Commit Graph

  • 54691044d4
    Add missing --jinja flag Akarshan 2025-06-23 16:48:43 +05:30
  • ae58c427a5
    fix: tool call params Louis 2025-06-23 18:16:17 +07:00
  • 6b86baaa2f
    Add tool choice type Akarshan 2025-06-23 16:45:00 +05:30
  • 6d5251d1c6
    Fixup tool type definition Akarshan 2025-06-23 16:39:52 +05:30
  • 7f25311d26
    Add tool type to chat completion requests Akarshan 2025-06-23 16:32:26 +05:30
  • 8bd4a3389f
    refactor: frontend uses new engine extension Louis 2025-06-23 13:06:29 +07:00
  • ad06b2a903
    Move llama-server cleanup code to a separate file Akarshan 2025-06-23 12:15:04 +05:30
  • 7de694c0cd
    add missing import during rebase Akarshan 2025-06-23 11:35:01 +05:30
  • 62ba503b86
    chore: cleanup llama-server processes upon app exit Akarshan 2025-06-23 11:11:51 +05:30
  • 01d49a4b28
    fix: Update server process handling for Windows and Unix systems Akarshan 2025-06-23 08:58:05 +05:30
  • 7dbc2c3af2
    download lib at build time Thien Tran 2025-06-16 15:41:27 +08:00
  • 48d1164858
    feat: add embedding support to llamacpp extension Akarshan 2025-06-16 12:26:28 +05:30
  • 2eeabf8ae6
    fix: ensure server process is properly terminated and reaped Akarshan 2025-06-11 19:05:31 +05:30
  • f463008362
    feat: add model load wait to ensure model is ready before use Akarshan 2025-06-11 12:31:25 +05:30
  • 9d4e7cb2b8
    fix: correct model_id to model_id in console error message Akarshan 2025-06-11 11:32:55 +05:30
  • d60257ebbd
    Revert: extension/yarn.lock Akarshan 2025-06-10 16:07:39 +05:30
  • dbcce86bb8
    refactor: rename interfaces and add getLoadedModels Akarshan 2025-06-08 13:24:12 +05:30
  • 4ffc504150
    style: Rename camelCase to snake_case in llamacpp extension code Akarshan 2025-06-06 10:14:12 +05:30
  • c2b606a3fc
    feat: enhance chatCompletionRequest with advanced sampling parameters Akarshan 2025-06-05 12:58:37 +05:30
  • 6c769c5db9
    feat: refactor llama server process storage to use HashMap Akarshan 2025-06-04 19:08:18 +05:30
  • 8bf4a5eb7d
    remove migration Thien Tran 2025-06-04 11:02:41 +08:00
  • 525cc93d4a
    fix system cudart detection on linux Thien Tran 2025-06-04 08:59:24 +08:00
  • ae349159ce
    remove yarn install:cortex Thien Tran 2025-06-04 08:31:53 +08:00
  • 95944fa081
    add Jan's library path to path Thien Tran 2025-06-03 22:01:10 +08:00
  • 65d6f34878
    check for system libraries Thien Tran 2025-06-03 21:41:27 +08:00
  • 1eb49350e9
    add is_library_available command Thien Tran 2025-06-03 15:15:57 +08:00
  • 622f4118c0
    add placeholder for windows and linux arm Thien Tran 2025-06-03 12:23:09 +08:00
  • f7bcf43334
    update folde structure. small refactoring Thien Tran 2025-06-02 11:58:29 +08:00
  • 3b72d80979
    fix wrong key for backend Thien Tran 2025-06-02 10:41:18 +08:00
  • 331c0e04a5
    fix: use modelId instead of sessionId for unloading Akarshan Biswas 2025-06-02 06:42:29 +05:30
  • e3d6cbd80f
    feat: add port parameter to generateApiKey for secure model-specific API keys Akarshan Biswas 2025-06-01 21:15:22 +05:30
  • 4dfdcd68d5
    refactor: rename session identifiers to pid and modelId Akarshan Biswas 2025-05-30 22:50:50 +05:30
  • f9d3935269
    feat: allow specifying port via command line argument Akarshan Biswas 2025-05-30 13:41:18 +05:30
  • 5d61062b0e
    feat: enhance argument parsing and add API key generation Akarshan Biswas 2025-05-30 13:39:34 +05:30
