0.5.0-1

Changes

• feature: support local model pull @louis-jan (#944)
• chore: handle failed download @marknguyen1302 (#943)
• chore: specify engine version to pull @louis-jan (#942)
• bump cortex llamacpp for lla‌ma 3.1 @Van-QA (#941)

Contributor

@Van-QA, @louis-jan and @marknguyen1302

0.5.0

Changes

• fix: should not return failed code on model already loaded by @louis-jan in https://github.com/janhq/cortex/pull/913
• refactor: cortex cli as client - communicate with API server via cortexjs by @louis-jan in https://github.com/janhq/cortex/pull/906
• chore: unsupported platform engine status by @louis-jan in https://github.com/janhq/cortex/pull/920
• chore: update default api server config by @louis-jan in https://github.com/janhq/cortex/pull/921
• fix: config remote engine by @marknguyen1302 in https://github.com/janhq/cortex/pull/922
• feat: add cortex-cpp version to log by @vansangpfiev in https://github.com/janhq/cortex/pull/912
• chore: group system apis by @marknguyen1302 in https://github.com/janhq/cortex/pull/924
• fix: transform anthropic response by @marknguyen1302 in https://github.com/janhq/cortex/pull/925
• chore: enhance error output by @louis-jan in https://github.com/janhq/cortex/pull/923
• Change from github hotsted to macos selfhosted by @hiento09 in https://github.com/janhq/cortex/pull/926
• chore: attempt to release running services on exit by @louis-jan in https://github.com/janhq/cortex/pull/927
• Update the api desc by @irfanpena in https://github.com/janhq/cortex/pull/933
• Fix winget PR issue by @hiento09 in https://github.com/janhq/cortex/pull/934
• fix: handle multi download model, uninstall script by @marknguyen1302 in https://github.com/janhq/cortex/pull/932
• Add exe to release for winget by @hiento09 in https://github.com/janhq/cortex/pull/935
• chore: inference chat preset support by @louis-jan in https://github.com/janhq/cortex/pull/931
• chore: add log downloading model by @marknguyen1302 in https://github.com/janhq/cortex/pull/936
• chore: fixed an issue where cortex chat reload the running models by @louis-jan in https://github.com/janhq/cortex/pull/937
• fix: correct progress multi download by @marknguyen1302 in https://github.com/janhq/cortex/pull/938
• chore: add model version output by @louis-jan in https://github.com/janhq/cortex/pull/939
• chore: correct output logs by @louis-jan in https://github.com/janhq/cortex/pull/940

Full Changelog: https://github.com/janhq/cortex/compare/v0.4.36...v0.5.0

0.4.37-7

Changes

• Fix winget PR issue @hiento09 (#934)
• Update the api desc @irfanpena (#933)
• chore: attempt to release running services on exit @louis-jan (#927)
• Change from github hotsted to macos selfhosted @hiento09 (#926)
• chore: enhance error output @louis-jan (#923)
• fix: transform anthropic response @marknguyen1302 (#925)
• chore: group system apis @marknguyen1302 (#924)
• feat: add cortex-cpp version to log @vansangpfiev (#912)
• fix: config remote engine @marknguyen1302 (#922)
• chore: update default api server config @louis-jan (#921)
• chore: unsupported platform engine status @louis-jan (#920)
• refactor: cortex cli as client - communicate with API server via cortexjs @louis-jan (#906)
• fix: should not return failed code on model already loaded @louis-jan (#913)
• fix: add engine in unload model request @marknguyen1302 (#916)
• Correct path of file source.changes @hiento09 (#915)
• Feat cortex publish launchpad @hiento09 (#910)
• fix: wrong condition to add engine param @marknguyen1302 (#914)
• fix: wrong remote engine payload @marknguyen1302 (#911)
• feat: add cortex version option @marknguyen1302 (#904)
• fix: electron build @louis-jan (#908)
• fix: can not chat with remote model @marknguyen1302 (#907)
• feat: update models command @marknguyen1302 (#905)
• remove --options max-old-space-size=30720,tls-min-v1.0,expose-gc pkg @hiento09 (#902)
• refactor: deprecate cortex configs @louis-jan (#901)
• feat: Create llama3.yml presets for llama3 family @Van-QA (#862)
• fix: allow duplicated options @marknguyen1302 (#903)
• chore: auto load model on /chat/completions request @louis-jan (#900)
• Remove serve command @marknguyen1302 (#896)
• fix: transfrom wrong format in json response from Anthropic @marknguyen1302 (#897)
• fix: download model wrong event emission @louis-jan (#895)
• chore: lock cortex-cpp dependency version @louis-jan (#894)
• feat: support running multiple engines at the same time @vansangpfiev (#891)
• fix: throttle leading and trailing event @louis-jan (#892)
• fix: wrong engine list @marknguyen1302 (#890)
• feat: add engine init endpoint @louis-jan (#888)
• feat: change init engine syntax @marknguyen1302 (#889)
• fix: wrong telemetry folder, correct swagger @marknguyen1302 (#887)
• Chore test openai api @hiento09 (#886)
• fix: add custom model id @marknguyen1302 (#882)
• fix: remote engines should accept normalized headers only @louis-jan (#885)
• add better example for the request body @irfanpena (#883)
• chore: add an entry to allow JS import @louis-jan (#878)
• fix: cortex-cpp node prebuild dependencies @louis-jan (#879)
• Update the README @irfanpena (#875)
• fix: chat completion endpoint is hang @louis-jan (#877)
• Fix openai collection test @hiento09 (#874)
• fix: create sqlite tables @marknguyen1302 (#873)
• chore: deprecate cortex init @louis-jan (#868)
• fix: use zlib static @vansangpfiev (#872)
• fix: correct consumed resource table @marknguyen1302 (#869)
• feat: add resources consumed in ps command @marknguyen1302 (#866)
• fix: clean resources should not remove engine file @louis-jan (#867)
• feat: support anthropic engine @marknguyen1302 (#864)
• fix: throw error when not found file in download model @marknguyen1302 (#865)
• feat: cortex-cpp node addon @louis-jan (#852)
• Remove the tap and untap brew installation command @irfanpena (#859)
• fix: correct telemetry timestamp @marknguyen1302 (#857)
• feat: support pull model by specific fileName @marknguyen1302 (#858)
• feat: replace typeorm by sequelize @marknguyen1302 (#856)
• cortex cpp switch to macos-latest runner @hiento09 (#854)

