ToolsRecipesCompareDGX SparkModelsAboutSponsor

โ† All tools

RAGFlow

Active Permissive (MIT/Apache/BSD) Server / Docker

Website ยท Source

License
Apache-2.0
Latest release
v1.0.0-rc1
Release date
2026-09-29
Hardware
4 cores, 16GB RAM, 50GB disk recommended (Docker)
Document types
PDF, scans, DOCX, XLSX, PPT, images
OCR / tables / retrieval
Strong: layout-aware parsing, OCR, table recognition, citations unverified
Cloud calls
None if pointed at Ollama/local embedder unverified
Fully offline
Yes

NVIDIA DGX Spark

DGX Spark: Known issues

No upstream ARM64 Docker images (GitHub issue #13845: exec format error); owner got v0.24.0 running only with a patched native build and onnxruntime-gpu compiled for SM_121. Source: https://forums.developer.nvidia.com/t/ragflow-v0-24-0-on-dgx-spark-working-native-arm64-build-with-gpu-accelerated-ocr/366321

DGX Spark guide โ†’

Comparisons

Last updated: 2026-10-24. License and release data from the GitHub API. Fields marked unverified have not yet been checked against official docs. Spot something wrong? Send a correction.

The RAGShelf weekly

New local RAG tools, releases, and tested setups. One email a week, no spam.