mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-02-14 08:31:10 -05:00
Code Issues Packages Projects Releases Wiki Activity
5,534 Commits 79 Branches 136 Tags
1479bee894d9ef984dda67f2e45cdd11c3069a39
Commit Graph

5534 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
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
LocalAI [bot]
0ee92317ec chore: ⬆️ Update ggml-org/llama.cpp to 57487a64c88c152ac72f3aea09bd1cc491b2f61e (#8499) 
⬆️ 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>
 2026-02-10 21:32:46 +00:00
LocalAI [bot]
743d2d1947 chore: ⬆️ Update ggml-org/whisper.cpp to 764482c3175d9c3bc6089c1ec84df7d1b9537d83 (#8478) 
⬆️ 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>
 2026-02-10 15:14:59 +01:00
LocalAI [bot]
df04843f34 chore: ⬆️ Update ggml-org/llama.cpp to 262364e31d1da43596fe84244fba44e94a0de64e (#8479) 
⬆️ 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>
 2026-02-10 15:14:33 +01:00
Kolega.dev
780877d1d0 security: validate URLs to prevent SSRF in content fetching endpoints (#8476) 
User-supplied URLs passed to GetContentURIAsBase64() and downloadFile()
were fetched without validation, allowing SSRF attacks against internal
services. Added URL validation that blocks private IPs, loopback,
link-local, and cloud metadata endpoints before fetching.

Co-authored-by: kolega.dev <faizan@kolega.ai>
 2026-02-10 15:14:14 +01:00
dependabot[bot]
08eeed61f4 chore(deps): bump github.com/openai/openai-go/v3 from 3.17.0 to 3.19.0 (#8485) 
Bumps [github.com/openai/openai-go/v3](https://github.com/openai/openai-go) from 3.17.0 to 3.19.0.
- [Release notes](https://github.com/openai/openai-go/releases)
- [Changelog](https://github.com/openai/openai-go/blob/main/CHANGELOG.md)
- [Commits](https://github.com/openai/openai-go/compare/v3.17.0...v3.19.0)

---
updated-dependencies:
- dependency-name: github.com/openai/openai-go/v3
  dependency-version: 3.19.0
  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>
 2026-02-10 05:41:15 +00:00
dependabot[bot]
5207ff84dc chore(deps): bump github.com/alecthomas/kong from 1.13.0 to 1.14.0 (#8481) 
Bumps [github.com/alecthomas/kong](https://github.com/alecthomas/kong) from 1.13.0 to 1.14.0.
- [Commits](https://github.com/alecthomas/kong/compare/v1.13.0...v1.14.0)

---
updated-dependencies:
- dependency-name: github.com/alecthomas/kong
  dependency-version: 1.14.0
  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>
 2026-02-10 04:29:00 +00:00
dependabot[bot]
4ade2e61ab chore(deps): bump github.com/onsi/ginkgo/v2 from 2.28.0 to 2.28.1 (#8483) 
Bumps [github.com/onsi/ginkgo/v2](https://github.com/onsi/ginkgo) from 2.28.0 to 2.28.1.
- [Release notes](https://github.com/onsi/ginkgo/releases)
- [Changelog](https://github.com/onsi/ginkgo/blob/master/CHANGELOG.md)
- [Commits](https://github.com/onsi/ginkgo/compare/v2.28.0...v2.28.1)

---
updated-dependencies:
- dependency-name: github.com/onsi/ginkgo/v2
  dependency-version: 2.28.1
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-02-10 03:15:46 +00:00
dependabot[bot]
818be98314 chore(deps): bump github.com/jaypipes/ghw from 0.21.2 to 0.22.0 (#8484) 
Bumps [github.com/jaypipes/ghw](https://github.com/jaypipes/ghw) from 0.21.2 to 0.22.0.
- [Release notes](https://github.com/jaypipes/ghw/releases)
- [Commits](https://github.com/jaypipes/ghw/compare/v0.21.2...v0.22.0)

---
updated-dependencies:
- dependency-name: github.com/jaypipes/ghw
  dependency-version: 0.22.0
  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>
 2026-02-10 02:02:38 +00:00
dependabot[bot]
056c438452 chore(deps): bump github.com/anthropics/anthropic-sdk-go from 1.20.0 to 1.22.0 (#8482) 
chore(deps): bump github.com/anthropics/anthropic-sdk-go

Bumps [github.com/anthropics/anthropic-sdk-go](https://github.com/anthropics/anthropic-sdk-go) from 1.20.0 to 1.22.0.
- [Release notes](https://github.com/anthropics/anthropic-sdk-go/releases)
- [Changelog](https://github.com/anthropics/anthropic-sdk-go/blob/main/CHANGELOG.md)
- [Commits](https://github.com/anthropics/anthropic-sdk-go/compare/v1.20.0...v1.22.0)