Contributor

@Van-QA, @hiento09, @hientominh, @irfanpena, @louis-jan, @marknguyen1302 and @vansangpfiev

0.4.37-2

Changes

• feat: add cortex-cpp version to log @vansangpfiev (#912)
• fix: config remote engine @marknguyen1302 (#922)
• chore: update default api server config @louis-jan (#921)
• chore: unsupported platform engine status @louis-jan (#920)
• refactor: cortex cli as client - communicate with API server via cortexjs @louis-jan (#906)
• fix: should not return failed code on model already loaded @louis-jan (#913)
• fix: add engine in unload model request @marknguyen1302 (#916)
• Correct path of file source.changes @hiento09 (#915)
• Feat cortex publish launchpad @hiento09 (#910)
• fix: wrong condition to add engine param @marknguyen1302 (#914)
• fix: wrong remote engine payload @marknguyen1302 (#911)
• feat: add cortex version option @marknguyen1302 (#904)
• fix: electron build @louis-jan (#908)
• fix: can not chat with remote model @marknguyen1302 (#907)
• feat: update models command @marknguyen1302 (#905)
• remove --options max-old-space-size=30720,tls-min-v1.0,expose-gc pkg @hiento09 (#902)
• refactor: deprecate cortex configs @louis-jan (#901)
• feat: Create llama3.yml presets for llama3 family @Van-QA (#862)
• fix: allow duplicated options @marknguyen1302 (#903)
• chore: auto load model on /chat/completions request @louis-jan (#900)
• Remove serve command @marknguyen1302 (#896)
• fix: transfrom wrong format in json response from Anthropic @marknguyen1302 (#897)
• fix: download model wrong event emission @louis-jan (#895)
• chore: lock cortex-cpp dependency version @louis-jan (#894)
• feat: support running multiple engines at the same time @vansangpfiev (#891)
• fix: throttle leading and trailing event @louis-jan (#892)
• fix: wrong engine list @marknguyen1302 (#890)
• feat: add engine init endpoint @louis-jan (#888)
• feat: change init engine syntax @marknguyen1302 (#889)
• fix: wrong telemetry folder, correct swagger @marknguyen1302 (#887)
• Chore test openai api @hiento09 (#886)
• fix: add custom model id @marknguyen1302 (#882)
• fix: remote engines should accept normalized headers only @louis-jan (#885)
• add better example for the request body @irfanpena (#883)
• chore: add an entry to allow JS import @louis-jan (#878)
• fix: cortex-cpp node prebuild dependencies @louis-jan (#879)
• Update the README @irfanpena (#875)
• fix: chat completion endpoint is hang @louis-jan (#877)
• Fix openai collection test @hiento09 (#874)
• fix: create sqlite tables @marknguyen1302 (#873)
• chore: deprecate cortex init @louis-jan (#868)
• fix: use zlib static @vansangpfiev (#872)
• fix: correct consumed resource table @marknguyen1302 (#869)
• feat: add resources consumed in ps command @marknguyen1302 (#866)
• fix: clean resources should not remove engine file @louis-jan (#867)
• feat: support anthropic engine @marknguyen1302 (#864)
• fix: throw error when not found file in download model @marknguyen1302 (#865)
• feat: cortex-cpp node addon @louis-jan (#852)
• Remove the tap and untap brew installation command @irfanpena (#859)
• fix: correct telemetry timestamp @marknguyen1302 (#857)
• feat: support pull model by specific fileName @marknguyen1302 (#858)
• feat: replace typeorm by sequelize @marknguyen1302 (#856)
• cortex cpp switch to macos-latest runner @hiento09 (#854)

