AI Enterprise in isolated infrastructure
IDE Services offers an on-premises solution for air-gapped operations of AI Enterprise. This solution involves using on-premises models (like Llama 3.1 Instruct 70B powered by Hugging Face) for core AI Assistant features, and JetBrains Mellum for lightweight features and code completion.
Hugging Face installation.
Deploy Llama 3.1 Instruct 70B, use the instructions provided in the official Hugging Face documentation. Refer to this section to learn about model-specific requirements.
Follow the instructions provided in the JetBrains Mellum section to install and configure JetBrains Mellum.
Start the IDE Services Server, and use the Web UI to configure the Hugging Face provider.
Last modified: 07 April 2025