A Python API that exposes AI backends, via FastAPI and gRPC, in the OpenAI API specification.
See the LeapfrogAI documentation website for system requirements and dependencies.
- UDS Kubernetes cluster bootstrapped with UDS Core Slim Dev for local KeyCloak authentication, Istio Service Mesh, and MetalLB advertisement
- Supabase for a vector database to store resulting embeddings in, and user management and authentication
- Text Embeddings for RAG
- LLaMA C++ Python or vLLM for completions and chat completions
To build and deploy the API Zarf package into an existing UDS Kubernetes cluster:
Important
Execute the following commands from the root of the LeapfrogAI repository
make build-api LOCAL_VERSION=dev FLAVOR=upstream
uds zarf package deploy packages/api/zarf-package-leapfrogai-api-*-dev.tar.zst --confirm
For other package flavors, use the following example:
make build-api FLAVOR=registry1
uds zarf package deploy packages/api/zarf-package-leapfrogai-api-*-dev.tar.zst --confirm
See the source code documentation for running the API from the source code for local Python environment development.