  • 6679debf72
    mkdir before write yaml Thien Tran 2025-05-30 15:37:41 +08:00
  • 1ae7c0b59a
    update version/backend format. fix bugs around load() Thien Tran 2025-05-30 13:55:31 +08:00
  • fd9e034461
    feat: update AIEngine load method and backend path handling Akarshan Biswas 2025-05-30 10:25:58 +05:30
  • 9e24e28341
    add await to config Thien Tran 2025-05-30 12:57:58 +08:00
  • 070d8534c4
    add some string validation Thien Tran 2025-05-30 12:06:52 +08:00
  • 494a47aaa5
    fix download condition Thien Tran 2025-05-30 10:17:07 +08:00
  • f32ae402d5
    fix CUDA version URL Thien Tran 2025-05-30 10:01:28 +08:00
  • 27146eb5cc
    fix feature parsing Thien Tran 2025-05-30 10:00:22 +08:00
  • a75d13f42f
    fix version compare Thien Tran 2025-05-30 09:47:35 +08:00
  • 3490299f66
    refactor get supported features. check driver version for cu11 and cu12 Thien Tran 2025-05-30 09:32:56 +08:00
  • 267bbbf77b
    feat: add model and mmproj paths to ImportOptions Akarshan Biswas 2025-05-29 20:54:38 +05:30
  • 07d76dc871
    feat: Allow specifying mmproj path during model loading Akarshan Biswas 2025-05-29 19:53:02 +05:30
  • fbfaaf43c5
    download CUDA libs if needed Thien Tran 2025-05-29 17:32:09 +08:00
  • 40cd7e962a
    feat: download backend for llama.cpp extension (#5123) Thien Tran 2025-05-29 16:36:08 +08:00
  • da23673a44
    feat: Add API key generation for Llama.cpp Akarshan Biswas 2025-05-29 12:02:55 +05:30
  • d6edb1e944
    If checking for proper ctx_len settings after refactoring Akarshan Biswas 2025-05-29 08:41:07 +05:30
  • 39bb3f34d6
    patch failing calls to cortex Thien Tran 2025-05-28 16:21:08 +08:00
  • 31971e7821
    (WIP)randomly generate api-key hash each session Akarshan Biswas 2025-05-28 09:52:25 +05:30
  • 1dd762f0cf
    remove parseGGUFFileName function as it is not used Akarshan Biswas 2025-05-28 09:17:10 +05:30
  • 7481fae0df
    remove ununsed imports and remove n_ctx key from loadOptions Akarshan Biswas 2025-05-28 07:29:10 +05:30
  • 77d861f56f
    Fixup: change key to ctx_size to align with upstream and remove duplicate key Akarshan Biswas 2025-05-28 07:19:21 +05:30
  • d5c07acdb5
    feat: add LlamacppConfig for llama.cpp extension to improve settings (#5121) Thien Tran 2025-05-28 09:47:09 +08:00
  • 9bb4deeb78
    update model config (import and list) Thien Tran 2025-05-26 19:28:59 +08:00
  • 5803fcdb99
    add read_yaml. use buffered reader/writer Thien Tran 2025-05-26 19:03:10 +08:00
  • d01cbe44ae
    use PathBuf to check exists() Thien Tran 2025-05-26 18:52:37 +08:00
  • 77f6770333
    update fileStat() Thien Tran 2025-05-26 18:51:56 +08:00
  • 742e731e96
    Add --reasoning_budget option Akarshan Biswas 2025-05-26 16:20:42 +05:30
  • fe457a5368
    slight modelbasepath refactoring Akarshan Biswas 2025-05-26 12:06:56 +05:30
  • c5a0ee7f6e
    refactor unload and implement a destructor to clean up sessions Akarshan Biswas 2025-05-26 11:42:18 +05:30
  • cd36b423b6
    add basic model list Thien Tran 2025-05-26 13:11:37 +08:00
  • d523166b61
    implement delete Thien Tran 2025-05-26 09:34:46 +08:00
  • 587ed3c83c
    refactor OAI request payload type to support image and audio Akarshan Biswas 2025-05-23 20:42:26 +05:30
  • ded9ae733a
    feat: Model import (download + local import) for llama.cpp extension (#5087) Thien Tran 2025-05-23 22:39:23 +08:00
