mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-02-01 02:03:04 -05:00
Code Issues Packages Projects Releases Wiki Activity
5,455 Commits 73 Branches 135 Tags
68dd9765a03ea88563e5768d52e374e7eb2ca2e8
Commit Graph

5455 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ettore Di Giacinto
68dd9765a0 feat(tts): add support for streaming mode (#8291) 
* feat(tts): add support for streaming mode

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

* Send first audio, make sure it's 16

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-30 11:58:01 +01:00
LocalAI [bot]
2c44b06a67 chore: ⬆️ Update ggml-org/llama.cpp to 4fdbc1e4dba428ce0cf9d2ac22232dc170bbca82 (#8283) 
⬆️ 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>
 2026-01-29 23:43:29 +01:00
LocalAI [bot]
7cc90db3e5 chore(model-gallery): ⬆️ update checksum (#8285) 
⬆️ 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>
 2026-01-29 21:51:18 +01:00
Ettore Di Giacinto
1e08e02598 feat(qwen-asr): add support to qwen-asr (#8281) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-29 21:50:35 +01:00
Richard Palethorpe
dd8e74a486 feat(realtime): Add audio conversations (#6245) 
* feat(realtime): Add audio conversations

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

* chore(realtime): Vendor the updated API and modify for server side

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

* feat(realtime): Update to the GA realtime API

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

* chore: Document realtime API and add docs to AGENTS.md

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

* feat: Filter reasoning from spoken output

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

* fix(realtime): Send delta and done events for tool calls and audio transcripts

Ensure that content is sent in both deltas and done events for function call arguments and audio transcripts. This fixes compatibility with clients that rely on delta events for parsing.

💘 Generated with Crush

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

* fix(realtime): Improve tool call handling and error reporting

- Refactor Model interface to accept []types.ToolUnion and *types.ToolChoiceUnion
  instead of JSON strings, eliminating unnecessary marshal/unmarshal cycles
- Fix Parameters field handling: support both map[string]any and JSON string formats
- Add PredictConfig() method to Model interface for accessing model configuration
- Add comprehensive debug logging for tool call parsing and function config
- Add missing return statement after prediction error (critical bug fix)
- Add warning logs for NoAction function argument parsing failures
- Improve error visibility throughout generateResponse function

💘 Generated with Crush

Assisted-by: Claude Sonnet 4.5 via Crush <crush@charm.land>
Signed-off-by: Richard Palethorpe <io@richiejp.com>

---------

Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2026-01-29 08:44:53 +01:00
Ettore Di Giacinto
48e08772f3 chore(llama.cpp): bump to 'f6b533d898ce84bae8d9fa8dfc6697ac087800bf' (#8275) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-29 00:22:25 +01:00
LocalAI [bot]
c28c0227c6 chore: ⬆️ Update leejet/stable-diffusion.cpp to e411520407663e1ddf8ff2e5ed4ff3a116fbbc97 (#8274) 
⬆️ Update leejet/stable-diffusion.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>
 2026-01-28 21:23:05 +00:00
Richard Palethorpe
856ca2d6b1 fix(qwen3): Be explicit with function calling format (#8265) 
Qwen3 4b was using the wrong function format (i.e. using "function"
instead of "name") within the realtime API.

If we specify the function calling format explicitly then it stops it.

Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2026-01-28 14:44:29 +01:00
Ettore Di Giacinto
9b973b79f6 feat: add VoxCPM tts backend (#8109) 
* feat: add VoxCPM tts backend

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

* Disable voxcpm on arm64 cpu

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-28 14:44:04 +01:00
Ettore Di Giacinto
cba8ef4e38 chore: fix backend icons 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-28 09:09:00 +01:00
Ettore Di Giacinto
f729e300d6 chore: fix backend icons 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-28 09:08:03 +01:00
LocalAI [bot]
9916811a79 chore: ⬆️ Update ggml-org/llama.cpp to 2b4cbd2834e427024bc7f935a1f232aecac6679b (#8258) 
⬆️ 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>
 2026-01-28 08:50:16 +01:00
Ettore Di Giacinto
2f7c595cd1 chore(model gallery): add z-image and z-image-turbo for diffusers (#8260) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-27 22:42:10 +01:00
rampa3
73decac746 chore(model gallery): Add mistral-community/pixtral-12b with mmproj (#8245) 
Rebased branch add_pixtral on master