Contributor

@Van-QA, @hiento09, @hientominh, @irfanpena, @louis-jan, @marknguyen1302 and @vansangpfiev

0.4.37

Changes

• fix: config remote engine @marknguyen1302 (#922)
• chore: update default api server config @louis-jan (#921)
• chore: unsupported platform engine status @louis-jan (#920)
• refactor: cortex cli as client - communicate with API server via cortexjs @louis-jan (#906)
• fix: should not return failed code on model already loaded @louis-jan (#913)
• fix: add engine in unload model request @marknguyen1302 (#916)
• Correct path of file source.changes @hiento09 (#915)
• Feat cortex publish launchpad @hiento09 (#910)
• fix: wrong condition to add engine param @marknguyen1302 (#914)
• fix: wrong remote engine payload @marknguyen1302 (#911)
• feat: add cortex version option @marknguyen1302 (#904)
• fix: electron build @louis-jan (#908)
• fix: can not chat with remote model @marknguyen1302 (#907)
• feat: update models command @marknguyen1302 (#905)
• remove --options max-old-space-size=30720,tls-min-v1.0,expose-gc pkg @hiento09 (#902)
• refactor: deprecate cortex configs @louis-jan (#901)
• feat: Create llama3.yml presets for llama3 family @Van-QA (#862)
• fix: allow duplicated options @marknguyen1302 (#903)
• chore: auto load model on /chat/completions request @louis-jan (#900)
• Remove serve command @marknguyen1302 (#896)
• fix: transfrom wrong format in json response from Anthropic @marknguyen1302 (#897)
• fix: download model wrong event emission @louis-jan (#895)
• chore: lock cortex-cpp dependency version @louis-jan (#894)
• feat: support running multiple engines at the same time @vansangpfiev (#891)
• fix: throttle leading and trailing event @louis-jan (#892)
• fix: wrong engine list @marknguyen1302 (#890)
• feat: add engine init endpoint @louis-jan (#888)
• feat: change init engine syntax @marknguyen1302 (#889)
• fix: wrong telemetry folder, correct swagger @marknguyen1302 (#887)
• Chore test openai api @hiento09 (#886)
• fix: add custom model id @marknguyen1302 (#882)
• fix: remote engines should accept normalized headers only @louis-jan (#885)
• add better example for the request body @irfanpena (#883)
• chore: add an entry to allow JS import @louis-jan (#878)
• fix: cortex-cpp node prebuild dependencies @louis-jan (#879)
• Update the README @irfanpena (#875)
• fix: chat completion endpoint is hang @louis-jan (#877)
• Fix openai collection test @hiento09 (#874)
• fix: create sqlite tables @marknguyen1302 (#873)
• chore: deprecate cortex init @louis-jan (#868)
• fix: use zlib static @vansangpfiev (#872)
• fix: correct consumed resource table @marknguyen1302 (#869)
• feat: add resources consumed in ps command @marknguyen1302 (#866)
• fix: clean resources should not remove engine file @louis-jan (#867)
• feat: support anthropic engine @marknguyen1302 (#864)
• fix: throw error when not found file in download model @marknguyen1302 (#865)
• feat: cortex-cpp node addon @louis-jan (#852)
• Remove the tap and untap brew installation command @irfanpena (#859)
• fix: correct telemetry timestamp @marknguyen1302 (#857)
• feat: support pull model by specific fileName @marknguyen1302 (#858)
• feat: replace typeorm by sequelize @marknguyen1302 (#856)
• cortex cpp switch to macos-latest runner @hiento09 (#854)

