initial docker config

.env.example

@@ -1,5 +1,5 @@
 # override this to your own model config toml
-LITELLM_CONFIG_PATH=model.config.toml
+LITELLM_CONFIG_PATH=./credentials/model.config.example.toml
 
 # Azure OpenAI Configuration (Legacy)
 AZURE_OPENAI_MODEL=your_model_name_here # e.g., o3-mini-deep-research
@@ -22,8 +22,10 @@ AWS_ACCESS_KEY_ID=your_aws_access_key_id
 AWS_SECRET_ACCESS_KEY=your_aws_secret_access_key
 SENDER_EMAIL=your_sender_email@domain.com
 
-# JINA API Key
+# External Services
 JINA_API_KEY="YOUR_JINA_API_KEY" # Leave blank if not using deep research
+BRAVE_SEARCH_API_KEY=""
+RAPIDAPI_KEY=""
 
 # LLM Routing Configuration
 # GPT-4o-mini Instance 1
@@ -53,6 +55,7 @@ SUPABASE_URL=your_supabase_url
 SUPABASE_KEY=your_supabase_key
 SUPABASE_SERVICE_ROLE_KEY=your_supabase_service_role_key
 WHITELIST_SIGNUP_URL=your_whitelist_signup_url # e.g., https://yourdomain.com/
+FRONTEND_URL=https://mxtoai.com/
 
 # Server Configuration
 PORT=8000

README.md

@@ -96,10 +96,58 @@ poetry run python run_api.py
 ```
 
 5. Start the workers:
+
+Using only single process and couple of threads for local development:
+
+```bash
+poetry run dramatiq mxtoai.tasks --processes 1 --threads 2 --watch ./.
+```
+
+### Docker Setup (Alternative Installation)
+
+The project can also be run using Docker Compose, which provides an isolated environment with all required services.
+
+1. Ensure you have Docker and Docker Compose installed on your system.
+
+2. Build and start all services:
 ```bash
-poetry run dramatiq mxtoai.tasks --watch ./.
+docker compose up -d
 ```
 
+3. Access the services:
+- API Server: http://localhost:8000
+- RabbitMQ Management: http://localhost:15672 (credentials: guest/guest)
+- Redis: localhost:6379
+- Ollama: localhost:11434 (optional)
+
+#### Service Details
+- **API Server**: FastAPI application running on port 8000
+- **Worker**: Background task processor using Dramatiq
+- **Redis**: Used for caching and session management
+- **RabbitMQ**: Message broker for task queue
+- **Ollama**: Optional LLM service (disabled by default)
+
+#### Running with Ollama
+To include the Ollama service (required for local LLM processing):
+```bash
+docker compose --profile ollama up -d
+```
+
+#### Stopping Services
+```bash
+# Stop all services
+docker compose down
+
+# Stop and remove all data volumes (this will delete all data)
+docker compose down -v
+```
+
+#### Important Notes
+- The Docker setup includes all required services (Redis, RabbitMQ) automatically
+- Model configuration file (`model.config.toml`) should be placed in the `credentials/` directory
+- All services are configured to restart automatically unless stopped manually
+- Data persistence is enabled for Redis, RabbitMQ, and Ollama through Docker volumes
+
 ### Environment Variables
 
 Copy the `.env.example` file to `.env` and update with your specific configuration:
@@ -110,6 +158,46 @@ LITELLM_CONFIG_PATH=model.config.toml
 # Redis configuration
 REDIS_HOST=localhost
 REDIS_PORT=6379
+REDIS_DB=0
+REDIS_PASSWORD=
+
+# rabbitmq config
+RABBITMQ_HOST=localhost
+RABBITMQ_PORT=5672
+RABBITMQ_USER=guest
+RABBITMQ_PASSWORD=guest
+RABBITMQ_VHOST=/
+RABBITMQ_HEARTBEAT=60 # Default heartbeat interval in seconds
+
+# server config
+PORT=8000
+HOST=0.0.0.0
+LOG_LEVEL=INFO
+IS_PROD=false
+X_API_KEY=your_api_key
+
+# supabase
+SUPABASE_URL=your_supabase_url
+SUPABASE_KEY=your_supabase_key
+SUPABASE_SERVICE_ROLE_KEY=your_supabase_service_role_key
+WHITELIST_SIGNUP_URL=your_whitelist_signup_url # e.g., https://yourdomain.com/
+
+# open ai api key
+AZURE_OPENAI_API_KEY=your_api_key_here
+
+# Hugging Face Token
+HF_TOKEN=your_huggingface_token
+
+# AWS SES Configuration
+AWS_REGION=your_aws_region # e.g., ap-south-1
+AWS_ACCESS_KEY_ID=your_aws_access_key_id
+AWS_SECRET_ACCESS_KEY=your_aws_secret_access_key
+SENDER_EMAIL=your_sender_email@domain.com
+
+# External services
+JINA_API_KEY="YOUR_JINA_API_KEY" # Leave blank if not using deep research
+BRAVE_SEARCH_API_KEY=""
+RAPIDAPI_KEY=""
 
 # Optional for research functionality
 JINA_API_KEY=your-jina-api-key
@@ -122,7 +210,7 @@ AZURE_VISION_KEY=your-azure-vision-key
 SERPAPI_API_KEY=your-serpapi-api-key
 ```
 
