ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2024-12-19 04:37:53 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity
2,659 Commits 43 Branches 108 Tags 45 MiB
e332ff8066
Commit Graph

2659 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ettore Di Giacinto
e332ff8066
models(gallery): add gemma-2-2b-arliai-rpmax-v1.1 (#3635) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-23 19:16:41 +02:00
Ettore Di Giacinto
26d99ed1c7
models(gallery): add gemma-2-9b-arliai-rpmax-v1.1 (#3634) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-23 19:12:54 +02:00
Ettore Di Giacinto
1da8d8b9db
models(gallery): add nightygurps-14b-v1.1 (#3633) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-23 19:09:51 +02:00
Ettore Di Giacinto
bf8f8671d1
chore(ci): adjust parallelism 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-09-23 19:04:36 +02:00
Ettore Di Giacinto
51cba89682
fix(hipblas): do not push all variants to hipblas builds (#3630) 
Like with CUDA builds, we don't need all the variants when we are
compiling against the accelerated variants - in this way we save space
and we avoid to exceed embedFS golang size limits.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-23 11:49:07 +02:00
Ettore Di Giacinto
3e8e71f8b6
fix(ci): fixup checksum scanning pipeline (#3631) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-23 10:56:10 +02:00
LocalAI [bot]
4edd8c80b4
chore: ⬆️ Update ggerganov/llama.cpp to c35e586ea57221844442c65a1172498c54971cb0 (#3629) 
⬆️ Update ggerganov/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>
 2024-09-22 21:41:34 +00:00
Ettore Di Giacinto
fd70a22196
chore(ci): adjust parallel jobs 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-09-22 15:21:16 +02:00
Ettore Di Giacinto
56f4deb938
chore(ci): split hipblas jobs 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-09-22 15:19:38 +02:00
Ettore Di Giacinto
9bd7f3f995
feat(coqui): switch to maintained community fork (#3625) 
Fixes: https://github.com/mudler/LocalAI/issues/2513

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-22 10:04:20 +02:00
Sertaç Özercan
ee21b00a8d
feat: auto load into memory on startup (#3627) 
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
 2024-09-22 10:03:30 +02:00
LocalAI [bot]
1f43678d53
chore: ⬆️ Update ggerganov/llama.cpp to d09770cae71b416c032ec143dda530f7413c4038 (#3626) 
⬆️ Update ggerganov/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>
 2024-09-21 22:03:23 +00:00
Ettore Di Giacinto
20c0e128c0
fix(sycl): downgrade pypinyin 
melotts requires pypinyin 0.50

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-09-21 21:52:12 +02:00
Ettore Di Giacinto
5c3d1d81e6
fix(parler-tts): fix install with sycl (#3624) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-21 16:04:04 +02:00
lnyxaris
c22b3187a7
Fix NeuralDaredevil URL (#3621) 
Signed-off-by: lnyxaris <nyxaris@anomalous.news>
 2024-09-21 10:10:27 +02:00
LocalAI [bot]
54f2657870
chore: ⬆️ Update ggerganov/llama.cpp to 63351143b2ea5efe9f8b9c61f553af8a51f1deff (#3622) 
⬆️ Update ggerganov/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>
 2024-09-21 10:09:41 +02:00
LocalAI [bot]
cef7f8a014
chore: ⬆️ Update ggerganov/whisper.cpp to 34972dbe221709323714fc8402f2e24041d48213 (#3623) 
⬆️ Update ggerganov/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>
 2024-09-20 21:41:13 +00:00
Ettore Di Giacinto
bf8e50a11d
chore(docs): add Vulkan images links (#3620) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-20 18:16:01 +02:00
Ettore Di Giacinto
6c6cd8bbe0
models(gallery): add llama-3.1-8b-arliai-rpmax-v1.1 (#3619) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-20 18:15:51 +02:00
Ettore Di Giacinto
00d6c2a966 models(gallery): add llama3.1-reflective config 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-20 17:35:06 +02:00
Ettore Di Giacinto
415cf31aa3
models(gallery): add buddy2 (#3618) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-20 17:33:29 +02:00
Ettore Di Giacinto
f55053bfba
models(gallery): add llama3.1-8b-shiningvaliant2 (#3617) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-20 17:26:59 +02:00
Ettore Di Giacinto
e24654ada0
models(gallery): add llama-3.1-supernova-lite (#3616) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-20 17:23:30 +02:00
Ettore Di Giacinto
c4cecba07f
models(gallery): add llama-3.1-supernova-lite-reflection-v1.0-i1 (#3615) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-20 17:19:53 +02:00
Ettore Di Giacinto
38cad0b8dc
models(gallery): add qwen2.5 32B, 72B, 32B Instruct (#3614) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-20 17:10:43 +02:00
Ettore Di Giacinto
052af98dcd
models(gallery): add qwen2.5-0.5b-instruct, qwen2.5-1.5b-instruct (#3613) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-20 15:45:23 +02:00
Ettore Di Giacinto
56d8f5163c
models(gallery): add qwen2.5-math-72b-instruct (#3612) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-20 15:12:35 +02:00
Ettore Di Giacinto
b6af4f4467
models(gallery): add qwen2.5-coder-7b-instruct (#3611) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-20 15:08:57 +02:00
Ettore Di Giacinto
a5b08f43ff
models(gallery): add qwen2.5-14b_uncencored (#3610) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-20 11:22:53 +02:00
Ettore Di Giacinto
c15f506fd5
models(gallery): add qwen2.5-math-7b-instruct (#3609) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-20 11:18:49 +02:00
Ettore Di Giacinto
a2a63460e9
models(gallery): add qwen2.5-14b-instruct (#3607) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-20 10:59:29 +02:00
LocalAI [bot]
2fcea486eb
chore: ⬆️ Update ggerganov/llama.cpp to 6026da52d6942b253df835070619775d849d0258 (#3605) 
⬆️ Update ggerganov/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>
 2024-09-20 10:50:14 +02:00
LocalAI [bot]
5c9d26e39b
feat(swagger): update swagger (#3604) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-09-20 10:49:32 +02:00
Ettore Di Giacinto
191bc2e50a
feat(api): allow to pass audios to backends (#3603) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-19 12:26:53 +02:00
Ettore Di Giacinto
fbb9facda4
feat(api): allow to pass videos to backends (#3601) 
This prepares the API to receive videos as well for video understanding.

