21eE/qYe/6zblYbtviKHtMDrdK8CingKfkI80r9bpZfO02xoruE"
+    "maKbTEzoykV8EJMEvlzY1rBlXbbNxXpt+5RKbsSUJKpIN2Wv1WpyaR+02f5rM5nHbR+Uij"
+    "H7otF+waNShBi7CammMpuYIDrXwyxGlWCO53x5/9k9nDX0mlKwFvWWYNbs9KzBF73mTdsX"
+    "C7f5xW5bJbwQIOxvU6ZZwOPU6OYl/5gVenpyP9VTJ3uquudwcXiZF4fDs+eLSOy2z55PKQ"
+    "0toNid6cRh4qmVhyhvszP6sEPWvDdp5aHU9KVqTxL2rIeEemr9rXF69u7s/Zvzs/eiiRpJ"
+    "ZnlXU/2dnr1BDsrLivYOt/6YLYQcxGAGUi6NLSAmzfcT4NNolZBwIJrz7K9hv7f2bSYNKY"
+    "EcETHBbx52+WvDx4x/302sNRTlrOsfkstvxqXDSP5AU/eK8yuPl8X/Etg7Fw=="
+)

migrations/models/1_20251025091926_update.py

@@ -0,0 +1,60 @@
+from tortoise import BaseDBAsyncClient
+
+RUN_IN_TRANSACTION = True
+
+
+async def upgrade(db: BaseDBAsyncClient) -> str:
+    return """
+        -- SQLite doesn't support ADD CONSTRAINT, so we need to recreate the table
+        CREATE TABLE "conversations_new" (
+            "id" CHAR(36) NOT NULL PRIMARY KEY,
+            "name" VARCHAR(255) NOT NULL,
+            "created_at" TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP,
+            "updated_at" TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP,
+            "user_id" CHAR(36),
+            FOREIGN KEY ("user_id") REFERENCES "users" ("id") ON DELETE CASCADE
+        );
+        INSERT INTO "conversations_new" ("id", "name", "created_at", "updated_at")
+        SELECT "id", "name", "created_at", "updated_at" FROM "conversations";
+        DROP TABLE "conversations";
+        ALTER TABLE "conversations_new" RENAME TO "conversations";"""
+
+
+async def downgrade(db: BaseDBAsyncClient) -> str:
+    return """
+        -- Recreate table without user_id column
+        CREATE TABLE "conversations_new" (
+            "id" CHAR(36) NOT NULL PRIMARY KEY,
+            "name" VARCHAR(255) NOT NULL,
+            "created_at" TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP,
+            "updated_at" TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP
+        );
+        INSERT INTO "conversations_new" ("id", "name", "created_at", "updated_at")
+        SELECT "id", "name", "created_at", "updated_at" FROM "conversations";
+        DROP TABLE "conversations";
+        ALTER TABLE "conversations_new" RENAME TO "conversations";"""
+
+
+MODELS_STATE = (
+    "eJztmWtP2zAUhv9KlE8gbQg6xhCaJqWlbB20ndp0F9gUuYnbWiROiJ1Bhfjvs91cnMRNKe"
+    "PSon6B9vic2H5s57w+vdU934Eu2Wn4+C8MCaDIx/qRdqtj4EH2Qdn+RtNBEGSt3EDB0BUB"
+    "tuQpWsCQ0BDYlDWOgEsgMzmQ2CEK4s5w5Lrc6NvMEeFxZoowuoqgRf0xpBMYsoaLP8yMsA"
+    "NvIEm+BpfWCEHXyY0bObxvYbfoNBC2waB1fCI8eXdDy/bdyMOZdzClEx+n7lGEnB0ew9vG"
+    "EMMQUOhI0+CjjKedmGYjZgYaRjAdqpMZHDgCkcth6B9HEbY5A030xP/sf9KXwMNQc7QIU8"
+    "7i9m42q2zOwqrzrhpfjN7Wu4NtMUuf0HEoGgUR/U4EAgpmoYJrBlL8L6FsTECoRpn4F2Cy"
+    "gT4EY2LIOGZ7KAGZAHoYNd0DN5YL8ZhO2Nfa+/cVGL8bPUGSeQmUPtvXs13fiZtqszaONE"
+    "Noh5BP2QK0DPKYtVDkQTXMfGQBqROH7iQfVhQwm4PTxe40PgQVfM1Wu9k3jfY3PhOPkCtX"
+    "IDLMJm+pCeu0YN06KCxF+hDtR8v8ovGv2nm30yzu/dTPPNf5mEBEfQv71xZwpPOaWBMwuY"
+    "WNAueBC5uP3Czsiy5sPHhpXQkMreUyiBTyH2kkHtszLuLDkwZPvaNLZc7gMMrwTvwQojE+"
+    "hVOBsMXGAbCtShax6BjEj1lVaJk1G0UIrlM1Im8KNjs2J0hn2dPoN4zjpi4YDoF9eQ1Cx5"
+    "oD04OEgDEkZaD1OPLktAfdVJqpWcoCrj174mq+VeaxFaz8mi8xytErN3k1r2gBmM3bifvm"
+    "PVXQWaCCJYj3E8OWvJAbUbzWopjCG0XKN5lVjTLxXxdRXJXKmz/NXBZPpO9W2/i5ncvkZ9"
+    "3O58RdksqNs259o5Bfo5AqK2QSQHCpEgP8AtnEkVeSArnVlcJf+Ojog36zd6TxjP4b91vt"
+    "unGkEeQNgX6/Jc7dMvd273HJ3Nude8fkTYUDJCea5V7zitDHfOevqYS1CwWv/5SyxfrZyl"
+    "JcqGkV22VZbfuUSk7cGRTSLblLzNdq/GhvtNn6azO+jssWLeWYddFoz1C4DAAh136o2Jl1"
+    "hEE4VcOUowowh1M6u/+sHs4KenUuWGW9xZjVWx2j90uteRN/eePWf5lNo4AXegC5y2zTNO"
+    "Bx9ujiI/+YO3Rv936qp0r2lHXP5uLwOi8Om9L6q1jYtHJXEoCLyp6l35Efp/a5VvXkJ615"
+    "GjBE9kRXaOW4pVItg8xnZeRyC88pvynVMsdc2Azxyr9ozhSV57e1vf0P+4fvDvYPmYsYSW"
+    "r5UPEyaHXMBeqYHwTllXa+6pBCNto4BcmPxhIQY/f1BPg00s3HFGJFev/a73bmlqqSkALI"
+    "AWYTvHCQTd9oLiL0z2piraDIZ11dVy+W0Au5mT+gripqPWch5u4f/FVgYA=="
+)

