diff --git a/Makefile b/Makefile index 18b95bb..a5936dc 100644 --- a/Makefile +++ b/Makefile @@ -21,7 +21,7 @@ help: #.PHONY: build-push #build-push: # docker login ghcr.io -# docker buildx build --push --platform linux/arm64/v8,linux/amd64 --tag ghcr.io/nextcloud/context_chat_backend:5.4.0-beta0 --tag ghcr.io/nextcloud/context_chat_backend:latest . +# docker buildx build --push --platform linux/arm64/v8,linux/amd64 --tag ghcr.io/nextcloud/context_chat_backend:5.4.0 --tag ghcr.io/nextcloud/context_chat_backend:latest . .PHONY: run run: @@ -34,5 +34,5 @@ run: register: docker exec master-nextcloud-1 sudo -u www-data php occ app_api:app:unregister context_chat_backend --silent || true docker exec master-nextcloud-1 sudo -u www-data php occ app_api:app:register context_chat_backend manual_install --json-info \ - "{\"id\":\"context_chat_backend\",\"name\":\"Context Chat Backend\",\"daemon_config_name\":\"manual_install\",\"version\":\"5.4.0-beta0\",\"secret\":\"12345\",\"port\":10034,\"scopes\":[],\"system\":0}" \ + "{\"id\":\"context_chat_backend\",\"name\":\"Context Chat Backend\",\"daemon_config_name\":\"manual_install\",\"version\":\"5.4.0\",\"secret\":\"12345\",\"port\":10034,\"scopes\":[],\"system\":0}" \ --force-scopes --wait-finish diff --git a/README.md b/README.md index 0cc3b45..c956d85 100644 --- a/README.md +++ b/README.md @@ -73,7 +73,7 @@ If nextcloud is inside a container, `--add-host` option would be required by you **2. Register the app using the deploy daemon (be mindful of the port number and the app's version):** ``` occ app_api:app:register context_chat_backend manual_install --json-info \ -"{\"appid\":\"context_chat_backend\",\"name\":\"Context Chat Backend\",\"daemon_config_name\":\"manual_install\",\"version\":\"5.4.0-beta0\",\"secret\":\"12345\",\"port\":10034}" \ +"{\"appid\":\"context_chat_backend\",\"name\":\"Context Chat Backend\",\"daemon_config_name\":\"manual_install\",\"version\":\"5.4.0\",\"secret\":\"12345\",\"port\":10034}" \ --wait-finish ``` The command to unregister is given below (force is used to also remove apps whose container has been removed) @@ -228,7 +228,7 @@ sudo -u www-data php occ app_api:app:register \ --json-info "{\"appid\":\"context_chat_backend\",\ \"name\":\"Context Chat Backend\",\ \"daemon_config_name\":\"manual_install\",\ - \"version\":\"5.4.0-beta0\",\ + \"version\":\"5.4.0\",\ \"secret\":\"12345\",\ \"port\":10034}" \ --wait-finish diff --git a/appinfo/info.xml b/appinfo/info.xml index b54031e..f70e61d 100644 --- a/appinfo/info.xml +++ b/appinfo/info.xml @@ -20,7 +20,7 @@ Install the given apps for Context Chat to work as desired **in the given order* Setup background job workers as described here: https://docs.nextcloud.com/server/latest/admin_manual/ai/overview.html#improve-ai-task-pickup-speed ]]> - 5.4.0-beta0 + 5.4.0 agpl Anupam Kumar Context Chat @@ -35,7 +35,7 @@ Setup background job workers as described here: https://docs.nextcloud.com/serve ghcr.io nextcloud-releases/context_chat_backend - 5.4.0-beta0 + 5.4.0 diff --git a/changelog.md b/changelog.md index e5e5b06..f87051b 100644 --- a/changelog.md +++ b/changelog.md @@ -9,6 +9,36 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/) and this project adheres to [Semantic Versioning](http://semver.org/). +## 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 + + ## 5.4.0-beta0 - 2026-05-26 ### Added diff --git a/example.env b/example.env index f5ccfb6..3f4579b 100644 --- a/example.env +++ b/example.env @@ -18,7 +18,7 @@ AA_VERSION=3.0.0 APP_SECRET=12345 APP_ID=context_chat_backend APP_DISPLAY_NAME=Context Chat Backend -APP_VERSION=5.4.0-beta0 +APP_VERSION=5.4.0 APP_HOST=0.0.0.0 APP_PORT=10034 APP_PERSISTENT_STORAGE=persistent_storage diff --git a/pyproject.toml b/pyproject.toml index ad45267..219c3b9 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -2,7 +2,7 @@ # SPDX-License-Identifier: AGPL-3.0-or-later [project] name = "context_chat_backend" -version = "5.4.0-beta0" +version = "5.4.0" requires-python = ">=3.11" authors = [ { name = "Anupam Kumar", email = "kyteinsky@gmail.com" }