Releases: janhq/cortex.cpp
Releases · janhq/cortex.cpp
0.4.10
Changes
- chore: cortex.llamacpp to version 0.1.11 @vansangpfiev (#622)
- chore: add update notifier @louis-jan (#614)
- feat: python runtime engine @vansangpfiev (#559)
- feat: add cortex data folder @namchuai (#615)
- API: added the API reference decorator @irfanpena (#591)
- build extension able to run on windows @hiento09 (#613)
- feat: cortex client sdk compatible @louis-jan (#594)
- feat: store messages when chat via cli @namchuai (#599)
- feat: pull model yaml from hf @namchuai (#605)
- feat: get running models @vansangpfiev (#592)
🚀 Features
Contributor
@hiento09, @irfanpena, @louis-jan, @namchuai and @vansangpfiev
0.4.9
Changes
- chore: cortex.llamacpp to version 0.1.10 @vansangpfiev (#609)
- fix: add llama3 chat template @louis-jan (#608)
- chore: remove log @namchuai (#607)
- feat: pull model from jan hub @louis-jan (#606)
- chore: add model pull alias @louis-jan (#604)
- chore: update README.md @louis-jan (#603)
- chore: update README @louis-jan (#601)
- chore: remove parameter for run command @namchuai (#602)
- chore: cortex.llamacpp to v0.1.8 @vansangpfiev (#598)
- chore: remove inference stream @namchuai (#596)
- chore: clean up chat stream @namchuai (#593)
- feat: add model settings and prompt template from hf @namchuai (#588)
- chore: cortex.llamacpp v0.1.6 @vansangpfiev (#587)
- chore: cortex llama.cpp to version 0.1.5 @vansangpfiev (#586)
🧰 Maintenance
Contributor
0.4.8
Changes
- chore: cortex.llamacpp to v0.1.8 @vansangpfiev (#598)
- chore: remove inference stream @namchuai (#596)
- chore: clean up chat stream @namchuai (#593)
- feat: add model settings and prompt template from hf @namchuai (#588)
- chore: cortex.llamacpp v0.1.6 @vansangpfiev (#587)
- chore: cortex llama.cpp to version 0.1.5 @vansangpfiev (#586)
🧰 Maintenance
Contributor
@hiento09, @namchuai and @vansangpfiev
What's Changed
- chore: cortex.llamacpp v0.1.6 by @vansangpfiev in https://github.com/janhq/cortex/pull/587
- feat: add model settings and prompt template from hf by @namchuai in https://github.com/janhq/cortex/pull/588
- chore: clean up chat stream by @namchuai in https://github.com/janhq/cortex/pull/593
- chore: remove inference stream by @namchuai in https://github.com/janhq/cortex/pull/596
- replace deprecated ci step by @hiento09 in https://github.com/janhq/cortex/pull/597
- chore: cortex.llamacpp to v0.1.8 by @vansangpfiev in https://github.com/janhq/cortex/pull/598
Full Changelog: https://github.com/janhq/cortex/compare/v0.4.7...v0.4.8
0.4.7
What's Changed
- chore: cortex llama.cpp to version 0.1.5 by @vansangpfiev in https://github.com/janhq/cortex/pull/586
Full Changelog: https://github.com/janhq/cortex/compare/v0.4.6...v0.4.7
0.4.6
What's Changed
- chore: fix local path by @namchuai in https://github.com/janhq/cortex/pull/584
- chore: remove unused ignore by @namchuai in https://github.com/janhq/cortex/pull/585
- fix: change to abs path for engine loading by @vansangpfiev in https://github.com/janhq/cortex/pull/560
Full Changelog: https://github.com/janhq/cortex/compare/v0.4.5...v0.4.6
0.4.4
v0.4.4 feat: cortex onboarding (#565)
0.4.3
Fix package error on windows (#563) Co-authored-by: Hien To <[email protected]>
0.4.2
What's Changed
- feat: add cortex-js by @namchuai in https://github.com/janhq/cortex/pull/530
- fix: cli commands by @louis-jan in https://github.com/janhq/cortex/pull/556
- chore: clean up node-fetch by @namchuai in https://github.com/janhq/cortex/pull/557
- feat: change unload model and model status to POST by @vansangpfiev in https://github.com/janhq/cortex/pull/558
Full Changelog: https://github.com/janhq/cortex/compare/v0.4.1...v0.4.2
0.4.1
v0.4.1 feat: cortex-cpp rename components (#545)
0.3.22
Changes
- chore: version pump @tikikun (#512)
- feat: e2e embedding endpoint scripts @vansangpfiev (#511)
- fix: reject completion request for embedding model @vansangpfiev (#510)
- fix: embedding fixup for nomic-embed-text model @vansangpfiev (#504)
- fix: race condition between stream and non-stream inference @vansangpfiev (#507)
- hotfix: will always be cleaning cache @tikikun (#509)
- Revert "fix: make embedding work again" @vansangpfiev (#502)
- fix: responses from /chat/completions endpoint contain a leading space in the content @vansangpfiev (#488)