pyproject.toml

@@ -4,4 +4,9 @@ version = "0.1.0"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.13"
-dependencies = []
+dependencies = ["chromadb>=1.1.0", "python-dotenv>=1.0.0", "flask>=3.1.2", "httpx>=0.28.1", "ollama>=0.6.0", "openai>=2.0.1", "pydantic>=2.11.9", "pillow>=10.0.0", "pymupdf>=1.24.0", "black>=25.9.0", "pillow-heif>=1.1.1", "flask-jwt-extended>=4.7.1", "bcrypt>=5.0.0", "pony>=0.7.19", "flask-login>=0.6.3", "quart>=0.20.0", "tortoise-orm>=0.25.1", "quart-jwt-extended>=0.1.0", "pre-commit>=4.3.0", "tortoise-orm-stubs>=1.0.2", "aerich>=0.8.0", "tomlkit>=0.13.3"]
+
+[tool.aerich]
+tortoise_orm = "app.TORTOISE_CONFIG"
+location = "./migrations"
+src_folder = "./."

query.py

@@ -1,10 +1,18 @@
 import json
+import os
 from typing import Literal
 import datetime
-from ollama import chat, ChatResponse
+from ollama import Client
+
+from openai import OpenAI
 
 from pydantic import BaseModel, Field
 
+# Configure ollama client with URL from environment or default to localhost
+ollama_client = Client(
+    host=os.getenv("OLLAMA_URL", "http://localhost:11434"), timeout=10.0
+)
+
 # This uses inferred filters — which means using LLM to create the metadata filters
 
 
@@ -28,12 +36,40 @@ class GeneratedQuery(BaseModel):
     extracted_metadata_fields: str
 
 
-PROMPT = """
-You are an information specialist that processes user queries. The current year is 2025. The user queries are all about 
-a cat, Simba, and its records. The types of records are listed below. Using the query, extract the 
-the date range the user is trying to query. You should return the it as a JSON. The date tag is created_date. Return the date in epoch time
+class Time(BaseModel):
+    time: int
 
 
+DOCTYPE_OPTIONS = [
+    "Bill",
+    "Image Description",
+    "Insurance",
+    "Medical Record",
+    "Documentation",
+    "Letter",
+]
+
+QUERY_TYPE_OPTIONS = [
+    "Simba",
+    "Other",
+]
+
+
+class DocumentType(BaseModel):
+    type: list[str] = Field(description="type of document", enum=DOCTYPE_OPTIONS)
+
+
+class QueryType(BaseModel):
+    type: str = Field(desciption="type of query", enum=QUERY_TYPE_OPTIONS)
+
+
+PROMPT = """
+You are an information specialist that processes user queries. The current year is 2025. The user queries are all about
+a cat, Simba, and its records. The types of records are listed below. Using the query, extract the
+the date range the user is trying to query. You should return it as a JSON. The date tag is created_date. Return the date in epoch time.
+
+If the created_date cannot be ascertained, set it to epoch time start.
+
 You have several operators at your disposal:
 - $gt: greater than
 - $gte: greater than or equal
@@ -72,6 +108,40 @@ Only return the extracted metadata fields. Make sure the extracted metadata fiel
 """
 
 
+DOCTYPE_PROMPT = f"""You are an information specialist that processes user queries. A query can have two tags attached from the following options. Based on the query, determine which of the following options is most appropriate: {",".join(DOCTYPE_OPTIONS)}
+
+### Example 1
+Query: "Who is Simba's current vet?"
+Tags: ["Bill", "Medical Record"]
+
+
+### Example 2
+Query: "Who does Simba know?"
+Tags: ["Letter", "Documentation"]
+"""
+
+QUERY_TYPE_PROMPT = f"""You are an information specialist that processes user queries.
+A query can have one tag attached from the following options. Based on the query and the transcript which is listed below, determine
+ which of the following options is most appropriate: {",".join(QUERY_TYPE_OPTIONS)}
+
+### Example 1
+Query: "Who is Simba's current vet?"
+Tags: ["Simba"]
+
+
+### Example 2
+Query: "What is the capital of Tokyo?"
+Tags: ["Other"]
+
+
+### Example 3
+Query: "Can you help me write an email?"
+Tags: ["Other"]
+
+TRANSCRIPT:
+"""
+
+
 class QueryGenerator:
     def __init__(self) -> None:
         pass
@@ -89,30 +159,93 @@ class QueryGenerator:
 
         return date.timestamp()
 
-    def get_query(self, input: str):
-        response: ChatResponse = chat(
-            model="gemma3n:e4b",
+    def get_doctype_query(self, input: str):
+        client = OpenAI()
+        response = client.chat.completions.create(
             messages=[
+                {
+                    "role": "system",
+                    "content": "You are an information specialist that is really good at deciding what tags a query should have",
+                },
+                {"role": "user", "content": DOCTYPE_PROMPT + " " + input},
+            ],
+            model="gpt-4o",
+            response_format={
+                "type": "json_schema",
+                "json_schema": {
+                    "name": "document_type",
+                    "schema": DocumentType.model_json_schema(),
+                },
+            },
+        )
+
+        response_json_str = response.choices[0].message.content
+        type_data = json.loads(response_json_str)
+        metadata_query = {"document_type": {"$in": type_data["type"]}}
+        return metadata_query
+
+    def get_query_type(self, input: str, transcript: str):
+        client = OpenAI()
+        response = client.chat.completions.create(
+            messages=[
+                {
+                    "role": "system",
+                    "content": "You are an information specialist that is really good at deciding what tags a query should have",
+                },
+                {
+                    "role": "user",
+                    "content": f"{QUERY_TYPE_PROMPT}\nTRANSCRIPT:\n{transcript}\nQUERY:{input}",
+                },
+            ],
+            model="gpt-4o",
+            response_format={
+                "type": "json_schema",
+                "json_schema": {
+                    "name": "query_type",
+                    "schema": QueryType.model_json_schema(),
+                },
+            },
+        )
+
+        response_json_str = response.choices[0].message.content
+        type_data = json.loads(response_json_str)
+        return type_data["type"]
+
+    def get_query(self, input: str):
+        client = OpenAI()
+        response = client.responses.parse(
+            model="gpt-4o",
+            input=[
                 {"role": "system", "content": PROMPT},
                 {"role": "user", "content": input},
             ],
-            format=GeneratedQuery.model_json_schema(),
+            text_format=GeneratedQuery,
         )
+        print(response.output)
+        query = json.loads(response.output_parsed.extracted_metadata_fields)
+        # response: ChatResponse = ollama_client.chat(
+        # model="gemma3n:e4b",
+        # messages=[
+        # {"role": "system", "content": PROMPT},
+        # {"role": "user", "content": input},
+        # ],
+        # format=GeneratedQuery.model_json_schema(),
+        # )
 