-This project supports load balancing and routing across multiple models, so you can define as many models as you'd like. Copy `model.config.example.toml` to a toml file and update it with your preferred configuration. Update `.env` with the path your toml relative to root.
+This project supports load balancing and routing across multiple models, so you can define as many models as you'd like. Copy `credentials/model.config.example.toml` to a toml file and update it in the same directory with your preferred configuration. Update `.env` with the path your toml relative to root.
 
 A sample configuration looks like this:
 

docker-compose.yml

@@ -0,0 +1,90 @@
+version: "3.9"
+
+services:
+  redis:
+    image: redis:7-alpine
+    container_name: redis
+    ports:
+      - ${REDIS_PORT:-6379}:${REDIS_PORT:-6379}
+    volumes:
+      - redis_data:/data
+    restart: unless-stopped
+    command: ["redis-server", "--requirepass", "${REDIS_PASSWORD:-changeme}"]
+
+  rabbitmq:
+    image: rabbitmq:3-management
+    container_name: rabbitmq
+    ports:
+      - ${RABBITMQ_PORT:-5672}:${RABBITMQ_PORT:-5672}
+      - ${RABBITMQ_MANAGEMENT_PORT:-15672}:${RABBITMQ_MANAGEMENT_PORT:-15672}
+    volumes:
+      - rabbitmq_data:/var/lib/rabbitmq
+    environment:
+      RABBITMQ_DEFAULT_USER: ${RABBITMQ_USER:-guest}
+      RABBITMQ_DEFAULT_PASS: ${RABBITMQ_PASSWORD:-guest}
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "rabbitmq-diagnostics", "ping"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+
+  ollama:
+    image: ollama/ollama:latest
+    container_name: ollama
+    ports:
+      - ${OLLAMA_PORT:-11434}:${OLLAMA_PORT:-11434}
+    volumes:
+      - ollama_data:/root/.ollama
+    restart: unless-stopped
+    profiles:
+      - ollama
+
+  api_server:
+    build:
+      context: .
+      dockerfile: docker/api_server.dockerfile
+    container_name: api_server
+    env_file:
+      - .env
+    depends_on:
+      rabbitmq:
+        condition: service_healthy
+      redis:
+        condition: service_started
+    ports:
+      - "8000:8000"
+    environment:
+      - REDIS_URL=redis://:${REDIS_PASSWORD:-changeme}@redis:${REDIS_PORT:-6379}/0
+      - RABBITMQ_URL=amqp://${RABBITMQ_USER:-guest}:${RABBITMQ_PASSWORD:-guest}@rabbitmq:${RABBITMQ_PORT:-5672}/
+      - OLLAMA_URL=http://ollama:${OLLAMA_PORT:-11434}
+      - LITELLM_CONFIG_PATH=/app/credentials/model.config.toml
+    volumes:
+      - ./credentials/model.config.toml:/app/credentials/model.config.toml
+    command: ["poetry", "run", "uvicorn", "mxtoai.api:app", "--host", "0.0.0.0", "--port", "8000", "--workers", "4"]
+
+  worker:
+    build:
+      context: .
+      dockerfile: docker/worker.dockerfile
+    container_name: worker
+    env_file:
+      - .env
+    depends_on:
+      rabbitmq:
+        condition: service_healthy
+      redis:
+        condition: service_started
+    environment:
+      - REDIS_URL=redis://:${REDIS_PASSWORD:-changeme}@redis:${REDIS_PORT:-6379}/0
+      - RABBITMQ_URL=amqp://${RABBITMQ_USER:-guest}:${RABBITMQ_PASSWORD:-guest}@rabbitmq:${RABBITMQ_PORT:-5672}/
+      - OLLAMA_URL=http://ollama:${OLLAMA_PORT:-11434}
+      - LITELLM_CONFIG_PATH=/app/credentials/model.config.toml
+    volumes:
+      - ./credentials/model.config.toml:/app/credentials/model.config.toml
+    command: ["poetry", "run", "dramatiq", "mxtoai.tasks", "--watch", "./."]
+
+volumes:
+  rabbitmq_data:
+  ollama_data:
+  redis_data:

