Spaces:
Running on L4
Running on L4
|
Download README.md from nvidia/simready-central: direct link, hf CLI and curl.
- Browser
- Download file 821 Bytes
-
https://huggingface.co/spaces/nvidia/simready-central/resolve/main/README.md
- Command line
-
hf download hf://spaces/nvidia/simready-central/README.md
-
curl -L -o README.md https://huggingface.co/spaces/nvidia/simready-central/resolve/main/README.md
821 Bytes
metadata
title: SimReady Central USD Search
emoji: ๐
colorFrom: green
colorTo: blue
sdk: docker
app_port: 7860
startup_duration_timeout: 1h
hardware: l4x4
SimReady Central USD Search
SimReady Central USD Search โ single-container demo (OpenSearch + Neo4j +
Redis + deepsearch-api + asset-graph-service, SigLIP2 embeddings via a local
siglip2-triton process โ see docker/Dockerfile.hf-space-gpu). Runs on a GPU
hardware tier (l4x4), unlike the free-tier
docker/Dockerfile.hf-space variant, which routes SigLIP2 to NVCF instead.
The index itself is pulled from the artifact S3 bucket at container
startup, not baked in. Deployed by
github.com/NVIDIA-dev/simready-central-indexing-internal's
python -m pipeline.run_pipeline deploy-space-gpu.
Third-party notices: THIRD_PARTY_NOTICE.md.