Commit Graph

2805 Commits

Author SHA1 Message Date
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
LocalAI [bot]
0e4e101101
chore: ⬆️ Update ggerganov/llama.cpp to 23e0d70bacaaca1429d365a44aa9e7434f17823b (#3581)
⬆️ 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 03:52:15 +00:00
dependabot[bot]
f4b1bd8f6d
chore(deps): Bump setuptools from 70.3.0 to 75.1.0 in /backend/python/vllm (#3580)
chore(deps): Bump setuptools in /backend/python/vllm

Bumps [setuptools](https://github.com/pypa/setuptools) from 70.3.0 to 75.1.0.
- [Release notes](https://github.com/pypa/setuptools/releases)
- [Changelog](https://github.com/pypa/setuptools/blob/main/NEWS.rst)
- [Commits](https://github.com/pypa/setuptools/compare/v70.3.0...v75.1.0)

---
updated-dependencies:
- dependency-name: setuptools
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-09-17 03:41:01 +00:00
dependabot[bot]
e95cb8eaac
chore(deps): Bump setuptools from 69.5.1 to 75.1.0 in /backend/python/transformers (#3579)
chore(deps): Bump setuptools in /backend/python/transformers

Bumps [setuptools](https://github.com/pypa/setuptools) from 69.5.1 to 75.1.0.
- [Release notes](https://github.com/pypa/setuptools/releases)
- [Changelog](https://github.com/pypa/setuptools/blob/main/NEWS.rst)
- [Commits](https://github.com/pypa/setuptools/compare/v69.5.1...v75.1.0)

---
updated-dependencies:
- dependency-name: setuptools
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-09-17 03:33:52 +00:00
Dave
db1159b651
feat: auth v2 - supersedes #2894 (#3476)
feat: auth v2 - supercedes #2894, metrics to follow later

Signed-off-by: Dave Lee <dave@gray101.com>
2024-09-16 23:29:07 -04:00