It works similarly to images, where the request should be in the form:

{
 "type": "video_url",
 "video_url": { "url": "url or base64 data" }
}

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-19 11:21:59 +02:00
LocalAI [bot]
c6a819e92f
chore: ⬆️ Update ggerganov/llama.cpp to 64c6af3195c3cd4aa3328a1282d29cd2635c34c9 (#3598) 
⬆️ Update ggerganov/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>
 2024-09-18 21:41:59 +00:00
Ettore Di Giacinto
a50cde69a2
chore(aio): rename gpt-4-vision-preview to gpt-4o (#3597) 
Fixes: 3596

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-18 15:55:46 +02:00
LocalAI [bot]
e5bd74878e
chore: ⬆️ Update ggerganov/whisper.cpp to 5b1ce40fa882e9cb8630b48032067a1ed2f1534f (#3592) 
⬆️ Update ggerganov/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>
 2024-09-18 00:02:02 +02:00
LocalAI [bot]
dc98b2ea44
chore: ⬆️ Update ggerganov/llama.cpp to 8b836ae731bbb2c5640bc47df5b0a78ffcb129cb (#3591) 
⬆️ Update ggerganov/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>
 2024-09-17 21:51:41 +00:00
Ettore Di Giacinto
acf119828f
Revert "chore(deps): Bump securego/gosec from 2.21.0 to 2.21.2" (#3590) 
Revert "chore(deps): Bump securego/gosec from 2.21.0 to 2.21.2 (#3561)"

This reverts commit 12a8d0e46f.
 2024-09-17 17:22:56 +02:00
Ettore Di Giacinto
a53392f919
chore(refactor): drop duplicated shutdown logics (#3589) 
* chore(refactor): drop duplicated shutdown logics

- Handle locking in Shutdown and CheckModelIsLoaded in a more go-idiomatic way
- Drop duplicated code and re-organize shutdown code

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

* fix: drop leftover

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

* chore: improve logging and add missing locks

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-09-17 16:51:40 +02:00
dependabot[bot]
eee1fb2c75
chore(deps): Bump pypinyin from 0.50.0 to 0.53.0 in /backend/python/openvoice (#3562) 
chore(deps): Bump pypinyin in /backend/python/openvoice

Bumps [pypinyin](https://github.com/mozillazg/python-pinyin) from 0.50.0 to 0.53.0.
- [Release notes](https://github.com/mozillazg/python-pinyin/releases)
- [Changelog](https://github.com/mozillazg/python-pinyin/blob/master/CHANGELOG.rst)
- [Commits](https://github.com/mozillazg/python-pinyin/compare/v0.50.0...v0.53.0)

