Run your own secure version of ChatGPT Enterprise in just a few minutes ⚡️

Multimodal GPT Slackbot is a comprehensive Docker image designed to enable businesses to empower their teams with the latest AI technologies provided by OpenAI, in a secure and efficient manner. By integrating OpenAI's APIs on the backend with Slack as the user interface, it offers a seamless experience for users to engage with multimodal AI capabilities directly within Slack.

• ✅ Conversation History
• ✅ GPT Vision Support
• ✅ Image Generation
• ✅ Text to Speech Conversion
• ✅ Speech to Text Conversion

To run Multimodal GPT Slackbot, you can choose from several options:

• Pull the Docker image:

docker pull skydockai/multimodal_gpt_slackbot:latest

• Configure Environment Variables: Download the config.env file and update the first three variables (SLACK_SOCKET_TOKEN, SLACK_BOT_USER_TOKEN, and OPENAI_KEY) with your Slack app tokens and OpenAI API key.

  (Note: If you use Azure OpenAI instead of OpenAI, please see this instruction)

• Run the Docker image:

docker run --env-file ./config.env multimodal_gpt_slackbot:latest

• Clone the source code:

git clone https://github.com/skydockAI/multimodal_gpt_slackbot.git

• Build the Docker image:

docker build -t multimodal_gpt_slackbot:latest .

• Configure and run: Follow the same steps as in the pre-built Docker image setup to configure your config.env and run the image.

• Clone the source code:

git clone https://github.com/skydockAI/multimodal_gpt_slackbot.git

• Configure environment variables: Update the config.env as described above.

• Run with Docker Compose:

docker compose up

• Conversation History: Maintains the context of each conversation within a Slack thread, ensuring continuity and ease of reference.

• GPT Vision Support: Utilizes the gpt-4-turbo model to provide cutting-edge vision capabilities.

• Image Generation: Leverages the Dall-E models to support creative and dynamic image generation.

• Text to Speech Conversion: Converts text messages into spoken words, enhancing accessibility.

• Speech to Text Conversion: Uses the Whisper model to transcribe spoken words into text, facilitating easy communication.

Multimodal GPT Slackbot is open-source and licensed under the GPL-3.0 license.