-        query = json.loads(
-            json.loads(response["message"]["content"])["extracted_metadata_fields"]
-        )
-        date_key = list(query["created_date"].keys())[0]
-        query["created_date"][date_key] = self.date_to_epoch(
-            query["created_date"][date_key]
-        )
+        # query = json.loads(
+        # json.loads(response["message"]["content"])["extracted_metadata_fields"]
+        # )
+        # date_key = list(query["created_date"].keys())[0]
+        # query["created_date"][date_key] = self.date_to_epoch(
+        # query["created_date"][date_key]
+        # )
 
-        if "$" not in date_key:
-            query["created_date"]["$" + date_key] = query["created_date"][date_key]
+        # if "$" not in date_key:
+        # query["created_date"]["$" + date_key] = query["created_date"][date_key]
 
         return query
 
 
 if __name__ == "__main__":
     qg = QueryGenerator()
-    print(qg.get_query("How heavy is Simba?"))
+    print(qg.get_doctype_query("How heavy is Simba?"))

raggr-frontend/.gitignore

@@ -0,0 +1,16 @@
+# Local
+.DS_Store
+*.local
+*.log*
+
+# Dist
+node_modules
+dist/
+
+# Profile
+.rspack-profile-*/
+
+# IDE
+.vscode/*
+!.vscode/extensions.json
+.idea

raggr-frontend/README.md

@@ -0,0 +1,36 @@
+# Rsbuild project
+
+## Setup
+
+Install the dependencies:
+
+```bash
+pnpm install
+```
+
+## Get started
+
+Start the dev server, and the app will be available at [http://localhost:3000](http://localhost:3000).
+
+```bash
+pnpm dev
+```
+
+Build the app for production:
+
+```bash
+pnpm build
+```
+
+Preview the production build locally:
+
+```bash
+pnpm preview
+```
+
+## Learn more
+
+To learn more about Rsbuild, check out the following resources:
+
+- [Rsbuild documentation](https://rsbuild.rs) - explore Rsbuild features and APIs.
+- [Rsbuild GitHub repository](https://github.com/web-infra-dev/rsbuild) - your feedback and contributions are welcome!

raggr-frontend/TOKEN_REFRESH_IMPLEMENTATION.md

@@ -0,0 +1,63 @@
+# Token Refresh Implementation
+
+## Overview
+
+The API services now automatically handle token refresh when access tokens expire. This provides a seamless user experience without requiring manual re-authentication.
+
+## How It Works
+
+### 1. **userService.ts**
+
+The `userService` now includes:
+
+- **`refreshToken()`**: Automatically gets the refresh token from localStorage, calls the `/api/user/refresh` endpoint, and updates the access token
+- **`fetchWithAuth()`**: A wrapper around `fetch()` that:
+  1. Automatically adds the Authorization header with the access token
+  2. Detects 401 (Unauthorized) responses
+  3. Automatically refreshes the token using the refresh token
+  4. Retries the original request with the new access token
+  5. Throws an error if refresh fails (e.g., refresh token expired)
+
+### 2. **conversationService.ts**
+
+Now uses `userService.fetchWithAuth()` for all API calls:
+- `sendQuery()` - No longer needs token parameter
+- `getMessages()` - No longer needs token parameter
+
+### 3. **Components Updated**
+
+**ChatScreen.tsx**:
+- Removed manual token handling
+- Now simply calls `conversationService.sendQuery(query)` and `conversationService.getMessages()`
+
+## Benefits
+
+✅ **Automatic token refresh** - Users stay logged in longer
+✅ **Transparent retry logic** - Failed requests due to expired tokens are automatically retried
+✅ **Cleaner code** - Components don't need to manage tokens
+✅ **Better UX** - No interruptions when access token expires
+✅ **Centralized auth logic** - All auth handling in one place
+
+## Error Handling
+
+- If refresh token is missing or invalid, the error is thrown
+- Components can catch these errors and redirect to login
+- LocalStorage is automatically cleared when refresh fails
+
+## Usage Example
+
+```typescript
+// Old way (manual token management)
+const token = localStorage.getItem("access_token");
+const result = await conversationService.sendQuery(query, token);
+
+// New way (automatic token refresh)
+const result = await conversationService.sendQuery(query);
+```
+
+## Token Storage
+
+- **Access Token**: `localStorage.getItem("access_token")`
+- **Refresh Token**: `localStorage.getItem("refresh_token")`
+
+Both are automatically managed by the services.

raggr-frontend/package.json

@@ -0,0 +1,41 @@
+{
+  "name": "raggr-frontend",
+  "version": "1.0.0",
+  "private": true,
+  "type": "module",
+  "scripts": {
+    "build": "rsbuild build",
+    "dev": "rsbuild dev --open",
+    "preview": "rsbuild preview",
+    "watch": "npm-watch build",
+    "watch:build": "rsbuild build --watch"
+  },
+  "dependencies": {
+    "axios": "^1.12.2",
+    "marked": "^16.3.0",
+    "npm-watch": "^0.13.0",
+    "react": "^19.1.1",
+    "react-dom": "^19.1.1",
+    "react-markdown": "^10.1.0",
+    "watch": "^1.0.2"
+  },
+  "devDependencies": {
+    "@rsbuild/core": "^1.5.6",
+    "@rsbuild/plugin-react": "^1.4.0",
+    "@tailwindcss/postcss": "^4.0.0",
+    "@types/react": "^19.1.13",
+    "@types/react-dom": "^19.1.9",
+    "typescript": "^5.9.2"
+  },
+  "watch": {
+    "build": {
+      "patterns": [
+        "src"
+      ],
+      "extensions": "ts,tsx,css,js,jsx",
+      "delay": 1000,
+      "quiet": false,
+      "inherit": true
+    }
+  }
+}

raggr-frontend/postcss.config.mjs

@@ -0,0 +1,5 @@
+export default {
+	plugins: {
+		"@tailwindcss/postcss": {},
+	},
+};

raggr-frontend/rsbuild.config.ts

@@ -0,0 +1,10 @@
+import { defineConfig } from '@rsbuild/core';
+import { pluginReact } from '@rsbuild/plugin-react';
+
+export default defineConfig({
+  plugins: [pluginReact()],
+  html: {
+    title: 'Raggr',
+    favicon: './src/assets/favicon.svg',
+  },
+});