---
updated-dependencies:
- dependency-name: pypinyin
  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>
 2024-09-17 10:24:34 +02:00
dependabot[bot]
8826ca93b3
chore(deps): Bump openai from 1.44.0 to 1.45.1 in /examples/langchain/langchainpy-localai-example (#3573) 
chore(deps): Bump openai

Bumps [openai](https://github.com/openai/openai-python) from 1.44.0 to 1.45.1.
- [Release notes](https://github.com/openai/openai-python/releases)
- [Changelog](https://github.com/openai/openai-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/openai/openai-python/compare/v1.44.0...v1.45.1)

---
updated-dependencies:
- dependency-name: openai
  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>
 2024-09-17 10:24:14 +02:00
dependabot[bot]
5049629381
chore(deps): Bump langchain from 0.2.16 to 0.3.0 in /examples/langchain/langchainpy-localai-example (#3577) 
chore(deps): Bump langchain

Bumps [langchain](https://github.com/langchain-ai/langchain) from 0.2.16 to 0.3.0.
- [Release notes](https://github.com/langchain-ai/langchain/releases)
- [Commits](https://github.com/langchain-ai/langchain/compare/langchain==0.2.16...langchain==0.3.0)

---
updated-dependencies:
- dependency-name: langchain
  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>
 2024-09-17 10:24:01 +02:00
Dave
92136a5d34
fix: gallery/index.yaml comment spacing (#3585) 
extremely minor fix: add a space to index.yaml for the scanner

Signed-off-by: Dave Lee <dave@gray101.com>
 2024-09-17 09:23:58 +02:00
Ettore Di Giacinto
075e5015c0
Revert "chore(deps): Bump setuptools from 69.5.1 to 75.1.0 in /backend/python/transformers" (#3586) 
Revert "chore(deps): Bump setuptools from 69.5.1 to 75.1.0 in /backend/python…"

This reverts commit e95cb8eaac.
 2024-09-17 09:06:07 +02:00
dependabot[bot]
46fd4ff6db
chore(deps): Bump openai from 1.44.0 to 1.45.1 in /examples/functions (#3560) 
Bumps [openai](https://github.com/openai/openai-python) from 1.44.0 to 1.45.1.
- [Release notes](https://github.com/openai/openai-python/releases)
- [Changelog](https://github.com/openai/openai-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/openai/openai-python/compare/v1.44.0...v1.45.1)

---
updated-dependencies:
- dependency-name: openai
  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>
 2024-09-17 06:19:52 +00:00
Alexander Izotov
4a4e44bf55
feat: allow setting trust_remote_code for sentencetransformers backend (#3552) 
Allow setting trust_remote_code for SentenceTransformers backend

Signed-off-by: Nyralei <93216976+Nyralei@users.noreply.github.com>
 2024-09-17 05:52:37 +00:00
dependabot[bot]
22247ad92c
chore(deps): Bump langchain from 0.2.16 to 0.3.0 in /examples/langchain-chroma (#3557) 
chore(deps): Bump langchain in /examples/langchain-chroma

Bumps [langchain](https://github.com/langchain-ai/langchain) from 0.2.16 to 0.3.0.
- [Release notes](https://github.com/langchain-ai/langchain/releases)
- [Commits](https://github.com/langchain-ai/langchain/compare/langchain==0.2.16...langchain==0.3.0)

---
updated-dependencies:
- dependency-name: langchain
  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>
 2024-09-17 05:50:31 +00:00
Ettore Di Giacinto
d0f2bf3181
fix(shutdown): do not shutdown immediately busy backends (#3543) 
* fix(shutdown): do not shutdown immediately busy backends

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

* chore(refactor): avoid duplicate functions

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

* fix: multiplicative backoff for shutdown (#3547)

* multiplicative backoff for shutdown

Rather than always retry every two seconds, back off the shutdown attempt rate? 

Signed-off-by: Dave <dave@gray101.com>

* Update loader.go

Signed-off-by: Dave <dave@gray101.com>

* add clamp of 2 minutes

Signed-off-by: Dave Lee <dave@gray101.com>

---------

Signed-off-by: Dave <dave@gray101.com>
Signed-off-by: Dave Lee <dave@gray101.com>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Dave <dave@gray101.com>
Signed-off-by: Dave Lee <dave@gray101.com>
Co-authored-by: Dave <dave@gray101.com>
 2024-09-17 04:50:57 +00:00