Signed-off-by: rampa3 <68955305+rampa3@users.noreply.github.com>
 2026-01-27 21:43:31 +01:00
Ettore Di Giacinto
ec1598868b feat(vibevoice): add ASR support (#8222) 
* feat(vibevoice): add ASR support

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

* Add tests

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

* fixups

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

* chore(tests): download voice files

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

* Small fixups

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

* Small fixups

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

* Try to run on bigger runner

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

* Fixups

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

* Fixups

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

* Fixups

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

* debug

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

* CI can't hold vibevoice

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-27 20:19:22 +01:00
rampa3
93d7e5d4b8 chore(model gallery): Add entry for Magistral Small 1.2 with mmproj (#8248) 
Signed-off-by: rampa3 <68955305+rampa3@users.noreply.github.com>
 2026-01-27 16:55:00 +01:00
rampa3
ff5a54b9d1 chore(model gallery): Add entry for Mistral Small 3.1 with mmproj (#8247) 
* chore(model gallery): Add entry for Mistral Small 3.1 with mmproj

Signed-off-by: rampa3 <68955305+rampa3@users.noreply.github.com>

* Use llama-cpp subfolder structure akin to Qwen 3 VL

Signed-off-by: rampa3 <68955305+rampa3@users.noreply.github.com>

---------

Signed-off-by: rampa3 <68955305+rampa3@users.noreply.github.com>
 2026-01-27 16:54:14 +01:00
LocalAI [bot]
3c1f823c47 chore: ⬆️ Update ggml-org/llama.cpp to 8f80d1b254aef70a0959e314be368d05debe7294 (#8229) 
⬆️ 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>
 2026-01-26 21:19:43 +00:00
LocalAI [bot]
4024220d00 chore(model gallery): 🤖 add 1 new models via gallery agent (#8220) 
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>
 2026-01-26 12:11:24 +01:00
LocalAI [bot]
f76958d761 chore: ⬆️ Update ggml-org/llama.cpp to 0440bfd1605333726ea0fb7a836942660bf2f9a6 (#8216) 
⬆️ 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>
 2026-01-26 00:50:35 +01:00
LocalAI [bot]
2bd5ca45de chore: ⬆️ Update leejet/stable-diffusion.cpp to 43e829f21966abb96b08c712bccee872dc820914 (#8215) 
⬆️ Update leejet/stable-diffusion.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>
 2026-01-26 00:50:16 +01:00
Ettore Di Giacinto
6804ce1c39 chore(docs): change MEMORY_FILE_PATH to MEMORY_INDEX_PATH 
Updated MEMORY_FILE_PATH to MEMORY_INDEX_PATH in memory configuration.

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-01-25 22:14:11 +01:00
Dedy F. Setyawan
d499071bff fix(ui): correctly display selected image model (#8208) 
Signed-off-by: Dedy F. Setyawan <dedyfajars@gmail.com>
 2026-01-25 14:54:40 +01:00
Ettore Di Giacinto
26a374b717 chore: drop bark which is unmaintained (#8207) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-25 09:26:40 +01:00
rampa3
980de0e25b chore(model gallery): Add most of not yet present Piper voices from Hugging Face (#8202) 
Signed-off-by: rampa3 <68955305+rampa3@users.noreply.github.com>
 2026-01-25 08:56:53 +01:00
Ettore Di Giacinto
4767371aee chore(README): Add links 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-24 22:49:27 +01:00
Ettore Di Giacinto
131d247b78 chore(README): Update and simplify links 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-24 22:46:40 +01:00
Ettore Di Giacinto
b2a8a63899 feat(vllm-omni): add new backend (#8188) 
* feat(vllm-omni: add new backend