docker/api_server.dockerfile

@@ -0,0 +1,28 @@
+FROM python:3.13-slim-bookworm
+
+# System dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    curl \
+    build-essential \
+    ffmpeg \
+ && rm -rf /var/lib/apt/lists/*
+
+# Set working directory
+WORKDIR /app
+
+# Install Poetry (latest)
+RUN curl -sSL https://install.python-poetry.org | python3 - && \
+    ln -s /root/.local/bin/poetry /usr/local/bin/poetry
+
+# Copy dependency files first (for cache)
+COPY pyproject.toml poetry.lock ./
+
+# Install dependencies (no virtualenv)
+RUN poetry config virtualenvs.create false && poetry install --no-root --no-interaction --no-ansi
+
+# Copy only the relevant application code
+COPY mxtoai ./mxtoai
+COPY run_api.py .
+
+# Run the API via uvicorn
+CMD ["poetry", "run", "uvicorn", "mxtoai.api:app", "--host", "0.0.0.0", "--port", "8000", "--workers", "4"]

docker/worker.dockerfile

@@ -0,0 +1,27 @@
+FROM python:3.13-slim-bookworm
+
+# System dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    curl \
+    build-essential \
+    ffmpeg \
+ && rm -rf /var/lib/apt/lists/*
+
+# Set working directory
+WORKDIR /app
+
+# Install Poetry (latest)
+RUN curl -sSL https://install.python-poetry.org | python3 - && \
+    ln -s /root/.local/bin/poetry /usr/local/bin/poetry
+
+# Copy dependency files first (for cache)
+COPY pyproject.toml poetry.lock ./
+
+# Install dependencies
+RUN poetry config virtualenvs.create false && poetry install --no-root --no-interaction --no-ansi
+
+# Copy only the relevant worker code
+COPY mxtoai ./mxtoai
+
+# Run the Dramatiq worker
+CMD ["poetry", "run", "dramatiq", "mxtoai.tasks", "--watch", "./mxtoai"]

docusaurus-site/docs/introduction.md

@@ -8,7 +8,7 @@ Welcome to MXtoAI!
 
 MXtoAI is an intelligent email assistant that processes users emails automatically. Users simply forward any email to our specialized handles (email IDs) and the appropriate actions are taken. Most of the actions are AI driven.
 
-Forward emails to our general email handle `ask@mxtoai.com` or to one of our specialized handles. Get summaries, replies, and research without the complexity.
+Forward emails to our general email handle `ask@mxtoai.com` or to one of our specialized handles. Get summaries, replies, research, and professional PDF exports without the complexity.
 
 ![Forwarding email to ask@mxtoai.com](/img/mxtoai-ask.gif)
 *Example: Forwarding an email to ask@mxtoai.com with instructions.*

docusaurus-site/docs/usage.md

@@ -18,7 +18,10 @@ Here's a brief overview of the available handles and their primary functions:
 *   `background@mxtoai.com`: Get background information on entities mentioned.
 *   `ask@mxtoai.com`: Ask specific questions about the email content.
 *   `schedule@mxtoai.com`: Extract scheduling information or propose meeting times.
+*   `pdf@mxtoai.com`: Export email content as a professional PDF document.
 
