Networking
Neural Inverse can be deployed in a VPC or on-premises in high-security environments. This guide covers the networking requirements and considerations.
Architecture diagram (from architecture overview):
Network Exposure & Service Configuration
Only the langfuse/langfuse (web) container needs to be accessible by users, via API, and SDKs.
Optionally, this can be behind a firewall, proxy, or VPN.
By default PORT=3000 is used for the Neural Inverse Web container. This can be configured using the PORT environment variable (docs). Usually a network load balancer is used to expose the service and handle ssl termination (docs).
Neural Inverse is designed to be exposed publicly as a web service. This is penetration tested and secure by design as the Neural Inverse Team runs the same container for the managed Neural Inverse Cloud Offering. See security documentation of Neural Inverse Cloud for more details.
Internet Access
Neural Inverse does not require internet access.
Some optional components, like the LLM Playground and LLM-evals require access to an LLM API/Gateway. This can be deployed in the same VPC or peered with the VPC.
Neural Inverse pings a cached version of the GitHub API to check for updates to the Neural Inverse Server. If internet access is not available, this check will fail gracefully.