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

* default to py3.12

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-24 22:23:30 +01:00
LocalAI [bot]
05a332cd5f chore: ⬆️ Update ggml-org/llama.cpp to bb02f74c612064947e51d23269a1cf810b67c9a7 (#8196) 
⬆️ 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>
 2026-01-24 21:19:43 +00:00
Ettore Di Giacinto
05904c77f5 chore(exllama): drop backend now almost deprecated (#8186) 
exllama2 development has stalled and only old architectures are
supported. exllamav3 is still in development, meanwhile cleaning up
exllama2 from the gallery.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-24 08:57:37 +01:00
LocalAI [bot]
17783fa7d9 chore: ⬆️ Update leejet/stable-diffusion.cpp to fa61ea744d1a87fa26a63f8a86e45587bc9534d6 (#8184) 
⬆️ Update leejet/stable-diffusion.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>
 2026-01-24 08:57:24 +01:00
LocalAI [bot]
4019094111 chore: ⬆️ Update ggml-org/llama.cpp to 557515be1e93ed8939dd8a7c7d08765fdbe8be31 (#8183) 
⬆️ 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>
 2026-01-24 08:57:08 +01:00
Ettore Di Giacinto
ca65fc751a chore(model gallery): add qwen3-tts to model gallery (#8187) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-23 23:06:50 +01:00
LocalAI [bot]
a1e3acc590 docs: ⬆️ update docs version mudler/LocalAI (#8182) 
⬆️ 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>
 2026-01-23 22:03:47 +01:00
Ettore Di Giacinto
a36960e069 fix(qwen-tts): change icon URL in index.yaml 
Updated the icon URL for the project.

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-01-23 22:00:14 +01:00
Ettore Di Giacinto
58bb6a29ed Revert "chore(deps): bump torch from 2.4.1 to 2.7.1+xpu in /backend/python/bark in the pip group across 1 directory" (#8180) 
Revert "chore(deps): bump torch from 2.4.1 to 2.7.1+xpu in /backend/python/ba…"

This reverts commit 5881c82413.
 2026-01-23 17:25:04 +01:00
dependabot[bot]
5881c82413 chore(deps): bump torch from 2.4.1 to 2.7.1+xpu in /backend/python/bark in the pip group across 1 directory (#8175) 
chore(deps): bump torch

Bumps the pip group with 1 update in the /backend/python/bark 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>
 2026-01-23 15:32:15 +00:00
Ettore Di Giacinto
923ebbb344 feat(qwen-tts): add Qwen-tts backend (#8163) 
* feat(qwen-tts): add Qwen-tts backend

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

* Update intel deps

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

* Drop flash-attn for cuda13

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
v3.10.1 		2026-01-23 15:18:41 +01:00
LocalAI [bot]
ea51567b89 chore(model gallery): 🤖 add 1 new models via gallery agent (#8170) 
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>
 2026-01-23 08:19:39 +01:00
LocalAI [bot]
552c62a19c chore: ⬆️ Update leejet/stable-diffusion.cpp to 5e4579c11d0678f9765463582d024e58270faa9c (#8166) 
⬆️ Update leejet/stable-diffusion.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>
 2026-01-23 08:18:05 +01:00
Ettore Di Giacinto
c0b21a921b feat: detect thinking support from backend automatically if not explicitly set (#8167) 
detect thinking support from backend automatically if not explicitly set

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-23 00:38:28 +01:00
LocalAI [bot]
b10045adc2 chore: ⬆️ Update ggml-org/llama.cpp to a5eaa1d6a3732bc0f460b02b61c95680bba5a012 (#8165) 
⬆️ 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>
 2026-01-22 23:32:05 +00:00
Ettore Di Giacinto
61b5e3b629 chore: drop test file 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-22 22:19:38 +00:00
Ettore Di Giacinto
e35d7cb3b3 chore: drop test file 
the function now was removed

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-22 21:47:52 +00:00
Ettore Di Giacinto
0fa0ac4797 fix(videogen): drop incomplete endpoint, add GGUF support for LTX-2 (#8160) 
* Debug

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

* Drop openai video endpoint (is not complete)

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

* Add download button

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-01-22 14:09:20 +01:00
LocalAI [bot]
be7ed85838 chore(model gallery): 🤖 add 1 new models via gallery agent (#8157) 
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>
 2026-01-22 08:25:40 +01:00
LocalAI [bot]
c12b310028 chore: ⬆️ Update ggml-org/llama.cpp to c301172f660a1fe0b42023da990bf7385d69adb4 (#8151) 
⬆️ 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>
 2026-01-22 00:51:22 +01:00
LocalAI [bot]
0447d5564d chore: ⬆️ Update leejet/stable-diffusion.cpp to 329571131d62d64a4f49e1acbef49ae02544fdcd (#8152) 
⬆️ Update leejet/stable-diffusion.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>
 2026-01-22 00:50:41 +01:00
Ettore Di Giacinto
22c0eb5421 chore(diffusers): add 'av' to requirements.txt (#8155) 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-01-21 22:35:00 +01:00
LocalAI [bot]
a0a00fb937 chore(model-gallery): ⬆️ update checksum (#8153) 
⬆️ 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>
 2026-01-21 21:45:11 +01:00