v5.4.1

5.4.1 - 2026-07-16

Changed

• NC 35 support (#328) @kyteinsky

Fixed

• fix(pgvector): drop "id" column from access_list (#329) @kyteinsky

v5.4.0

5.4.0 - 2026-06-24

Highlights

• The indexing direction has been reversed now. Instead of the context_chat PHP app sending documents to the context_chat_backend ExApp, the ExApp downloads the documents from the server according to a list obtained from the PHP app. This also means that the occ context_chat:scan command serves no purpose and has been removed. Indexing should be smoother and run continuously now.
• Kubernetes support to scale the CPU computation
• Separate docker images for CPU, CUDA and ROCM (uses Vulkan) instead of one heavy CUDA/CPU image
• CUDA 12.8 is shipped in the CUDA image so the host drivers should be updated to this at the minimum.

Added

• add network embedding batching (#276) @fcharlaix-opendsi
• add kubernetes support and reverse content/indexing flow (#284) @kyteinsky @marcelklehr
• add gh workflows for docker builds and do separate cpu, cuda and rocm (vulkan) images (#295) @kyteinsky

Changed

• update readme according to the latest changes (#300) @kyteinsky
• bump llama_cpp_python to 0.3.23 (#301) @kyteinsky
• move task types to the backend (#321) @kyteinsky
• adjust comment in Dockerfile regarding RTX5090 support (#316) @kyteinsky

Fixed

• improve loadSources error handling (#288) @kyteinsky
• fix(pgvector): add chunking to prevent long list of args in queries (#290) @kyteinsky
• fix(pgvector): make doc deletion query faster (#289) @kyteinsky
• drop latin-1 decode in source title and userIds (#306) @kyteinsky
• handle validation errors of files and content providers individually (#308) @kyteinsky
• prevent race condition in vectordb tables creation (#308) @kyteinsky
• pass actual error in the error object (#308) @kyteinsky
• add container hostname to /etc/hosts to silence sudo warning (#311) @sanzakicesarr

v5.4.0-beta0

5.4.0-beta0 - 2026-05-26

Added

• add network embedding batching (#276) @fcharlaix-opendsi
• add kubernetes support and reverse content/indexing flow (#284) @kyteinsky @marcelklehr
• add gh workflows for docker builds and do separate cpu, cuda and rocm (vulkan) images (#295) @kyteinsky

Changed

• update readme according to the latest changes (#300) @kyteinsky
• bump llama_cpp_python to 0.3.23 (#301) @kyteinsky

Fixed

• improve loadSources error handling (#288) @kyteinsky
• fix(pgvector): add chunking to prevent long list of args in queries (#290) @kyteinsky
• fix(pgvector): make doc deletion query faster (#289) @kyteinsky

v5.3.0

Added

• migrate from httpx to niquests (#275) @kyteinsky
• added support for NC 34

Fixed

• deep copy config before redaction (#272) @kyteinsky

v4.6.0

Changed

• pin max NC version to 31

Fixed

• narrow down pip's package search (#238) @kyteinsky
• fix langchain package versions (#238) @kyteinsky
• ensure the decoded text from the document is utf-8 compat (#227) @kyteinsky
• make the wait message not look like an error (#226) @kyteinsky

Added

• support podman @oleksandr-nc

v5.2.0

5.2.0 - 2025-01-08

Added

• add HaRP support (#247) @kyteinsky
• support external embedding service for scaling (#248) @kyteinsky

Fixed

• setup env vars before any relevant imports (#251) @kyteinsky

v5.1.0

5.1.0 - 2025-12-05

Added

• add env var to skip model downloads from huggingface (#242) @kyteinsky

Fixed

• narrow down pip's package search and other ci fixes (#236) @kyteinsky

v5.0.1

5.0.1 - 2025-11-12

Fixed

• expand the source id regex item part (#232) @kyteinsky

Changed

• document HaRP being not supported (#231) @kyteinsky

v5.0.0

5.0.0 - 2025-10-15

Changed

• feat(podman): support build ExApp from source @oleksandr-nc
• min NC 32 and CI adjustment (#221) @kyteinsky

Fixed

• make the wait message not look like an error in em server (#225) @kyteinsky
• ensure the decoded text from the document is utf-8 compat (#223) @kyteinsky

v4.5.0

4.5.0 - 2025-09-23

Changed

• stable release of the 4.5.0-beta series
• bump max NC version to 33
• store worker logs and present them better (#200) @kyteinsky

Fixed

• better parsing of version string for repairs (#209) @kyteinsky
• suppress tokenizer max context length warning (#200) @kyteinsky
• fix nc_py_api to 0.20.2 (#200) @kyteinsky

Added

• add app version to file logs (#201) @kyteinsky