raggr-frontend/src/App.css

@@ -0,0 +1,6 @@
+@import "tailwindcss";
+
+body {
+	margin: 0;
+	font-family: Inter, Avenir, Helvetica, Arial, sans-serif;
+}

raggr-frontend/src/App.tsx

@@ -0,0 +1,72 @@
+import { useState, useEffect } from "react";
+
+import "./App.css";
+import { AuthProvider } from "./contexts/AuthContext";
+import { ChatScreen } from "./components/ChatScreen";
+import { LoginScreen } from "./components/LoginScreen";
+import { conversationService } from "./api/conversationService";
+
+const AppContainer = () => {
+  const [isAuthenticated, setAuthenticated] = useState<boolean>(false);
+  const [isChecking, setIsChecking] = useState<boolean>(true);
+
+  useEffect(() => {
+    const checkAuth = async () => {
+      const accessToken = localStorage.getItem("access_token");
+      const refreshToken = localStorage.getItem("refresh_token");
+
+      // No tokens at all, not authenticated
+      if (!accessToken && !refreshToken) {
+        setIsChecking(false);
+        setAuthenticated(false);
+        return;
+      }
+
+      // Try to verify token by making a request
+      try {
+        await conversationService.getMessages();
+        // If successful, user is authenticated
+        setAuthenticated(true);
+      } catch (error) {
+        // Token is invalid or expired
+        console.error("Authentication check failed:", error);
+        localStorage.removeItem("access_token");
+        localStorage.removeItem("refresh_token");
+        setAuthenticated(false);
+      } finally {
+        setIsChecking(false);
+      }
+    };
+
+    checkAuth();
+  }, []);
+
+  // Show loading state while checking authentication
+  if (isChecking) {
+    return (
+      <div className="h-screen flex items-center justify-center bg-white/85">
+        <div className="text-xl">Loading...</div>
+      </div>
+    );
+  }
+
+  return (
+    <>
+      {isAuthenticated ? (
+        <ChatScreen setAuthenticated={setAuthenticated} />
+      ) : (
+        <LoginScreen setAuthenticated={setAuthenticated} />
+      )}
+    </>
+  );
+};
+
+const App = () => {
+  return (
+    <AuthProvider>
+      <AppContainer />
+    </AuthProvider>
+  );
+};
+
+export default App;

raggr-frontend/src/api/conversationService.ts

@@ -0,0 +1,115 @@
+import { userService } from "./userService";
+
+interface Message {
+  id: string;
+  text: string;
+  speaker: "user" | "simba";
+  created_at: string;
+}
+
+interface Conversation {
+  id: string;
+  name: string;
+  messages?: Message[];
+  created_at: string;
+  updated_at: string;
+  user_id?: string;
+}
+
+interface QueryRequest {
+  query: string;
+}
+
+interface QueryResponse {
+  response: string;
+}
+
+interface CreateConversationRequest {
+  user_id: string;
+}
+
+class ConversationService {
+  private baseUrl = "/api";
+  private conversationBaseUrl = "/api/conversation";
+
+  async sendQuery(
+    query: string,
+    conversation_id: string,
+  ): Promise<QueryResponse> {
+    const response = await userService.fetchWithRefreshToken(
+      `${this.baseUrl}/query`,
+      {
+        method: "POST",
+        body: JSON.stringify({ query, conversation_id }),
+      },
+    );
+
+    if (!response.ok) {
+      throw new Error("Failed to send query");
+    }
+
+    return await response.json();
+  }
+
+  async getMessages(): Promise<Conversation> {
+    const response = await userService.fetchWithRefreshToken(
+      `${this.baseUrl}/messages`,
+      {
+        method: "GET",
+      },
+    );
+
+    if (!response.ok) {
+      throw new Error("Failed to fetch messages");
+    }
+
+    return await response.json();
+  }
+
+  async getConversation(conversationId: string): Promise<Conversation> {
+    const response = await userService.fetchWithRefreshToken(
+      `${this.conversationBaseUrl}/${conversationId}`,
+      {
+        method: "GET",
+      },
+    );
+
+    if (!response.ok) {
+      throw new Error("Failed to fetch conversation");
+    }
+
+    return await response.json();
+  }
+
+  async createConversation(): Promise<Conversation> {
+    const response = await userService.fetchWithRefreshToken(
+      `${this.conversationBaseUrl}/`,
+      {
+        method: "POST",
+      },
+    );
+
+    if (!response.ok) {
+      throw new Error("Failed to create conversation");
+    }
+
+    return await response.json();
+  }
+
+  async getAllConversations(): Promise<Conversation[]> {
+    const response = await userService.fetchWithRefreshToken(
+      `${this.conversationBaseUrl}/`,
+      {
+        method: "GET",
+      },
+    );
+
+    if (!response.ok) {
+      throw new Error("Failed to fetch conversations");
+    }
+
+    return await response.json();
+  }
+}
+
+export const conversationService = new ConversationService();

