mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-12-31 14:40:15 -06:00
Code Issues Packages Projects Releases Wiki Activity
5,141 Commits 65 Branches 133 Tags
00a05208bcaedafe4e90ada49c5b9f0c5acf05a4
Commit Graph

5141 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ettore Di Giacinto
00a05208bc chore(docs): center video 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-12-08 16:59:11 +01:00
Ettore Di Giacinto
4a7cd256c9 Revise 'Screenshots' section to include video 
Updated section title and added video link for LocalAI.

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-12-08 16:56:34 +01:00
Ettore Di Giacinto
a27d0d151f Embed YouTube video in documentation 
Added an embedded YouTube video to the documentation.

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-12-08 16:53:20 +01:00
Ettore Di Giacinto
03a17a2986 fix(paths): remove trailing slash from requests (#7451) 
This removes any ambiguity from how paths are handled, and at the same
time it uniforms the ui paths with the other paths that don't have a
trailing slash

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-07 21:45:09 +01:00
Ettore Di Giacinto
8ca98c90ea chore(importers/llama.cpp): add models to 'llama-cpp' subfolder (#7450) 
This makes paths predictable, and avoids multiple model files to show in
the main view

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-07 21:44:57 +01:00
Ettore Di Giacinto
18b8956bd9 chore(gallery agent): strip thinking tags (#7464) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-07 19:25:41 +01:00
Ettore Di Giacinto
262afd28a0 chore(gallery agent): summary now is at root of the git repository (#7463) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-07 19:23:27 +01:00
LocalAI [bot]
5610384d8a chore: ⬆️ Update ggml-org/llama.cpp to db97837385edfbc772230debbd49e5efae843a71 (#7447) 
⬆️ 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>
 2025-12-07 08:32:35 +01:00
rampa3
6aee29d18f fix(ui): Update few links in web UI from 'browse' to '/browse/' (#7445) 
* Update few links in web UI from 'browse' to '/browse/'

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

* Update core/http/views/404.html

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>

* Update core/http/views/error.html

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>

* Update core/http/views/manage.html

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>

---------

Signed-off-by: rampa3 <68955305+rampa3@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-12-06 22:40:26 +01:00
LocalAI [bot]
c3493e4917 chore: ⬆️ Update ggml-org/whisper.cpp to a88b93f85f08fc6045e5d8a8c3f94b7be0ac8bce (#7448) 
⬆️ 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>
 2025-12-06 21:26:25 +00:00
LocalAI [bot]
edf7141b9b chore: ⬆️ Update ggml-org/llama.cpp to 8160b38a5fa8a25490ca33ffdd200cda51405688 (#7438) 
⬆️ 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>
 2025-12-06 13:35:24 +01:00
Ettore Di Giacinto
446b686470 Update model version in gallery-agent workflow 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-12-05 22:08:16 +01:00
Ettore Di Giacinto
b287944f07 Add Proto Dependencies installation step 
Added steps to install protobuf and Go dependencies in the GitHub Actions workflow.

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-12-05 21:40:36 +01:00
LocalAI [bot]
f3ae358689 chore(model-gallery): ⬆️ update checksum (#7437) 
⬆️ 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>
 2025-12-05 15:20:21 +01:00
Richard Palethorpe
c7aaeab683 fix(stablediffusion-ggml): Correct Z-Image model name (#7436) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2025-12-05 14:57:39 +01:00
Ettore Di Giacinto
024aa6a55b chore(deps): bump llama.cpp to 'bde188d60f58012ada0725c6dd5ba7c69fe4dd87' (#7434) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-05 00:17:35 +01:00
Ettore Di Giacinto
7ce8a56e96 chore(ci/agent): correctly invoke go run 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-04 23:12:04 +01:00
Ettore Di Giacinto
3e9ed48432 chore(ci/agent): support quantization 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-04 22:56:35 +01:00
Ettore Di Giacinto
963796ff51 Update localai-github-action to version 1.1 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-12-04 22:50:55 +01:00
Ettore Di Giacinto
6bd9a304bc Add local AI model to gallery agent workflow 
Updated the GitHub Actions workflow to include the local AI model and modified environment variables for the gallery agent.

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-12-04 22:43:31 +01:00
Ettore Di Giacinto
7990c7a401 chore(agent): update gallery agent to use importers 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-04 22:23:43 +01:00
LocalAI [bot]
4bb93b1c4c chore(model-gallery): ⬆️ update checksum (#7433) 
⬆️ 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>
 2025-12-04 21:23:26 +01:00
Copilot
1abbedd732 feat(diffusers): implement dynamic pipeline loader to remove per-pipeline conditionals (#7365) 
* Initial plan

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

* Add dynamic loader for diffusers pipelines and refactor backend.py

Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fix pipeline discovery error handling and test mock issue

Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Address code review feedback: direct imports, better error handling, improved tests

Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Address remaining code review feedback: specific exceptions, registry access, test imports

Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add defensive fallback for DiffusionPipeline registry access

Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Actually use dynamic pipeline loading for all pipelines in backend

Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Use dynamic loader consistently for all pipelines including AutoPipelineForText2Image

Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Move dynamic loader tests into test.py for CI compatibility

Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Extend dynamic loader to discover any diffusers class type, not just DiffusionPipeline

Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add AutoPipeline classes to pipeline registry for default model loading

Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(python): set pyvenv python home

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

* do pyenv update during start

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

* Minor changes

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-12-04 19:02:06 +01:00
Ettore Di Giacinto
92ee8c2256 fix(ui): prevent box overflow in chat view (#7430) 
Otherwise tool call and result might overflow the box