 For detailed information on each handle, including aliases and key features, please refer to the [Email Handles section on our website](https://www.mxtoai.com/#usecases).
 
 **Pro tip:** Add our email handles to your contacts for quicker access when forwarding emails.
+
+**Note:** Any handle can export content as PDF by simply asking "convert to PDF" or "export as PDF" in your request.

docusaurus-site/docs/why-use-mxtoai.md

@@ -8,8 +8,9 @@
 - Works anywhere - Gmail, Outlook, Apple Mail, even your phone
 - Works with attachments - PDFs, images, spreadsheets all processed
 - Works with email threads - understands context from conversation history
+- **PDF Export** - any response can be converted to PDF, or use pdf@ to export content directly
 
-As simple as it sounds, MXtoAI is very powerful. If you spend more than 10 minutes a day reading, understanding, or responding to emails, MXtoAI can probably save you time and mental energy. Whether you're dealing with work emails, personal correspondence, or staying informed, there's likely a use case that fits your daily routine. Here are some use-cases you can use it for.
+As simple as it sounds, MXtoAI is very powerful. If you spend more than 10 minutes a day reading, understanding, or responding to emails, MXtoAI can probably save you time and mental energy. Whether you're dealing with work emails, personal correspondence, or staying informed, there's likely a use case that fits your daily routine. Plus, any content generated can be exported as a professional PDF for sharing, printing, or archiving. Here are some use-cases you can use it for.
 
 ## 📧 Daily Email Management
 
@@ -70,6 +71,10 @@ As simple as it sounds, MXtoAI is very powerful. If you spend more than 10 minut
 - Forward to summarize@mxtoai.com - get key requirements and deadlines
 - Forward to ask@mxtoai.com with "What's our competitive advantage here?"
 
+**"I need to document compliance or regulatory communications"**
+- Forward regulatory emails to pdf@mxtoai.com for permanent, clean records
+- Perfect for audit trails and compliance documentation
+
 ## 🔍 Information Verification & Research
 
 **"I get forwarded news and want to check if it's true"**
@@ -88,6 +93,20 @@ As simple as it sounds, MXtoAI is very powerful. If you spend more than 10 minut
 - Forward competitor emails to background@mxtoai.com
 - Get market position, recent moves, customer feedback
 
+## 📄 PDF Export & Document Creation
+
+**"I need to create professional documents from email content"**
+- Forward newsletters to pdf@mxtoai.com - get clean, formatted PDF without email headers
+- Perfect for sharing research, reports, or important communications
+
+**"I want to convert AI responses to shareable documents"**
+- Ask any handle to "generate a report and convert to PDF"
+- Forward to ask@mxtoai.com with "Create a HN newsletter with top AI posts of the week and export as PDF"
+
+**"I need to archive important email content professionally"**
+- Forward contracts, agreements, or important announcements to pdf@mxtoai.com
+- Get clean documents without email clutter - perfect for filing or legal records
+
 ## 🏠 Personal Life
 
 **"I get complex medical/insurance emails"**
@@ -128,6 +147,10 @@ As simple as it sounds, MXtoAI is very powerful. If you spend more than 10 minut
 - Forward to ask@mxtoai.com with "What are the practical applications?"
 - Understand real-world relevance quickly
 
+**"I want to compile research findings into shareable documents"**
+- Forward multiple research emails to ask@mxtoai.com with "Synthesize findings and create PDF report"
+- Perfect for thesis research or professional development
+
 ## 🛍️ Shopping & Consumer Decisions
 
 **"I get overwhelmed by product comparison emails"**
@@ -199,6 +222,7 @@ As simple as it sounds, MXtoAI is very powerful. If you spend more than 10 minut
 **Consultant:**
 - "I forward client emails to background@mxtoai.com before meetings to understand industry challenges"
 - "I forward RFPs to ask@mxtoai.com with 'What's the hidden agenda here?' to win more bids"
+- "I forward research findings to ask@mxtoai.com with 'Create client presentation and export as PDF' for professional deliverables"
 
 **Retiree:**
 - "I forward Medicare emails to simplify@mxtoai.com - healthcare is confusing enough"