raggr-frontend/src/api/userService.ts

@@ -0,0 +1,138 @@
+interface LoginResponse {
+  access_token: string;
+  refresh_token: string;
+  user: {
+    id: string;
+    username: string;
+  };
+}
+
+interface RefreshResponse {
+  access_token: string;
+}
+
+class UserService {
+  private baseUrl = "/api/user";
+
+  async login(username: string, password: string): Promise<LoginResponse> {
+    const response = await fetch(`${this.baseUrl}/login`, {
+      method: "POST",
+      headers: { "Content-Type": "application/json" },
+      body: JSON.stringify({ username, password }),
+    });
+
+    if (!response.ok) {
+      throw new Error("Invalid credentials");
+    }
+
+    return await response.json();
+  }
+
+  async refreshToken(): Promise<string> {
+    const refreshToken = localStorage.getItem("refresh_token");
+
+    if (!refreshToken) {
+      throw new Error("No refresh token available");
+    }
+
+    const response = await fetch(`${this.baseUrl}/refresh`, {
+      method: "POST",
+      headers: {
+        "Content-Type": "application/json",
+        Authorization: `Bearer ${refreshToken}`,
+      },
+    });
+
+    if (!response.ok) {
+      // Refresh token is invalid or expired, clear storage
+      localStorage.removeItem("access_token");
+      localStorage.removeItem("refresh_token");
+      throw new Error("Failed to refresh token");
+    }
+
+    const data: RefreshResponse = await response.json();
+    localStorage.setItem("access_token", data.access_token);
+    return data.access_token;
+  }
+
+  async validateToken(): Promise<boolean> {
+    const refreshToken = localStorage.getItem("refresh_token");
+
+    if (!refreshToken) {
+      return false;
+    }
+
+    try {
+      await this.refreshToken();
+      return true;
+    } catch (error) {
+      return false;
+    }
+  }
+
+  async fetchWithAuth(
+    url: string,
+    options: RequestInit = {},
+  ): Promise<Response> {
+    const accessToken = localStorage.getItem("access_token");
+
+    // Add authorization header
+    const headers = {
+      "Content-Type": "application/json",
+      ...(options.headers || {}),
+      ...(accessToken && { Authorization: `Bearer ${accessToken}` }),
+    };
+
+    let response = await fetch(url, { ...options, headers });
+
+    // If unauthorized, try refreshing the token
+    if (response.status === 401) {
+      try {
+        const newAccessToken = await this.refreshToken();
+
+        // Retry the request with new token
+        headers.Authorization = `Bearer ${newAccessToken}`;
+        response = await fetch(url, { ...options, headers });
+      } catch (error) {
+        // Refresh failed, redirect to login or throw error
+        throw new Error("Session expired. Please log in again.");
+      }
+    }
+
+    return response;
+  }
+
+  async fetchWithRefreshToken(
+    url: string,
+    options: RequestInit = {},
+  ): Promise<Response> {
+    const refreshToken = localStorage.getItem("refresh_token");
+
+    // Add authorization header
+    const headers = {
+      "Content-Type": "application/json",
+      ...(options.headers || {}),
+      ...(refreshToken && { Authorization: `Bearer ${refreshToken}` }),
+    };
+
+    let response = await fetch(url, { ...options, headers });
+
+    // If unauthorized, try refreshing the token
+    if (response.status === 401) {
+      try {
+        const newAccessToken = await this.refreshToken();
+
+        // Retry the request with new token
+        headers.Authorization = `Bearer ${newAccessToken}`;
+        response = await fetch(url, { ...options, headers });
+      } catch (error) {
+        // Refresh failed, redirect to login or throw error
+        throw new Error("Session expired. Please log in again.");
+      }
+    }
+
+    return response;
+  }
+}
+
+export const userService = new UserService();

raggr-frontend/src/assets/favicon.svg

@@ -0,0 +1,3 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 100 100">
+  <text y="80" font-size="80" font-family="system-ui, -apple-system, sans-serif">🐱</text>
+</svg>

raggr-frontend/src/components/AnswerBubble.tsx

@@ -0,0 +1,31 @@
+import ReactMarkdown from "react-markdown";
+
+type AnswerBubbleProps = {
+  text: string;
+  loading?: boolean;
+};
+
+export const AnswerBubble = ({ text, loading }: AnswerBubbleProps) => {
+  return (
+    <div className="rounded-md bg-orange-100 p-3 sm:p-4">
+      {loading ? (
+        <div className="flex flex-col w-full animate-pulse gap-2">
+          <div className="flex flex-row gap-2 w-full">
+            <div className="bg-gray-400 w-1/2 p-3 rounded-lg" />
+            <div className="bg-gray-400 w-1/2 p-3 rounded-lg" />
+          </div>
+          <div className="flex flex-row gap-2 w-full">
+            <div className="bg-gray-400 w-1/3 p-3 rounded-lg" />
+            <div className="bg-gray-400 w-2/3 p-3 rounded-lg" />
+          </div>
+        </div>
+      ) : (
+        <div className="flex flex-col break-words overflow-wrap-anywhere">
+          <ReactMarkdown className="text-sm sm:text-base [&>*]:break-words">
+            {"🐈: " + text}
+          </ReactMarkdown>
+        </div>
+      )}
+    </div>
+  );
+};

