Installation & Requirements

System Requirements

Before installing Deeptrain, ensure your environment meets the following hardware and software specifications to handle multi-modal data processing efficiently.

Hardware Prerequisites

• CPU: Multi-core processor (Intel i5/AMD Ryzen 5 or higher recommended).
• Memory:
  • Minimum: 8 GB RAM.
  • Recommended: 16 GB+ RAM (required for processing large video files and high-density embedding databases).
• Storage: 5 GB of available space for initial setup; additional space required for local vector storage and media caching.
• GPU (Optional): While not strictly required for text-only processing, an NVIDIA GPU with CUDA support is highly recommended for accelerated image and video transcription tasks.

Software Prerequisites

• Operating System: Linux (Ubuntu 20.04+ recommended), macOS 12+, or Windows 10/11 (via WSL2).
• Python: Version 3.9 or higher.
• FFmpeg: Required for audio and video processing (transcription and frame extraction).
• Docker: Required for hosting localized embedding databases (e.g., ChromaDB, Milvus, or Qdrant) in a containerized environment.

Installation

Deeptrain can be installed directly from source. Follow these steps to set up your development environment.

1. Clone the Repository

Begin by cloning the VMTP repository to your local machine:

git clone https://github.com/UditAkhourii/VMTP.git
cd VMTP

2. Create a Virtual Environment

It is recommended to use a virtual environment to manage dependencies:

# Using venv
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install Dependencies

Install the required packages using pip. This includes the core engine and multi-modal processing libraries:

pip install --upgrade pip
pip install -r requirements.txt

4. Install FFmpeg

If you plan to use the Transcribe API or process Video/Audio, ensure FFmpeg is installed on your system:

• Ubuntu/Debian: sudo apt update && sudo apt install ffmpeg
• macOS: brew install ffmpeg
• Windows: Download the binary from the official FFmpeg site and add it to your PATH.

Configuration

Deeptrain requires configuration via environment variables to connect to LLM providers and embedding databases.

Environment Variables

Create a .env file in your root directory and populate it with your credentials:

# LLM Provider Configuration
OPENAI_API_KEY=your_openai_key
ANTHROPIC_API_KEY=your_anthropic_key

# Embedding Database Configuration
VECTOR_DB_TYPE=chroma  # options: chroma, pinecone, qdrant
VECTOR_DB_HOST=localhost
VECTOR_DB_PORT=8000

# Feature Flags
ENABLE_VIDEO_PROCESSING=true
ENABLE_COMPUTER_VISION=true

Database Setup

To use the localized embedding database feature, start your preferred vector store using Docker:

# Example: Running ChromaDB locally
docker run -p 8000:8000 chromadb/chroma

Verifying the Installation

To ensure that Deeptrain is correctly configured and can access your Python environment, run the following check:

import deeptrain

# Check connectivity and version
print(f"Deeptrain version: {deeptrain.__version__}")

# Initialize a basic client
client = deeptrain.Client()
print("System initialized successfully.")

If the system returns the version number and the success message, you are ready to begin integrating multi-modal data into your AI agents.