---
updated-dependencies:
- dependency-name: github.com/anthropics/anthropic-sdk-go
  dependency-version: 1.22.0
  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>
 2026-02-09 23:34:36 +00:00
LocalAI [bot]
0c040beb59 chore: ⬆️ Update antirez/voxtral.c to c9e8773a2042d67c637fc492c8a655c485354080 (#8477) 
⬆️ 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>
 2026-02-09 22:20:03 +01:00
Ettore Di Giacinto
bf5a1dd840 feat(voxtral): add voxtral backend (#8451) 
* feat(voxtral): add voxtral backend

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

* simplify

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-09 09:12:05 +01:00
rampa3
f44200bec8 chore(model gallery): Add Ministral 3 family of models (aside from base versions) (#8467) 
Signed-off-by: rampa3 <68955305+rampa3@users.noreply.github.com>
 2026-02-09 09:10:37 +01:00
LocalAI [bot]
3b1b08efd6 chore: ⬆️ Update ggml-org/llama.cpp to e06088da0fa86aa444409f38dff274904931c507 (#8464) 
⬆️ 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>
 2026-02-09 09:09:32 +01:00
LocalAI [bot]
3d8791067f chore: ⬆️ Update ggml-org/whisper.cpp to 4b23ff249e7f93137cb870b28fb27818e074c255 (#8463) 
⬆️ 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>
 2026-02-09 09:08:55 +01:00
Austen
da8207b73b feat(stablediffusion-ggml): Improve legacy CPU support for stablediffusion-ggml backend (#8461) 
* Port AVX logic from whisper to stablediffusion-ggml

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

* disable BMI2 on AVX builds

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

---------

Signed-off-by: Austen Dicken <cvpcsm@gmail.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-02-08 23:11:33 +00:00
Varun Chawla
aa9ca401fa docs: update model gallery documentation to reference main repository (#8452) 
Fixes #8212 - Updated the note about reporting broken models to
reference the main LocalAI repository instead of the outdated
separate gallery repository reference.
 2026-02-08 22:14:23 +01:00
LocalAI [bot]
e43c0c3ffc docs: ⬆️ update docs version mudler/LocalAI (#8462) 
⬆️ Update docs version mudler/LocalAI

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-02-08 21:12:50 +00:00
LocalAI [bot]
944874d08b chore: ⬆️ Update ggml-org/llama.cpp to 8872ad2125336d209a9911a82101f80095a9831d (#8448) 
⬆️ 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>
v3.11.0 		2026-02-07 21:22:18 +00:00
Ettore Di Giacinto
3370d807c2 feat(nemo): add Nemo (only asr for now) backend (#8436) 
* feat(nemo): add Nemo (only asr for now) backend

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

* feat(nemo): add Nemo backend without Python version pins (#8438)

* Initial plan

* Remove Python version pins from nemo backend install.sh

Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>

* Pin pyarrow to 20.0.0 in nemo requirements

Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-02-07 08:19:37 +01:00
LocalAI [bot]
ae2689936a chore: ⬆️ Update ggml-org/llama.cpp to b83111815e9a79949257e9d4b087206b320a3063 (#8434) 
⬆️ 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>
 2026-02-06 21:22:33 +00:00
Richard Palethorpe
15c12674b6 fix(qwen-asr): Remove contagious slop (DEFAULT_GOAL) from Makefile (#8431) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2026-02-06 17:12:45 +01:00
Richard Palethorpe
7fbe1d2e72 chore(models): Add Qwen TTS 0.6b (#8428) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2026-02-06 10:30:36 +01:00
Richard Palethorpe
c1d0b10b14 chore(docs): Document using a local model gallery (#8426) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2026-02-06 10:28:41 +01:00
Andres
efd552f83e fix(api)!: Stop model prior to deletion (#8422) 
* Unload model prior to deletion

Signed-off-by: Andres Smith <andressmithdev@pm.me>

* Fix LFM model in gallery

Signed-off-by: Andres Smith <andressmithdev@pm.me>

* Remove mistakenly added files

Signed-off-by: Andres Smith <andressmithdev@pm.me>

---------

Signed-off-by: Andres Smith <andressmithdev@pm.me>
 2026-02-06 09:22:10 +01:00
LocalAI [bot]
bcd927da6e chore: ⬆️ Update ggml-org/llama.cpp to 22cae832188a1f08d18bd0a707a4ba5cd03c7349 (#8419) 
⬆️ 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>
 2026-02-06 09:21:33 +01:00
LocalAI [bot]
682ac7e637 chore(model-gallery): ⬆️ update checksum (#8420) 
⬆️ 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>
 2026-02-05 21:34:26 +01:00
LocalAI [bot]
c8d74d35df feat(swagger): update swagger (#8418) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-02-05 21:33:44 +01:00
Ettore Di Giacinto
a849f285a5 chore(tests): add audio/wav to expected wav file 2026-02-05 20:27:06 +00:00
Ettore Di Giacinto
697f6aa71c feat(audio): set audio content type (#8416) 
* feat(audio): set audio content type