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-04 17:21:17 +01:00
Ettore Di Giacinto
78105e6b20 chore(ui): uniform buttons (#7429) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-04 17:18:51 +01:00
Richard Palethorpe
c2e4a1f29b feat(stablediffusion): Passthrough more parameters to support z-image and flux2 (#7419) 
* feat(stablediffusion): Passthrough more parameters to support z-image and flux2

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

* chore(z-image): Add Z-Image-Turbo GGML to library

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

* fix(stablediffusion-ggml): flush stderr and check errors when writing PNG

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

* fix(stablediffusion-ggml): Re-allocate Go strings in C++

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

* fix(stablediffusion-ggml): Try to avoid segfaults

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

* fix(stablediffusion-ggml): Init sample and easycache params

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>
 2025-12-04 17:08:21 +01:00
Ettore Di Giacinto
100ebdfa2c chore(ci): do not overload the apple tests 
Skip tests that are already run on other jobs and not really adding anything here. We have already functional tests that cover apple.

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-12-04 14:15:15 +01:00
LocalAI [bot]
ca2e878aaf chore: ⬆️ Update ggml-org/llama.cpp to e9f9483464e6f01d843d7f0293bd9c7bc6b2221c (#7421) 
⬆️ 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>
 2025-12-04 11:54:01 +01:00
Igor B. Poretsky
96e123d53a Messages output fix (#7424) 
The internal echo command in sh does not support "-e" and "-E" options
and interprets backslash escape sequences by default. So we prefer the
external echo command when it is available.
 2025-12-04 11:30:02 +01:00
LocalAI [bot]
7c5a0cde64 chore: ⬆️ Update leejet/stable-diffusion.cpp to 5865b5e7034801af1a288a9584631730b25272c6 (#7422) 
⬆️ 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>
 2025-12-04 11:29:16 +01:00
Ettore Di Giacinto
edcbf82b31 chore(ci): add wget 2025-12-04 10:01:34 +01:00
Ettore Di Giacinto
6558caca85 chore(ci): adapt also golang-based backends docker images 2025-12-04 09:14:08 +01:00
Ettore Di Giacinto
b4172762d7 chore(ci): do override pip in 24.04 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-03 22:54:13 +01:00
Ettore Di Giacinto
dc6182bbb1 chore(ci): add wget to llama-cpp docker image builder 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-03 22:48:41 +01:00
Ettore Di Giacinto
1d1d52da59 chore(ci): small fixups to build arm64 images 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-03 21:42:33 +01:00
Ettore Di Giacinto
46b1a1848f chore(ci): minor fixup 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-03 16:47:31 +01:00
LocalAI [bot]
957eea3da3 chore: ⬆️ Update ggml-org/llama.cpp to 61bde8e21f4a1f9a98c9205831ca3e55457b4c78 (#7415) 
⬆️ 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>
 2025-12-03 16:27:12 +01:00
Ettore Di Giacinto
ab4f2742a6 chore(ci): minor fixup 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-03 16:26:33 +01:00
Ettore Di Giacinto
03f3bf2d94 chore(ci): only install runtime libs needed on arm64 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-03 15:13:21 +01:00
Ettore Di Giacinto
774ddc60db chore(ci): specify ubuntu version in pipelines 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-03 11:10:18 +01:00
Ettore Di Giacinto
0ca1322b43 chore(ci): correctly pass ubuntu-version 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-03 09:58:10 +01:00
Ettore Di Giacinto
8dfeea2f55 fix: use ubuntu 24.04 for cuda13 l4t images (#7418) 
* fix: use ubuntu 24.04 for cuda13 l4t images

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

* Drop openblas from containers

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>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-03 09:47:03 +01:00
Ettore Di Giacinto
fea9018dc5 Revert "feat(stablediffusion): Passthrough more parameters to support z-image and flux2" (#7417) 
Revert "feat(stablediffusion): Passthrough more parameters to support z-image…"

This reverts commit 4018e59b2a.
 2025-12-02 22:14:28 +01:00
Ettore Di Giacinto
d8c7e90a69 Add Dockerfile for arm64 with nvpl installation (#7416) 
Added installation of nvpl and updated apt-get commands for arm64 architecture.

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-12-02 21:55:42 +01:00
Ettore Di Giacinto
c045b7a6bb Update Dockerfile to install cudss package 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-12-02 21:23:21 +01:00
Ettore Di Giacinto
7a5c61b057 fix: configure sbsa packages for arm64 (#7413) 
* fix: configure sbsa packages for arm64

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

* tests

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>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-02 18:59:36 +01:00
Richard Palethorpe
4018e59b2a feat(stablediffusion): Passthrough more parameters to support z-image and flux2 (#7414) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2025-12-02 18:28:26 +01:00
Richard Palethorpe
aaece6685f chore(deps/stable-diffusion-ggml): update stablediffusion-ggml (#7411) 
* ⬆️ Update leejet/stable-diffusion.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* fix(stablediffusion-ggml): fixup schedulers and samplers arrays, use default getters

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

---------

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Signed-off-by: Richard Palethorpe <io@richiejp.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-12-02 16:35:39 +01:00
Ettore Di Giacinto
f5df806f35 Fixup tags 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-02 15:15:41 +01:00
Ettore Di Giacinto
cfd95745ed feat: add cuda13 images (#7404) 
* chore(ci): add cuda13 jobs

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

* Add to pipelines and to capabilities. Start to work on the gallery

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

* gallery

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

* capabilities: try to detect by looking at /usr/local

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

* neutts

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

* backends.yaml

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

* add cuda13 l4t requirements.txt

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

* add cuda13 requirements.txt

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>

* Pin vllm

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

* Not all backends are compatible

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

* add vllm to requirements

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

* vllm is not pre-compiled for cuda 13

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-12-02 14:24:35 +01:00