  • a7a2dcc8d8
    refactor load/unload again; move types to core and refactor AIEngine abstract class Akarshan Biswas 2025-05-20 19:33:26 +05:30
  • ee2cb9e625
    remove override from localOAIEngine and OAIEngine Akarshan Biswas 2025-05-20 13:04:06 +05:30
  • 0e9a8a27e5
    fixup from refactoring Akarshan Biswas 2025-05-20 12:48:08 +05:30
  • bbbf4779df
    refactor load/unload Akarshan Biswas 2025-05-20 12:39:18 +05:30
  • b4670b5526
    remove cortex engine dirs Akarshan Biswas 2025-05-19 20:23:13 +05:30
  • 47881db696
    remove cortex from tauri.conf.json Akarshan Biswas 2025-05-19 20:11:07 +05:30
  • 021f8ae80f
    Fixup: llama-server load Akarshan Biswas 2025-05-19 19:33:22 +05:30
  • ed6f86d4b1
    Change scripts to download only llama.cpp engine Akarshan Biswas 2025-05-19 09:40:27 +05:30
  • a8abc9f9aa
    Resolved conflicts by keeping HEAD changes Akarshan Biswas 2025-05-17 12:55:38 +05:30
  • 19274f7e69
    update settings Akarshan Biswas 2025-05-12 12:22:13 +05:30
  • 3f082372fd
    add llamacpp-extension. can list some models Thien Tran 2025-05-07 15:23:40 +07:00
  • 15f0b11c0d
    make it compile Thien Tran 2025-05-07 13:06:22 +07:00
  • 0551b0bfd2
    Fix import Akarshan Biswas 2025-05-07 09:29:37 +05:30
  • f5b5596306
    add thiserror to Cargo.toml Akarshan Biswas 2025-05-07 09:23:13 +05:30
  • 5c9e8dce76
    Add spaces before EOF Akarshan Biswas 2025-05-06 20:11:28 +05:30
  • 9016fbff68
    feat: inference-llamacpp-extension: backend implementation Akarshan Biswas 2025-05-06 20:04:25 +05:30
  • c288e75407
    Merge pull request #5671 from menloresearch/dev Louis 2025-07-02 11:33:01 +07:00
  • a3fd6fcd3c
    Merge pull request #5670 from menloresearch/release/v0.6.6 Louis 2025-07-02 10:58:33 +07:00
  • dc4e592de9
    Merge branch 'dev' into release/v0.6.6 Louis 2025-07-02 10:43:12 +07:00
  • ccffe4ced5
    Merge pull request #5669 from menloresearch/release/v0.6.4 Louis 2025-07-02 10:42:07 +07:00
  • 2a0597ff01
    Merge branch 'dev' into release/v0.6.6 Faisal Amir 2025-07-02 10:26:32 +07:00
  • f072aded62
    Merge branch 'menloresearch:dev' into de_de-i18n Bob Ros 2025-07-01 20:46:46 +02:00
  • defc6b92d2
    Merge pull request #5661 from menloresearch/template/yml-to-md Bui Quang Huy 2025-07-01 23:47:33 +08:00
  • a8a1de9ad0 🔧 config: all yml to md for issue template LazyYuuki 2025-07-01 23:45:44 +08:00
  • 5690c43633
    Merge pull request #5658 from menloresearch/template/fix-bug-md Bui Quang Huy 2025-07-01 23:36:13 +08:00
  • 5dc9073108 🔧 config: fix bug template LazyYuuki 2025-07-01 23:33:30 +08:00
  • 99df080bd6
    Merge pull request #5657 from menloresearch/template/yml-to-md Bui Quang Huy 2025-07-01 23:26:21 +08:00
  • 8e837fc73d 🔧 config: from yml to md for template LazyYuuki 2025-07-01 23:25:08 +08:00
  • 71cf69bb16
    Merge pull request #5606 from menloresearch/dependabot/npm_and_yarn/multi-f00634d4ce Louis 2025-07-01 20:02:59 +07:00
  • 94b25ec6e8
    Merge pull request #5650 from menloresearch/fix/top_k-model-setting-validation v0.6.4 release/v0.6.4 Louis 2025-07-01 17:31:03 +07:00
  • 0b88d93e18
    fix: top_k validation Louis 2025-07-01 16:40:22 +07:00
  • 7dd95101c2
    Merge pull request #5647 from menloresearch/template/update-config Bui Quang Huy 2025-07-01 15:04:51 +08:00
  • f1e28c2ab5
    Update config.yml Bui Quang Huy 2025-07-01 15:03:12 +08:00