1.0.0

Changes

• fix: pull api @vansangpfiev (#1445)
• chore: change update to patch for models update @vansangpfiev (#1444)
• chore: add /v1/models/ APIs @vansangpfiev (#1443)
• chore: add /v1/engines @vansangpfiev (#1442)
• fix: chat completion parameters @vansangpfiev (#1440)
• fix: handle EOF @vansangpfiev (#1434)
• docs: correct download url @hiento09 (#1433)
• feat: uplift pull and run cmd @namchuai (#1430)
• docs: Add download url @hiento09 (#1431)
• fix: skip unexpect deleted model when list model @nguyenhoangthuan99 (#1420)
• fix: minor log issue and engine name issue @vansangpfiev (#1427)
• Chore: Improve User Experience in Cortex Uninstall Scripts for Linux and macOS @hiento09 (#1429)
• chore: rename engines @vansangpfiev (#1406)
• fix: no sudo for root use @vansangpfiev (#1421)
• feat: macos universal installer and binary @hiento09 (#1402)
• fix: avoid running multiple subcommands @vansangpfiev (#1417)
• Chore/utils unitests @nguyenhoangthuan99 (#1400)
• chore: add read remote yaml function @namchuai (#1411)
• Fix/skip re download model yml @nguyenhoangthuan99 (#1409)
• fix: use relative path for model information @vansangpfiev (#1399)
• fix: Installer progress bar should not 100% while downloading dependencies @hiento09 (#1385)
• Chore/change swagger route @nguyenhoangthuan99 (#1397)
• Chore/change swagger route @nguyenhoangthuan99 (#1392)
• Chore/fix float number yaml file @nguyenhoangthuan99 (#1383)
• feat: e2e tests for APIs @vansangpfiev (#1358)
• feat: e2e test ci @vansangpfiev (#1238)
• chore: change default server port @vansangpfiev (#1373)
• fix: nightly version discord message hard to read on PC @hiento09 (#1377)
• Feat/add swagger @nguyenhoangthuan99 (#1366)
• fix: validate url before pull @namchuai (#1382)
• fix: pull issue @vansangpfiev (#1381)
• fix: run cmd @vansangpfiev (#1380)
• fix: correct model_id in chat @vansangpfiev (#1379)
• Revert "fix: Windows installer final screen stalls much longer" @hiento09 (#1378)
• fix: Windows installer final screen stalls much longer @hiento09 (#1374)
• Fix/max context length @nguyenhoangthuan99 (#1370)
• fix: ignore SIGINT for server @vansangpfiev (#1371)
• Fix/download model logs @nguyenhoangthuan99 (#1361)
• fix: make cortex models stop works again @vansangpfiev (#1364)
• chore: some format for cortex ps @namchuai (#1363)
• Feat/config log location for engines @nguyenhoangthuan99 (#1356)
• fix: UI/UX improvement for cortex CLI @vansangpfiev (#1351)
• feat: cortex ps @namchuai (#1345)
• fix: work around for connection hang when network down @vansangpfiev (#1352)
• fix: create config file if does not exist before getting data path @vansangpfiev (#1349)
• feat: sqlite database implementation @vansangpfiev (#1336)
• fix: re-assign model_id to DownloadModel result @vansangpfiev (#1343)
• docs: remove outdated links @0xSage (#1319)
• docs: Update command cortex -> cortex start @irfanpena (#1339)
• fix/mistral-nemo-chat-template @nguyenhoangthuan99 (#1337)
• Add support download model for author:model @namchuai (#1333)
• Macos add local installer @hiento09 (#1335)
• Linux add local installer @hiento09 (#1332)
• fix: save latest release info @vansangpfiev (#1334)
• fix: cortex chat is a non-interactive request @vansangpfiev (#1331)
• Windows add local installer @hiento09 (#1324)
• chore: replace result api instead of throwing exception @namchuai (#1254)
• Feat/new model folder @nguyenhoangthuan99 (#1327)
• fix: require sudo for cortex update @vansangpfiev (#1318)
• fix: align github syntax for cuda @vansangpfiev (#1316)
• fix: resume download failed @namchuai (#1314)
• fix: gcc9 issue for std::variant @vansangpfiev (#1310)
• feat: install local engine @vansangpfiev (#1292)
• Add chat template renderer from llama.cpp @nguyenhoangthuan99 (#1289)
• fix: remove cortex tmp after cortex update @vansangpfiev (#1295)
• Fix ci nightly build @hiento09 (#1296)
• Fix permission macos installer @hiento09 (#1294)
• fix: cli helper @vansangpfiev (#1291)
