mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-02-18 23:21:58 -05:00
Code Issues Packages Projects Releases Wiki Activity
5,580 Commits 81 Branches 136 Tags
01a238cd2cfeefd217283d8078a2b57a556777e6
Commit Graph

5580 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
dependabot[bot]
01a238cd2c chore(deps): bump github.com/mudler/cogito 
Bumps [github.com/mudler/cogito](https://github.com/mudler/cogito) from 0.8.2-0.20260214201734-da0d4ceb2b44 to 0.9.0.
- [Release notes](https://github.com/mudler/cogito/releases)
- [Commits](https://github.com/mudler/cogito/commits/v0.9.0)

---
updated-dependencies:
- dependency-name: github.com/mudler/cogito
  dependency-version: 0.9.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
 2026-02-18 21:34:38 +00:00
LocalAI [bot]
68c7077491 chore: ⬆️ Update ggml-org/llama.cpp to b55dcdef5dcd74dc75c4921090e928d43453c157 (#8599) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-02-18 22:33:25 +01:00
Ettore Di Giacinto
b471619ad9 chore(deps): bump cogito and add new options to the agent config (#8601) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-18 22:10:26 +01:00
LocalAI [bot]
a0476d5567 chore(model-gallery): ⬆️ update checksum (#8600) 
⬆️ Checksum updates in gallery/index.yaml

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-02-18 21:52:28 +01:00
Ettore Di Giacinto
a2228f1418 fix(ui): improve view on mobile (#8598) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-18 19:50:59 +01:00
Ettore Di Giacinto
7dd9a155a3 fix(ui): drop duplicated footer import 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-18 14:38:53 +01:00
Richard Palethorpe
4fe830ff58 fix(realtime): Limit buffer sizes to prevent DoS (#8596) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2026-02-18 14:36:43 +01:00
Richard Palethorpe
86b3bc9313 fix(realtime): Better support for thinking models and setting model parameters (#8595) 
* fix(realtime): Wrap functions in OpenAI chat completions format

Signed-off-by: Richard Palethorpe <io@richiejp.com>

* feat(realtime): Set max tokens from session object

Signed-off-by: Richard Palethorpe <io@richiejp.com>

* fix(realtime): Find thinking start tag for thinking extraction

Signed-off-by: Richard Palethorpe <io@richiejp.com>

* fix(realtime): Don't send buffer cleared message when we automatically drop it

Signed-off-by: Richard Palethorpe <io@richiejp.com>

---------

Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2026-02-18 14:36:16 +01:00
Ettore Di Giacinto
2fabdc08e6 feat(ui): left navbar, dark/light theme (#8594) 
* feat(ui): left navbar, dark/light theme

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* darker background

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-18 00:14:39 +01:00
LocalAI [bot]
ed832cf0e0 chore: ⬆️ Update ggml-org/llama.cpp to 2b089c77580d347767f440205103e4da8ec33d89 (#8592) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-02-17 22:35:07 +00:00
LocalAI [bot]
95db1da309 chore(model-gallery): ⬆️ update checksum (#8593) 
⬆️ Checksum updates in gallery/index.yaml

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-02-17 21:31:35 +01:00
Richard Palethorpe
9e692967c3 fix(llama-cpp): Pass parameters when using embedded template (#8590) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2026-02-17 18:50:05 +01:00
Ettore Di Giacinto
ecba23d44e fix: improve watchdown logics (#8591) 
* fix: ensure proper watchdog shutdown and state passing between restarts

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix: add missing watchdog settings

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix: untrack model if we shut it down successfully

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-17 18:49:22 +01:00
LocalAI [bot]
067a255435 chore: ⬆️ Update ggml-org/llama.cpp to d612901116ab2066c7923372d4827032ff296bc4 (#8588) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-02-17 00:57:32 +01:00
dependabot[bot]
637ecba382 chore(deps): bump github.com/modelcontextprotocol/go-sdk from 1.2.0 to 1.3.0 (#8585) 
chore(deps): bump github.com/modelcontextprotocol/go-sdk

Bumps [github.com/modelcontextprotocol/go-sdk](https://github.com/modelcontextprotocol/go-sdk) from 1.2.0 to 1.3.0.
- [Release notes](https://github.com/modelcontextprotocol/go-sdk/releases)
- [Commits](https://github.com/modelcontextprotocol/go-sdk/compare/v1.2.0...v1.3.0)