raggr-frontend/src/components/ChatScreen.tsx

@@ -0,0 +1,252 @@
+import { useEffect, useState, useRef } from "react";
+import { conversationService } from "../api/conversationService";
+import { QuestionBubble } from "./QuestionBubble";
+import { AnswerBubble } from "./AnswerBubble";
+import { ConversationList } from "./ConversationList";
+import { parse } from "node:path/win32";
+
+type Message = {
+  text: string;
+  speaker: "simba" | "user";
+};
+
+type QuestionAnswer = {
+  question: string;
+  answer: string;
+};
+
+type Conversation = {
+  title: string;
+  id: string;
+};
+
+type ChatScreenProps = {
+  setAuthenticated: (isAuth: boolean) => void;
+};
+
+export const ChatScreen = ({ setAuthenticated }: ChatScreenProps) => {
+  const [query, setQuery] = useState<string>("");
+  const [answer, setAnswer] = useState<string>("");
+  const [simbaMode, setSimbaMode] = useState<boolean>(false);
+  const [questionsAnswers, setQuestionsAnswers] = useState<QuestionAnswer[]>(
+    [],
+  );
+  const [messages, setMessages] = useState<Message[]>([]);
+  const [conversations, setConversations] = useState<Conversation[]>([
+    { title: "simba meow meow", id: "uuid" },
+  ]);
+  const [showConversations, setShowConversations] = useState<boolean>(false);
+  const [selectedConversation, setSelectedConversation] =
+    useState<Conversation | null>(null);
+
+  const messagesEndRef = useRef<HTMLDivElement>(null);
+  const simbaAnswers = ["meow.", "hiss...", "purrrrrr", "yowOWROWWowowr"];
+
+  const scrollToBottom = () => {
+    messagesEndRef.current?.scrollIntoView({ behavior: "smooth" });
+  };
+
+  const handleSelectConversation = (conversation: Conversation) => {
+    setShowConversations(false);
+    setSelectedConversation(conversation);
+    const loadMessages = async () => {
+      try {
+        const fetchedConversation = await conversationService.getConversation(
+          conversation.id,
+        );
+        setMessages(
+          fetchedConversation.messages.map((message) => ({
+            text: message.text,
+            speaker: message.speaker,
+          })),
+        );
+      } catch (error) {
+        console.error("Failed to load messages:", error);
+      }
+    };
+    loadMessages();
+  };
+
+  const loadConversations = async () => {
+    try {
+      const fetchedConversations =
+        await conversationService.getAllConversations();
+      const parsedConversations = fetchedConversations.map((conversation) => ({
+        id: conversation.id,
+        title: conversation.name,
+      }));
+      setConversations(parsedConversations);
+      setSelectedConversation(parsedConversations[0]);
+      console.log(parsedConversations);
+    } catch (error) {
+      console.error("Failed to load messages:", error);
+    }
+  };
+
+  const handleCreateNewConversation = async () => {
+    const newConversation = await conversationService.createConversation();
+    await loadConversations();
+    setSelectedConversation({
+      title: newConversation.name,
+      id: newConversation.id,
+    });
+  };
+
+  useEffect(() => {
+    loadConversations();
+  }, []);
+
+  useEffect(() => {
+    scrollToBottom();
+  }, [messages]);
+
+  useEffect(() => {
+    const loadMessages = async () => {
+      if (selectedConversation == null) return;
+      try {
+        const conversation = await conversationService.getConversation(
+          selectedConversation.id,
+        );
+        setMessages(
+          conversation.messages.map((message) => ({
+            text: message.text,
+            speaker: message.speaker,
+          })),
+        );
+      } catch (error) {
+        console.error("Failed to load messages:", error);
+      }
+    };
+    loadMessages();
+  }, [selectedConversation]);
+
+  const handleQuestionSubmit = async () => {
+    if (!query.trim()) return; // Don't submit empty messages
+
+    const currMessages = messages.concat([{ text: query, speaker: "user" }]);
+    setMessages(currMessages);
+    setQuery(""); // Clear input immediately after submission
+
+    if (simbaMode) {
+      console.log("simba mode activated");
+      const randomIndex = Math.floor(Math.random() * simbaAnswers.length);
+      const randomElement = simbaAnswers[randomIndex];
+      setAnswer(randomElement);
+      setQuestionsAnswers(
+        questionsAnswers.concat([
+          {
+            question: query,
+            answer: randomElement,
+          },
+        ]),
+      );
+      return;
+    }
+
+    try {
+      const result = await conversationService.sendQuery(
+        query,
+        selectedConversation.id,
+      );
+      setQuestionsAnswers(
+        questionsAnswers.concat([{ question: query, answer: result.response }]),
+      );
+      setMessages(
+        currMessages.concat([{ text: result.response, speaker: "simba" }]),
+      );
+    } catch (error) {
+      console.error("Failed to send query:", error);
+      // If session expired, redirect to login
+      if (error instanceof Error && error.message.includes("Session expired")) {
+        setAuthenticated(false);
+      }
+    }
+  };
+
+  const handleQueryChange = (event: React.ChangeEvent<HTMLTextAreaElement>) => {
+    setQuery(event.target.value);
+  };
+
+  const handleKeyDown = (event: React.KeyboardEvent<HTMLTextAreaElement>) => {
+    // Submit on Enter, but allow Shift+Enter for new line
+    if (event.key === "Enter" && !event.shiftKey) {
+      event.preventDefault();
+      handleQuestionSubmit();
+    }
+  };
+
+  return (
+    <div className="h-screen bg-opacity-20">
+      <div className="bg-white/85 h-screen">
+        <div className="flex flex-row justify-center py-4">
+          <div className="flex flex-col gap-4 w-full px-4 sm:w-11/12 sm:max-w-2xl lg:max-w-4xl sm:px-0">
+            <div className="flex flex-col sm:flex-row gap-3 sm:gap-0 sm:justify-between">
+              <header className="flex flex-row justify-center gap-2 sticky top-0 z-10 bg-white">
+                <h1 className="text-2xl sm:text-3xl">ask simba!</h1>
+              </header>
+              <div className="flex flex-row gap-2 justify-center sm:justify-end">
+                <button
+                  className="p-2 h-11 border border-green-400 bg-green-200 hover:bg-green-400 cursor-pointer rounded-md text-sm sm:text-base"
+                  onClick={() => setShowConversations(!showConversations)}
+                >
+                  {showConversations
+                    ? "hide conversations"
+                    : "show conversations"}
+                </button>
+                <button
+                  className="p-2 h-11 border border-red-400 bg-red-200 hover:bg-red-400 cursor-pointer rounded-md text-sm sm:text-base"
+                  onClick={() => setAuthenticated(false)}
+                >
+                  logout
+                </button>
+              </div>
+            </div>
+            {showConversations && (
+              <ConversationList
+                conversations={conversations}
+                onCreateNewConversation={handleCreateNewConversation}
+                onSelectConversation={handleSelectConversation}
+              />
+            )}
+            {messages.map((msg, index) => {
+              if (msg.speaker === "simba") {
+                return <AnswerBubble key={index} text={msg.text} />;
+              }
+              return <QuestionBubble key={index} text={msg.text} />;
+            })}
+            <div ref={messagesEndRef} />
+            <footer className="flex flex-col gap-2 sticky bottom-0">
+              <div className="flex flex-row justify-between gap-2 grow">
+                <textarea
+                  className="p-3 sm:p-4 border border-blue-200 rounded-md grow bg-white min-h-[44px] resize-y"
+                  onChange={handleQueryChange}
+                  onKeyDown={handleKeyDown}
+                  value={query}
+                  rows={2}
+                  placeholder="Type your message... (Press Enter to send, Shift+Enter for new line)"
+                />
+              </div>
+              <div className="flex flex-row justify-between gap-2 grow">
+                <button
+                  className="p-3 sm:p-4 min-h-[44px] border border-blue-400 bg-blue-200 hover:bg-blue-400 cursor-pointer rounded-md flex-grow text-sm sm:text-base"
+                  onClick={() => handleQuestionSubmit()}
+                  type="submit"
+                >
+                  Submit
+                </button>
+              </div>
+              <div className="flex flex-row justify-center gap-2 grow items-center">
+                <input
+                  type="checkbox"
+                  onChange={(event) => setSimbaMode(event.target.checked)}
+                  className="w-5 h-5 cursor-pointer"
+                />
+                <p className="text-sm sm:text-base">simba mode?</p>
+              </div>
+            </footer>
+          </div>
+        </div>
+      </div>
+    </div>
+  );
+};

raggr-frontend/src/components/ConversationList.tsx

@@ -0,0 +1,63 @@
+import { useState, useEffect } from "react";
+
+import { conversationService } from "../api/conversationService";
+type Conversation = {
+  title: string;
+  id: string;
+};
+
+type ConversationProps = {
+  conversations: Conversation[];
+  onSelectConversation: (conversation: Conversation) => void;
+  onCreateNewConversation: () => void;
+};
+
+export const ConversationList = ({
+  conversations,
+  onSelectConversation,
+  onCreateNewConversation,
+}: ConversationProps) => {
+  const [conservations, setConversations] = useState(conversations);
+
+  useEffect(() => {
+    const loadConversations = async () => {
+      try {
+        const fetchedConversations =
+          await conversationService.getAllConversations();
+        setConversations(
+          fetchedConversations.map((conversation) => ({
+            id: conversation.id,
+            title: conversation.name,
+          })),
+        );
+      } catch (error) {
+        console.error("Failed to load messages:", error);
+      }
+    };
+    loadConversations();
+  }, []);
+
+  return (
+    <div className="bg-indigo-300 rounded-md p-3 sm:p-4 flex flex-col gap-1">
+      {conservations.map((conversation) => {
+        return (
+          <div
+            key={conversation.id}
+            className="border-blue-400 bg-indigo-300 hover:bg-indigo-200 cursor-pointer rounded-md p-3 min-h-[44px] flex items-center"
+            onClick={() => onSelectConversation(conversation)}
+          >
+            <p className="text-sm sm:text-base break-words">
+              {conversation.title}
+            </p>
+          </div>
+        );
+      })}
+      <div
+        className="border-blue-400 bg-indigo-300 hover:bg-indigo-200 cursor-pointer rounded-md p-3 min-h-[44px] flex items-center"
+        onClick={() => onCreateNewConversation()}
+      >
+        <p className="text-sm sm:text-base"> + Start a new thread</p>
+      </div>
+    </div>
+  );
+};

