# Release Notes: Visual Search and QA ## Version 2026.3.0 **Helm Chart Version**: 1.1.0 **Release Date**: October 9, 2026 **Changes**: - Data Preparation: - Replaced the Milvus-specific data preparation microservice with the generic Multimodal DataPrep microservice, which is shared with other applications. - Media is embedded in place from the shared data mount, so ingesting a directory no longer stores a second copy of the media on disk. - Re-running an update against the same directory now skips already ingested files instead of duplicating them. - Object detection is disabled by default. Only full frames are indexed, which keeps search results free of crop duplicates. Set `MM_DATAPREP_ENABLE_OBJECT_DETECTION` and `DATA_INGEST_WITH_DETECT` to enable it. - Object detection now uses Hugging Face OpenVINO models. Set `DATAPREP_DETECTION_MODEL` (Helm `MM_DATAPREP_DETECTION_MODEL_NAME`) to an `OpenVINO/` object-detection model such as `OpenVINO/yolox_s-int8-ov`. It has no default and is required whenever object detection is enabled. The optional `DATAPREP_DETECTION_CLASSES` keeps only the listed classes. Downloaded models are cached in the `dataprep-detection-models` volume; the former `dataprep-yolox-models` volume is no longer used and can be removed. - Added `DATAPREP_PIPELINE_STALL_TIMEOUT_S` (default 300s), which fails an ingest job whose pipeline stops making progress instead of leaving it running indefinitely. Set it to 0 to disable the watchdog. - Helm Chart: - The chart is no longer tied to a namespace named `vsqa`. In-cluster service addresses are derived from the release namespace, so it can be installed into any namespace. - Added `resources` on the VLM, embedding, and data preparation services to request Intel device plugin resources when running on GPU or NPU. - The render device group is now applied to the pods, so a non-root container user can open `/dev/dri/renderD*`. - Added `global.nodeSelector` to pin the pods to the node that holds the host data path and the accelerator devices. - Deployment: - Inference devices are now selected per microservice in Docker Compose instead of being derived from `EMBEDDING_DEVICE`. Setting a GPU for query embedding no longer moves the ingest pipeline onto the same device, where two copies of a large embedding model could exhaust it and make queries fail with `CL_OUT_OF_RESOURCES`. - The dataprep devices are now set with `DATAPREP_EMBEDDING_DEVICE` and `DATAPREP_DETECTION_DEVICE`, matching the other `DATAPREP_*` settings. The previous `MM_DATAPREP_*` names are still honoured. - Device defaults are now `CPU` for query embedding and `GPU` for the VLM and the ingest pipeline. The previous `GPU.1` default did not exist on platforms with a single GPU. - Documentation: - Documented device selection, device plugin resources, device group ids, node pinning, and the corresponding troubleshooting steps for Helm. - Documented the per-service device variables, their defaults, and the single-GPU contention caveat for Docker Compose. - Documented `HOST_DATA_PATH`, `HF_ENDPOINT` and `VLM_COMPRESSION_WEIGHT_FORMAT` in the Compose guide. `HF_ENDPOINT` defaults to a mirror intended for mainland China and has to be overridden to download models from Hugging Face directly. - VLM OpenVINO Serving is now consumed as a published image instead of being built from source. **Hardware Used for Validation**: - Intel® Core™ processors (13th Gen, i7 recommended) - Intel® Arc™ A-Series Graphics (Intel® Arc™ A770 recommended) ## Version 2025.2.0 **Helm Chart Version**: 1.0.0 **Release Date**: December 10, 2025 **Features**: - Visual Search: - Search images and videos using natural language queries. - Question Answering: - Ask questions about selected media and receive context-aware answers. - Microservices Architecture: - Includes data preparation, retriever, multimodal embedding, VLM serving, and a Streamlit-based web UI. **Hardware Used for Validation**: - Intel® Core™ processors (13th Gen, i7 recommended) - Intel® Arc™ A-Series Graphics (Intel® Arc™ A770 recommended)