New research: ContextNest adds a governance layer beneath RAG for AI agents, using hash-chained version histories and audit traces. Governed selection beats BM25 (97% vs 93% pass rate) at a third the token cost. hubs.la/Q04tJ-fr0
🦉DVC
@DVCorg
Open source tool for data, models, & experiment versioning for ML projects. Join our stellar community dvc.org/support for help, support and insights.
- Proud to be a part of @lakeFS being named a Cool Vendor in Data Management. The world is catching up to the importance of data version control. 😎 Get the report: hubs.la/Q04sX88H0
- Sendoa Moronta's escape route from the final_v2_last.ipynb trap: treat data as fundamentally separate from code, version it with DVC, and keep notebooks as consumers — not owners — of your logic. 💫 👉🏽 hubs.la/Q04nZC2Q0
- For AI touching power grids and pipelines, the baseline here is non-negotiable: DVC and Git tracing every dataset behind a recommendation, plus physics-based constraint checks before anything reaches a control system. 👉🏽 hubs.la/Q04nYtMV0
- @truefoundry published a hands-on guide (auf Deutsch) to deploying DVC-versioned models straight to @kubernetes — dvc pull the model from S3, wrap it in @FastAPI, and ship it. 👉🏽 hubs.la/Q04nZ4Lg0