Contributor

@Van-QA, @hiento09, @irfanpena, @louis-jan, @marknguyen1302 and @vansangpfiev

0.4.36

v0.4.36

fix: add engine to unload model request

0.4.35

v0.4.35

fix: wrong condition to add engine param

0.4.32-6

Changes

• feat: add cortex version option @marknguyen1302 (#904)
• fix: electron build @louis-jan (#908)
• fix: can not chat with remote model @marknguyen1302 (#907)
• feat: update models command @marknguyen1302 (#905)
• remove --options max-old-space-size=30720,tls-min-v1.0,expose-gc pkg @hiento09 (#902)
• refactor: deprecate cortex configs @louis-jan (#901)
• feat: Create llama3.yml presets for llama3 family @Van-QA (#862)
• fix: allow duplicated options @marknguyen1302 (#903)
• chore: auto load model on /chat/completions request @louis-jan (#900)
• Remove serve command @marknguyen1302 (#896)
• fix: transfrom wrong format in json response from Anthropic @marknguyen1302 (#897)
• fix: download model wrong event emission @louis-jan (#895)
• chore: lock cortex-cpp dependency version @louis-jan (#894)
• feat: support running multiple engines at the same time @vansangpfiev (#891)
• fix: throttle leading and trailing event @louis-jan (#892)
• fix: wrong engine list @marknguyen1302 (#890)
• feat: add engine init endpoint @louis-jan (#888)
• feat: change init engine syntax @marknguyen1302 (#889)
• fix: wrong telemetry folder, correct swagger @marknguyen1302 (#887)
• Chore test openai api @hiento09 (#886)
• fix: add custom model id @marknguyen1302 (#882)
• fix: remote engines should accept normalized headers only @louis-jan (#885)
• add better example for the request body @irfanpena (#883)
• chore: add an entry to allow JS import @louis-jan (#878)
• fix: cortex-cpp node prebuild dependencies @louis-jan (#879)
• Update the README @irfanpena (#875)
• fix: chat completion endpoint is hang @louis-jan (#877)
• Fix openai collection test @hiento09 (#874)
• fix: create sqlite tables @marknguyen1302 (#873)
• chore: deprecate cortex init @louis-jan (#868)
• fix: use zlib static @vansangpfiev (#872)
• fix: correct consumed resource table @marknguyen1302 (#869)
• feat: add resources consumed in ps command @marknguyen1302 (#866)
• fix: clean resources should not remove engine file @louis-jan (#867)
• feat: support anthropic engine @marknguyen1302 (#864)
• fix: throw error when not found file in download model @marknguyen1302 (#865)
• feat: cortex-cpp node addon @louis-jan (#852)
• Remove the tap and untap brew installation command @irfanpena (#859)
• fix: correct telemetry timestamp @marknguyen1302 (#857)
• feat: support pull model by specific fileName @marknguyen1302 (#858)
• feat: replace typeorm by sequelize @marknguyen1302 (#856)
• cortex cpp switch to macos-latest runner @hiento09 (#854)

Contributor

@Van-QA, @hiento09, @hientominh, @irfanpena, @louis-jan, @marknguyen1302 and @vansangpfiev

0.4.34

NOTE: NPM dependency - do not remove yet

0.4.33

Changes

• Remove serve command @marknguyen1302 (#896)
• fix: transfrom wrong format in json response from Anthropic @marknguyen1302 (#897)
• fix: download model wrong event emission @louis-jan (#895)
• chore: lock cortex-cpp dependency version @louis-jan (#894)
• feat: support running multiple engines at the same time @vansangpfiev (#891)
• fix: throttle leading and trailing event @louis-jan (#892)
• fix: wrong engine list @marknguyen1302 (#890)
• feat: add engine init endpoint @louis-jan (#888)
• feat: change init engine syntax @marknguyen1302 (#889)
• fix: wrong telemetry folder, correct swagger @marknguyen1302 (#887)
• Chore test openai api @hiento09 (#886)
• fix: add custom model id @marknguyen1302 (#882)
• fix: remote engines should accept normalized headers only @louis-jan (#885)
• add better example for the request body @irfanpena (#883)
• chore: add an entry to allow JS import @louis-jan (#878)
• fix: cortex-cpp node prebuild dependencies @louis-jan (#879)
• Update the README @irfanpena (#875)
• fix: chat completion endpoint is hang @louis-jan (#877)
• Fix openai collection test @hiento09 (#874)
• fix: create sqlite tables @marknguyen1302 (#873)
• chore: deprecate cortex init @louis-jan (#868)
• fix: use zlib static @vansangpfiev (#872)
• fix: correct consumed resource table @marknguyen1302 (#869)
• feat: add resources consumed in ps command @marknguyen1302 (#866)
• fix: clean resources should not remove engine file @louis-jan (#867)
• feat: support anthropic engine @marknguyen1302 (#864)
• fix: throw error when not found file in download model @marknguyen1302 (#865)
• feat: cortex-cpp node addon @louis-jan (#852)
• Remove the tap and untap brew installation command @irfanpena (#859)
• fix: correct telemetry timestamp @marknguyen1302 (#857)
• feat: support pull model by specific fileName @marknguyen1302 (#858)
• feat: replace typeorm by sequelize @marknguyen1302 (#856)
• cortex cpp switch to macos-latest runner @hiento09 (#854)

Contributor

@hiento09, @hientominh, @irfanpena, @louis-jan, @marknguyen1302 and @vansangpfiev