---
updated-dependencies:
- dependency-name: github.com/modelcontextprotocol/go-sdk
  dependency-version: 1.3.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-02-16 23:04:19 +00:00
dependabot[bot]
46c64e59f5 chore(deps): bump github.com/jaypipes/ghw from 0.22.0 to 0.23.0 (#8587) 
Bumps [github.com/jaypipes/ghw](https://github.com/jaypipes/ghw) from 0.22.0 to 0.23.0.
- [Release notes](https://github.com/jaypipes/ghw/releases)
- [Commits](https://github.com/jaypipes/ghw/compare/v0.22.0...v0.23.0)

---
updated-dependencies:
- dependency-name: github.com/jaypipes/ghw
  dependency-version: 0.23.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-02-16 21:49:41 +00:00
dependabot[bot]
f806838c37 chore(deps): bump google.golang.org/grpc from 1.78.0 to 1.79.1 (#8583) 
Bumps [google.golang.org/grpc](https://github.com/grpc/grpc-go) from 1.78.0 to 1.79.1.
- [Release notes](https://github.com/grpc/grpc-go/releases)
- [Commits](https://github.com/grpc/grpc-go/compare/v1.78.0...v1.79.1)

---
updated-dependencies:
- dependency-name: google.golang.org/grpc
  dependency-version: 1.79.1
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-02-16 20:20:30 +00:00
Richard Palethorpe
074a982853 fix(gallery): Use YAML v3 to avoid merging maps with incompatible keys (#8580) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2026-02-16 14:10:19 +01:00
LocalAI [bot]
109f29cc24 chore: ⬆️ Update ggml-org/llama.cpp to 27b93cbd157fc4ad94573a1fbc226d3e18ea1bb4 (#8577) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-02-15 23:42:36 +01:00
LocalAI [bot]
587e4a21b3 chore: ⬆️ Update antirez/voxtral.c to 134d366c24d20c64b614a3dcc8bda2a6922d077d (#8578) 
⬆️ Update antirez/voxtral.c

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-02-15 23:42:11 +01:00
LocalAI [bot]
3f1f58b2ab chore: ⬆️ Update ggml-org/whisper.cpp to 364c77f4ca2737e3287652e0e8a8c6dce3231bba (#8576) 
⬆️ Update ggml-org/whisper.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-02-15 21:20:04 +00:00
Ettore Di Giacinto
01eb70caff Fix formatting in README.md for Audio to Text section 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-02-15 09:57:50 +01:00
LocalAI [bot]
d784851337 chore: ⬆️ Update ggml-org/llama.cpp to 01d8eaa28d57bfc6d06e30072085ed0ef12e06c5 (#8567) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-02-14 22:52:32 +01:00
Ettore Di Giacinto
1c4e5aa5c0 chore: bump cogito (#8568) 
Adapt to new API and drop call to Ask()

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-14 22:52:22 +01:00
LocalAI [bot]
94df096fb9 fix: pin neutts-air to known working commit (#8566) 
* chore: init

* fix: pin neutts-air to known working commit

---------

Co-authored-by: localai-bot <localai-bot@users.noreply.github.com>
 2026-02-14 21:16:37 +01:00
Ettore Di Giacinto
820bd7dd01 fix(ci): try to fix deps for l4t13 on qwen-* 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-14 10:21:23 +01:00
Austen
42cb7bda19 fix(llama-cpp): populate tensor_buft_override buffer so llama-cpp properly performs fit calculations (#8560) 
fix auto-fit for llama-cpp
 2026-02-14 10:07:37 +01:00
Ettore Di Giacinto
2fb9940b8a fix(voxcpm): pin setuptools (#8556) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-13 23:44:35 +01:00
LocalAI [bot]
2ff0ad4190 chore: ⬆️ Update ggml-org/llama.cpp to 05a6f0e8946914918758db767f6eb04bc1e38507 (#8553) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-02-13 22:48:01 +01:00
Ettore Di Giacinto
bd12103ed4 chore: compute capabilities once (#8555) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-13 22:23:06 +01:00
LocalAI [bot]
2e17edd72a fix: prevent excessive logging in capability detection (#8552) 
Closes #8527.

This PR fixes the excessive logging issue in capability detection by applying the existing capabilityLogged guard to the forced capability run file case.