• fix: correct minimum required cuda version for llamacpp @vansangpfiev (#1286)
• Fix: add try catch when parsing streaming result from server @nguyenhoangthuan99 (#1280)
• Chore use aws s3 sync @hiento09 (#1290)
• docs: Update README.md @0xSage (#1284)
• feat: add download resume @namchuai (#1279)
• Feat/model get @nguyenhoangthuan99 (#1271)
• fix: should check model status before start it @vansangpfiev (#1277)
• Feat/model import cmd @nguyenhoangthuan99 (#1248)
• fix: flush chat content to for each response data @vansangpfiev (#1275)
• fix: set timeout for checking new update @vansangpfiev (#1276)
• model set alias command @nguyenhoangthuan99 (#1256)
• fix: correct permissions owner and group @vansangpfiev (#1267)
• fix: e2e failed test when download model with selection @namchuai (#1260)
• Fix Updater nightly error and Macos uninstaller stop cortex before uninstall @hiento09 (#1258)
• Docs: Update the Readme per feedback @irfanpena (#1236)
• feat: add support HF model handle and quant selection @namchuai (#1239)
• Quality Gate mac intel switch to selfhosted agent @hiento09 (#1250)
• Feat/gguf yaml parser @nguyenhoangthuan99 (#1246)
• feat: categorize commands @vansangpfiev (#1245)
• feat: redirect llamacpp log @nguyenhoangthuan99 (#1194)
• Init model.list utils @nguyenhoangthuan99 (#1240)
• chore: minor copy nits @0xSage (#1213)
• feat: cortex start command @vansangpfiev (#1235)
• feat: download pre-release engine @vansangpfiev (#1237)
• feat: download model with direct url @namchuai (#1227)
• fix: print all logs to terminal with --verbose @vansangpfiev (#1228)
• feat: cortex models delete command @vansangpfiev (#1189)
• feat: beta updater @vansangpfiev (#1197)
• adding libcurl to support pause/resume download @namchuai (#1179)
• Fix #1216 - remove create shortcut item task and move download llamacpp engine to install dialog @hiento09 (#1219)
• Fix issue postinstaller not run in macos @hiento09 (#1212)
• feat: add unit tests CI @vansangpfiev (#1214)
• fix: spawn process linux @vansangpfiev (#1210)
• Correct command post install download cortex.llamacpp @hiento09 (#1211)
• Correct package file name @hiento09 (#1209)
• fix: cortex update unit test @vansangpfiev (#1207)
• Update README.md @imtuyethan (#1203)
• Fix wrong nightly download URL on Discord. @hiento09 (#1206)
• fix: nightly updater @vansangpfiev (#1202)
• Fix: create log folder before logging @nguyenhoangthuan99 (#1200)
• Add noti discord for nightly channel @hiento09 (#1199)
• Simplify Cortex README.md @irfanpena (#1098)
• feat: add pytest for e2e testing @namchuai (#1188)
• fix: add dll search path @vansangpfiev (#982)
• Feat Installer and CICD nightly, beta, stable for cortexcpp @hiento09 (#1122)
• fix: empty engine name while install @namchuai (#1193)
• chore: update engine list @namchuai (#1183)
• feat: nightly updater @vansangpfiev (#1175)
• feat-logger-update @nguyenhoangthuan99 (#1173)
• chore: standardize issue templates @0xSage (#1177)
• chore: add some unit tests @namchuai (#1158)
• fix: update engine install/uninstall CLI commands @namchuai (#1171)
• chore: update .cortexrc fields @namchuai (#1172)
• chore: add variant support @namchuai (#1138)
• fix: correct path to work with data folder structure @vansangpfiev (#1132)
• feat: cortex update command @vansangpfiev (#1095)
• feat: add engine uninstall command @namchuai (#1094)
• fix: CI after renaming repository @vansangpfiev (#1096)
• feat: cli output log @vansangpfiev (#1049)
• chore: rename cortex-js folder to platform @marknguyen1302 (#1033)
• Update the cortex-cpp Readme @irfanpena (#1028)
• fix: dynamically get cuda toolkit version @namchuai (#1053)
• feat: support custom log path @marknguyen1302 (#1024)
• add engine list cmd @nguyenhoangthuan99 (#1050)
• fix: use model_id.yaml for model info @vansangpfiev (#1051)
• feat: cortex engine @vansangpfiev (#1027)
• feat: download cuda toolkit @namchuai (#1044)
• fix: handle stop server @vansangpfiev (#1048)
• feat: run command @vansangpfiev (#1045)