raggr-frontend/src/components/ConversationMenu.tsx

@@ -0,0 +1,24 @@
+type Conversation = {
+  title: string;
+  id: string;
+};
+
+type ConversationMenuProps = {
+  conversations: Conversation[];
+};
+
+export const ConversationMenu = ({ conversations }: ConversationMenuProps) => {
+  return (
+    <div className="absolute bg-white w-md rounded-md shadow-xl m-4 p-4">
+      <p className="py-2 px-4 rounded-md w-full text-xl font-bold">askSimba!</p>
+      {conversations.map((conversation) => (
+        <p
+          key={conversation.id}
+          className="py-2 px-4 rounded-md hover:bg-stone-200 w-full text-xl font-bold cursor-pointer"
+        >
+          {conversation.title}
+        </p>
+      ))}
+    </div>
+  );
+};

raggr-frontend/src/components/LoginScreen.tsx

@@ -0,0 +1,122 @@
+import { useState, useEffect } from "react";
+import { userService } from "../api/userService";
+
+type LoginScreenProps = {
+  setAuthenticated: (isAuth: boolean) => void;
+};
+
+export const LoginScreen = ({ setAuthenticated }: LoginScreenProps) => {
+  const [username, setUsername] = useState<string>("");
+  const [password, setPassword] = useState<string>("");
+  const [error, setError] = useState<string>("");
+  const [isChecking, setIsChecking] = useState<boolean>(true);
+
+  useEffect(() => {
+    // Check if user is already authenticated
+    const checkAuth = async () => {
+      const isValid = await userService.validateToken();
+      if (isValid) {
+        setAuthenticated(true);
+      }
+      setIsChecking(false);
+    };
+    checkAuth();
+  }, [setAuthenticated]);
+
+  const handleLogin = async (e?: React.FormEvent) => {
+    e?.preventDefault();
+
+    if (!username || !password) {
+      setError("Please enter username and password");
+      return;
+    }
+
+    try {
+      const result = await userService.login(username, password);
+      localStorage.setItem("access_token", result.access_token);
+      localStorage.setItem("refresh_token", result.refresh_token);
+      setAuthenticated(true);
+      setError("");
+    } catch (err) {
+      setError("Login failed. Please check your credentials.");
+      console.error("Login error:", err);
+    }
+  };
+
+  const handleKeyPress = (e: React.KeyboardEvent) => {
+    if (e.key === "Enter") {
+      handleLogin();
+    }
+  };
+
+  // Show loading state while checking authentication
+  if (isChecking) {
+    return (
+      <div className="h-screen bg-opacity-20">
+        <div className="bg-white/85 h-screen flex items-center justify-center">
+          <div className="text-center">
+            <p className="text-lg sm:text-xl">Checking authentication...</p>
+          </div>
+        </div>
+      </div>
+    );
+  }
+
+  return (
+    <div className="h-screen bg-opacity-20">
+      <div className="bg-white/85 h-screen">
+        <div className="flex flex-row justify-center py-4">
+          <div className="flex flex-col gap-4 w-full px-4 sm:w-11/12 sm:max-w-2xl lg:max-w-4xl sm:px-0">
+            <div className="flex flex-col gap-1">
+              <div className="flex flex-grow justify-center w-full bg-amber-400 p-2">
+                <h1 className="text-base sm:text-xl font-bold text-center">
+                  I AM LOOKING FOR A DESIGNER. THIS APP WILL REMAIN UGLY UNTIL A
+                  DESIGNER COMES.
+                </h1>
+              </div>
+              <header className="flex flex-row justify-center gap-2 grow sticky top-0 z-10 bg-white">
+                <h1 className="text-2xl sm:text-3xl">ask simba!</h1>
+              </header>
+              <label htmlFor="username" className="text-sm sm:text-base">
+                username
+              </label>
+              <input
+                type="text"
+                id="username"
+                name="username"
+                value={username}
+                onChange={(e) => setUsername(e.target.value)}
+                onKeyPress={handleKeyPress}
+                className="border border-s-slate-950 p-3 rounded-md min-h-[44px]"
+              />
+              <label htmlFor="password" className="text-sm sm:text-base">
+                password
+              </label>
+              <input
+                type="password"
+                id="password"
+                name="password"
+                value={password}
+                onChange={(e) => setPassword(e.target.value)}
+                onKeyPress={handleKeyPress}
+                className="border border-s-slate-950 p-3 rounded-md min-h-[44px]"
+              />
+              {error && (
+                <div className="text-red-600 font-semibold text-sm sm:text-base">
+                  {error}
+                </div>
+              )}
+            </div>
+
+            <button
+              className="p-3 sm:p-4 min-h-[44px] border border-blue-400 bg-blue-200 hover:bg-blue-400 cursor-pointer rounded-md flex-grow text-sm sm:text-base"
+              onClick={handleLogin}
+            >
+              login
+            </button>
+          </div>
+        </div>
+      </div>
+    </div>
+  );
+};

raggr-frontend/src/components/QuestionBubble.tsx

@@ -0,0 +1,11 @@
+type QuestionBubbleProps = {
+  text: string;
+};
+
+export const QuestionBubble = ({ text }: QuestionBubbleProps) => {
+  return (
+    <div className="rounded-md bg-stone-200 p-3 sm:p-4 break-words overflow-wrap-anywhere text-sm sm:text-base">
+      🤦: {text}
+    </div>
+  );
+};