## Changes
- Apply capabilityLogged flag to forced capability detection logging
- Prevents repeated log messages during backend discovery and gallery operations

Co-authored-by: localai-bot <localai-bot@users.noreply.github.com>
 2026-02-13 20:00:29 +00:00
Richard Palethorpe
24aab68b3f feat(gallery): Add nanbeige4.1-3b (#8551) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2026-02-13 18:23:44 +01:00
Richard Palethorpe
5bdbb10593 fix(realtime): Send proper image data to backend (#8547) 
* fix(realtime): Allow empty parameters

Signed-off-by: Richard Palethorpe <io@richiejp.com>

* fix(realtime): Just pass base64 string to backend

Signed-off-by: Richard Palethorpe <io@richiejp.com>

---------

Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2026-02-13 18:01:07 +01:00
Ettore Di Giacinto
2fd026e958 fix: update moonshine API, add setuptools to voxcpm requirements (#8541) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-12 23:22:37 +01:00
LocalAI [bot]
08718b656e chore: ⬆️ Update ggml-org/llama.cpp to 338085c69e486b7155e5b03d7b5087e02c0e2528 (#8538) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-02-12 23:21:53 +01:00
LocalAI [bot]
7121b189f7 chore(model-gallery): ⬆️ update checksum (#8540) 
⬆️ Checksum updates in gallery/index.yaml

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-02-12 21:54:33 +01:00
Richard Palethorpe
f6c80a6987 feat(realtime): Allow sending text, image and audio conversation items" (#8524) 
feat(realtime): Allow sending text and image conversation items

Signed-off-by: Richard Palethorpe <io@richiejp.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-02-12 19:33:46 +00:00
Ettore Di Giacinto
4a4d65f8e8 chore(model gallery): add vllm-omni models (#8536) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-12 18:27:20 +01:00
Ettore Di Giacinto
2858e71606 chore(model gallery): add neutts (#8535) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-12 18:17:03 +01:00
Ettore Di Giacinto
088205339c chore(model gallery): add voxcpm, whisperx, moonshine-tiny (#8534) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-12 18:13:03 +01:00
Ettore Di Giacinto
8616397d59 chore(model gallery): add nemo-asr (#8533) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-12 18:01:42 +01:00
Ettore Di Giacinto
1698f92bd0 Remove URL entry from gallery index 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-02-12 17:50:13 +01:00
Ettore Di Giacinto
02c95a57ae Add known use cases for audio processing 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-02-12 17:49:54 +01:00
rampa3
2ab6be1d0c chore(model gallery): Add npc-llm-3-8b (#8498) 
Signed-off-by: rampa3 <68955305+rampa3@users.noreply.github.com>
 2026-02-12 17:46:25 +01:00
Ettore Di Giacinto
9d78ec1bd8 chore(model gallery): add voxtral (which is only available in development) (#8532) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-12 17:44:24 +01:00
LocalAI [bot]
b10b85de52 chore: improve log levels verbosity (#8528) 
* chore: init for PR

* feat: improve log verbosity per #8449 - demote /api/resources to DEBUG, elevate job events to INFO

---------

Co-authored-by: localai-bot <localai-bot@users.noreply.github.com>
 2026-02-12 16:24:46 +01:00
Richard Palethorpe
1479bee894 fix(realtime): Sampling and websocket locking (#8521) 
* fix(realtime): Use locked websocket for concurrent access

Signed-off-by: Richard Palethorpe <io@richiejp.com>

* fix(realtime): Use sample rate set in session

Signed-off-by: Richard Palethorpe <io@richiejp.com>

* fix(config): Allow pipelines to have no model parameters

Signed-off-by: Richard Palethorpe <io@richiejp.com>

---------

Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2026-02-12 13:57:34 +01:00
Austen
cff972094c feat(diffusers): add experimental support for sd_embed-style prompt embedding (#8504) 
* add experimental support for sd_embed-style prompt embedding

Signed-off-by: Austen Dicken <cvpcsm@gmail.com>

* add doc equivalent to compel

Signed-off-by: Austen Dicken <cvpcsm@gmail.com>

* need to use flux1 embedding function for flux model

Signed-off-by: Austen Dicken <cvpcsm@gmail.com>

---------

Signed-off-by: Austen Dicken <cvpcsm@gmail.com>
 2026-02-11 22:58:19 +01:00
LocalAI [bot]
79a25f7ae9 chore: ⬆️ Update ggml-org/llama.cpp to 4d3daf80f8834e0eb5148efc7610513f1e263653 (#8513) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-02-11 21:48:39 +00:00
Richard Palethorpe
7270a98ce5 fix(realtime): Use user provided voice and allow pipeline models to have no backend (#8415) 
* fix(realtime): Use the voice provided by the user or none at all

Signed-off-by: Richard Palethorpe <io@richiejp.com>

* fix(ui,config): Allow pipeline models to have no backend and use same validation in frontend

Signed-off-by: Richard Palethorpe <io@richiejp.com>

---------

Signed-off-by: Richard Palethorpe <io@richiejp.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-02-11 14:18:05 +01:00