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

* chore: add tests

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-05 19:14:12 +01:00
Ettore Di Giacinto
218d0526cb fix(qwen-tts): add six dependency 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-05 18:05:31 +01:00
Ettore Di Giacinto
9bc5ab18fa fix(voxcpm): make sed call unix-compliant 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-05 17:15:58 +01:00
Ettore Di Giacinto
a9267f391c fix(huggingface): add clean target 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-05 16:54:41 +01:00
Ettore Di Giacinto
029ae3420d fix(package.sh): drop redundant -a and -R 
-a implies already -R

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-05 16:39:38 +01:00
Ettore Di Giacinto
c0461f32a1 fix: add missing clean targets 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-05 16:38:16 +01:00
Ettore Di Giacinto
8989d2944e fix: add clean target to local-store 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-05 14:55:34 +01:00
Ettore Di Giacinto
7aea2add44 Revert "chore(deps): bump torch from 2.4.1 to 2.7.1+xpu in /backend/python/rerankers in the pip group across 1 directory" (#8412) 
Revert "chore(deps): bump torch from 2.4.1 to 2.7.1+xpu in /backend/python/re…"

This reverts commit 55e43b3f92.
 2026-02-05 14:17:33 +01:00
dependabot[bot]
55e43b3f92 chore(deps): bump torch from 2.4.1 to 2.7.1+xpu in /backend/python/rerankers in the pip group across 1 directory (#8407) 
chore(deps): bump torch

Bumps the pip group with 1 update in the /backend/python/rerankers directory: torch.


Updates `torch` from 2.4.1 to 2.7.1+xpu

---
updated-dependencies:
- dependency-name: torch
  dependency-version: 2.7.1+xpu
  dependency-type: direct:production
  dependency-group: pip
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-02-05 12:37:52 +00:00
Ettore Di Giacinto
53276d28e7 feat(musicgen): add ace-step and UI interface (#8396) 
* feat(musicgen): add ace-step and UI interface

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

* Correctly handle model dir

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

* Drop auto-download

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

* Fixups

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

* Add to models, fixup UIs icons

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

* fixups

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

* Update docs

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

* l4t13 is incompatbile

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

* avoid pinning version for cuda12

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

* Drop l4t12

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-05 12:04:53 +01:00
Yaroslav98214
6dbcdb0b9e fix: filter GGUF and GGML files from model list (#8397) 
Filter GGUF and GGML files from model list

Skip .gguf/.ggml loose files when listing models and add a test
for .gguf exclusion.

Closes #1077

Signed-off-by: Yaroslav98214 <diakovichyaroslav30@gmail.com>
 2026-02-05 10:17:46 +01:00
LocalAI [bot]
c30866ba95 chore: ⬆️ Update ggml-org/llama.cpp to b536eb023368701fe3564210440e2df6151c3e65 (#8399) 
⬆️ 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>
 2026-02-04 23:08:08 +01:00
LocalAI [bot]
b413beba2d chore: ⬆️ Update ggml-org/whisper.cpp to 941bdabbe4561bc6de68981aea01bc5ab05781c5 (#8398) 
⬆️ 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>
 2026-02-04 21:20:59 +00:00
Ettore Di Giacinto
9db4df22f3 chore: update torch and torchaudio version specifications for qwen-tts in MPS 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-02-04 16:55:42 +01:00
Jonas Bernard
5ac50c9348 fix(docs): Promote DEBUG=false in production docker compose (#8390) 
fix(docs): Use DEBUG=false in production docker compose

Signed-off-by: Jonas Bernard <public.jbernard@web.de>
 2026-02-04 09:35:32 +01:00
Ettore Di Giacinto
5201b58d3e feat(mlx): Add support for CUDA12, CUDA13, L4T, SBSA and CPU (#8380) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-02-03 23:53:34 +01:00
LocalAI [bot]
8fa6737bdc chore(model gallery): 🤖 add 1 new models via gallery agent (#8381) 
chore(model gallery): 🤖 add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-02-03 22:40:22 +01:00
Ettore Di Giacinto
3039ced287 chore(ci): enlarge sleep startup time 
Even if suboptimal as we should poll to wait for the service to be available, this should at least alleviate tests for now

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-02-03 22:07:07 +01:00