raggr-frontend/src/contexts/AuthContext.tsx

@@ -0,0 +1,56 @@
+import { createContext, useContext, useState, ReactNode } from "react";
+import { userService } from "../api/userService";
+
+interface AuthContextType {
+  token: string | null;
+  login: (username: string, password: string) => Promise<any>;
+  logout: () => void;
+  isAuthenticated: () => boolean;
+}
+
+const AuthContext = createContext<AuthContextType | undefined>(undefined);
+
+interface AuthProviderProps {
+  children: ReactNode;
+}
+
+export const AuthProvider = ({ children }: AuthProviderProps) => {
+  const [token, setToken] = useState(localStorage.getItem("access_token"));
+
+  const login = async (username: string, password: string) => {
+    try {
+      const data = await userService.login(username, password);
+      setToken(data.access_token);
+      localStorage.setItem("access_token", data.access_token);
+      localStorage.setItem("refresh_token", data.refresh_token);
+      return data;
+    } catch (error) {
+      console.error("Login failed:", error);
+      throw error;
+    }
+  };
+
+  const logout = () => {
+    setToken(null);
+    localStorage.removeItem("access_token");
+    localStorage.removeItem("refresh_token");
+  };
+
+  const isAuthenticated = () => {
+    return token !== null && token !== undefined && token !== "";
+  };
+
+  return (
+    <AuthContext.Provider value={{ token, login, logout, isAuthenticated }}>
+      {children}
+    </AuthContext.Provider>
+  );
+};
+
+export const useAuth = () => {
+  const context = useContext(AuthContext);
+  if (context === undefined) {
+    throw new Error("useAuth must be used within an AuthProvider");
+  }
+  return context;
+};

raggr-frontend/src/env.d.ts

@@ -0,0 +1,11 @@
+/// <reference types="@rsbuild/core/types" />
+
+/**
+ * Imports the SVG file as a React component.
+ * @requires [@rsbuild/plugin-svgr](https://npmjs.com/package/@rsbuild/plugin-svgr)
+ */
+declare module '*.svg?react' {
+  import type React from 'react';
+  const ReactComponent: React.FunctionComponent<React.SVGProps<SVGSVGElement>>;
+  export default ReactComponent;
+}

raggr-frontend/src/index.tsx

@@ -0,0 +1,13 @@
+import React from 'react';
+import ReactDOM from 'react-dom/client';
+import App from './App';
+
+const rootEl = document.getElementById('root');
+if (rootEl) {
+  const root = ReactDOM.createRoot(rootEl);
+  root.render(
+    <React.StrictMode>
+      <App />
+    </React.StrictMode>,
+  );
+}

raggr-frontend/tsconfig.json

@@ -0,0 +1,25 @@
+{
+  "compilerOptions": {
+    "lib": ["DOM", "ES2020"],
+    "jsx": "react-jsx",
+    "target": "ES2020",
+    "noEmit": true,
+    "skipLibCheck": true,
+    "useDefineForClassFields": true,
+
+    /* modules */
+    "module": "ESNext",
+    "moduleDetection": "force",
+    "moduleResolution": "bundler",
+    "verbatimModuleSyntax": true,
+    "resolveJsonModule": true,
+    "allowImportingTsExtensions": true,
+    "noUncheckedSideEffectImports": true,
+
+    /* type checking */
+    "strict": true,
+    "noUnusedLocals": true,
+    "noUnusedParameters": true
+  },
+  "include": ["src"]
+}

request.py

@@ -1,31 +1,43 @@
 import os
 import tempfile
 import httpx
+import logging
 
 from dotenv import load_dotenv
 
 load_dotenv()
 
+logging.basicConfig(level=logging.INFO)
+
 
 class PaperlessNGXService:
     def __init__(self):
         self.base_url = os.getenv("BASE_URL")
         self.token = os.getenv("PAPERLESS_TOKEN")
-        self.url = f"http://{os.getenv("BASE_URL")}/api/documents/?query=simba"
-        self.headers = {"Authorization": f"Token {os.getenv("PAPERLESS_TOKEN")}"}
+        self.url = f"http://{os.getenv('BASE_URL')}/api/documents/?tags__id=8"
+        self.headers = {"Authorization": f"Token {os.getenv('PAPERLESS_TOKEN')}"}
 
     def get_data(self):
         print(f"Getting data from: {self.url}")
         r = httpx.get(self.url, headers=self.headers)
-        return r.json()["results"]
+        results = r.json()["results"]
+
+        nextLink = r.json().get("next")
+
+        while nextLink:
+            r = httpx.get(nextLink, headers=self.headers)
+            results += r.json()["results"]
+            nextLink = r.json().get("next")
+
+        return results
 
     def get_doc_by_id(self, doc_id: int):
-        url = f"http://{os.getenv("BASE_URL")}/api/documents/{doc_id}/"
+        url = f"http://{os.getenv('BASE_URL')}/api/documents/{doc_id}/"
         r = httpx.get(url, headers=self.headers)
         return r.json()
 
     def download_pdf_from_id(self, id: int) -> str:
-        download_url = f"http://{os.getenv("BASE_URL")}/api/documents/{id}/download/"
+        download_url = f"http://{os.getenv('BASE_URL')}/api/documents/{id}/download/"
         response = httpx.get(
             download_url, headers=self.headers, follow_redirects=True, timeout=30
         )
@@ -39,10 +51,35 @@ class PaperlessNGXService:
         return pdf_to_process
 
     def upload_cleaned_content(self, document_id, data):
-        PUTS_URL = f"http://{os.getenv("BASE_URL")}/api/documents/{document_id}/"
+        PUTS_URL = f"http://{os.getenv('BASE_URL')}/api/documents/{document_id}/"
         r = httpx.put(PUTS_URL, headers=self.headers, data=data)
         r.raise_for_status()
 
+    def upload_description(self, description_filepath, file, title, exif_date: str):
+        POST_URL = f"http://{os.getenv('BASE_URL')}/api/documents/post_document/"
+        files = {"document": ("description_filepath", file, "application/txt")}
+        data = {
+            "title": title,
+            "create": exif_date,
+            "document_type": 3,
+            "tags": [7],
+        }
+
+        r = httpx.post(POST_URL, headers=self.headers, data=data, files=files)
+        r.raise_for_status()
+
+    def get_tags(self):
+        GET_URL = f"http://{os.getenv('BASE_URL')}/api/tags/"
+        r = httpx.get(GET_URL, headers=self.headers)
+        data = r.json()
+        return {tag["id"]: tag["name"] for tag in data["results"]}
+
+    def get_doctypes(self):
+        GET_URL = f"http://{os.getenv('BASE_URL')}/api/document_types/"
+        r = httpx.get(GET_URL, headers=self.headers)
+        data = r.json()
+        return {doctype["id"]: doctype["name"] for doctype in data["results"]}
+
 
 if __name__ == "__main__":
     pp = PaperlessNGXService()

startup.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+echo "Running database migrations..."
+aerich upgrade
+
+echo "Starting reindex process..."
+python main.py "" --reindex
+
+echo "Starting Flask application..."
+python app.py