• Feat background process server @nguyenhoangthuan99 (#1043)
• feat: models get command @nguyenhoangthuan99 (#1035)
• fix: guarantee lifetime for captured variables @vansangpfiev (#1042)
• feat: add engine install cli @namchuai (#1034)
• feat: chat command @vansangpfiev (#1032)
• feat: support to start model by file path @marknguyen1302 (#1026)
• feat: expose server instance @marknguyen1302 (#1025)
• fix: engine init is broken @louis-jan (#1022)
• Resolve comment in brew PR @hiento09 (#1018)
• feat: support to change config path @marknguyen1302 (#1009)
• Feature dockerfile for cortex @hiento09 (#1014)
• chore: fallback noavx binary @louis-jan (#1013)
• fix: add used vram into system event body @louis-jan (#1012)
• chore: system resource events should include gpu system information @louis-jan (#1011)
• fix: remove uploads_folder_path @vansangpfiev (#996)
• feat: unload engine when init engine @marknguyen1302 (#1003)
• fix: binary file lookup @louis-jan (#1001)
• feat: add pagination for thread list api @marknguyen1302 (#1000)
• fix: set namespace for js module @louis-jan (#999)
• fix: increase CI timeout @louis-jan (#998)
• chore: support more configurations via direct js import @louis-jan (#997)
• Fix brew build from source error @hiento09 (#995)
• fix: hide gpu check windows @louis-jan (#993)
• Chore bump cortex-cpp to 0.5.0-34 @hiento09 (#992)
• Fix cortex-cpp rebuild @hiento09 (#994)
• fix: fix checksum undefined @marknguyen1302 (#991)
• feat: support unload engine @vansangpfiev (#989)
• cortex js allow tag x.y.z-t @hiento09 (#990)
• add build-deps for cortex-cpp binding @hiento09 (#988)
• fix: env does not work after bundled in an electron app @louis-jan (#987)
• feat: download model checksum @marknguyen1302 (#986)
• Windows uninstaller should stop cortex and remove cortex home folder for all users @hiento09 (#984)
• chore: name cortex processes @louis-jan (#983)
• fix: correct swagger port @marknguyen1302 (#980)
• fix: missing utils reference @louis-jan (#978)
• fix: force change localhost @marknguyen1302 (#977)
• chore: bump cpp version to 0.5.0-27 @marknguyen1302 (#976)
• chore: return error on pulling an existing model @louis-jan (#975)
• feat: add config cpp port @marknguyen1302 (#973)
• chore: clean logs periodically @louis-jan (#972)
• Fix codesign macos for application and installer @hiento09 (#974)
• fix: persists engine version on init @louis-jan (#969)
• feat: support multi process in cortex @marknguyen1302 (#965)
• Update the Base URL for the API reference to reflect the new URL @irfanpena (#971)
• fix: disable devtool @marknguyen1302 (#967)
• Fix codesign windows @hiento09 (#964)
• fix: create message request with string content instead of array @louis-jan (#963)
• fix: cortex engines init api with empty body should init default options @louis-jan (#962)
• fix: change default host cortex @marknguyen1302 (#961)
• feat: watch models and engines update for proper data retrieval @louis-jan (#960)
• fix: fix issue when re-download aborted model @marknguyen1302 (#959)
• Add launchpad uninstaller prerm and postrm @hiento09 (#957)
• feat: support martian nvidia engine @marknguyen1302 (#956)
• chore: delete local file when abort download @marknguyen1302 (#954)
• fix: terminate system should kill cortex process @louis-jan (#955)
• fix: start and run models are not outputting last error logs @louis-jan (#951)
• fix: remove hardcode stream @marknguyen1302 (#952)
• chore: persist context length and ngl from gguf file @louis-jan (#947)
• chore: show error from remote engine, lint @marknguyen1302 (#949)
• Fix openai api pipeline @hiento09 (#948)
• chore: destroy dangling processes on uninstall @louis-jan (#945)
• feat: support openrouter, cohere engine @marknguyen1302 (#946)
• 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

@0xSage, @Van-QA, @dan-homebrew, @hiento09, @hientominh, @imtuyethan, @irfanpena, @louis-jan, @marknguyen1302, @namchuai, @nguyenhoangthuan99 and @vansangpfiev