Mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2024-06-07 19:40:48 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,486 Commits 23 Branches 89 Tags 18 MiB
48d0aa2f6d
Commit Graph

1486 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ettore Di Giacinto
48d0aa2f6d
models(gallery): add new models to the gallery (#2124) 
* models: add reranker and parler-tts-mini

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

* fix: chatml im_end should not have a newline

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

* models(noromaid): add

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

* models(llama3): add 70b, add dolphin2.9

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

* models(llama3): add unholy-8b

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

* models(llama3): add therapyllama3, aura

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-25 01:28:02 +02:00
Ettore Di Giacinto
b664edde29
feat(rerankers): Add new backend, support jina rerankers API (#2121) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-25 00:19:02 +02:00
LocalAI [bot]
e16658b7ec
⬆️ Update ggerganov/llama.cpp (#2123) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-04-24 22:00:17 +00:00
LocalAI [bot]
d30280ed23
⬆️ Update ggerganov/whisper.cpp (#2122) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-04-24 21:55:30 +00:00
Ettore Di Giacinto
9dbd217c59
docs(integrations): add Wave terminal 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-04-24 19:56:51 +02:00
Ettore Di Giacinto
23eac98b3c
docs: update hot topics 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-04-24 19:43:07 +02:00
Ettore Di Giacinto
4fffc47e77
deps(llama.cpp): update, use better model for function call tests (#2119) 
deps(llama.cpp): update

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-24 18:44:04 +02:00
LocalAI [bot]
d65214a234
⬆️ Update docs version mudler/LocalAI (#2113) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-04-24 11:11:41 +02:00
jtwolfe
2fb34b00b5
Incl ocv pkg for diffsusers utils (#2115) 
* Update diffusers.yml

Signed-off-by: jtwolfe <jamie.t.wolfe@gmail.com>

* Update diffusers-rocm.yml

Signed-off-by: jtwolfe <jamie.t.wolfe@gmail.com>

---------

Signed-off-by: jtwolfe <jamie.t.wolfe@gmail.com>
 2024-04-24 09:17:49 +02:00
fakezeta
f718a391c0
fix missing TrustRemoteCode in OpenVINO model load (#2114) 2024-04-24 00:45:37 +00:00
Ettore Di Giacinto
ac56ac2b2d
fix(gallery): show a fake image if no there is no icon (#2111) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-23 20:10:58 +02:00
Ettore Di Giacinto
34c3f563fd fix(gallery): fixup dreamshaper icon 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-23 20:05:59 +02:00
Ettore Di Giacinto
d2bea6f9e3 fix(gallery): fixup hermes q8 entry 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-23 20:01:56 +02:00
Ettore Di Giacinto
a09fe1b9ba fix(gallery): set margin for images 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-23 20:00:20 +02:00
Ettore Di Giacinto
55778b35ff fix(gallery): move metadata where it belongs 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-23 19:47:45 +02:00
Ettore Di Giacinto
8b169f1dac
feat(gallery): add llama3, hermes, phi-3, and others (#2110) 
Also adds embeddings and llava models

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-23 19:35:45 +02:00
Ettore Di Giacinto
d344daf129
feat(models-ui): minor visual enhancements (#2109) 
Show image if present, URL, tags, and better display buttons

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-23 18:43:25 +02:00
cryptk
3411e072ca
Fix cleanup sonarqube findings (#2106) 
* fix: update dockerignore and gitignore to exclude sonarqube work dir

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: remove useless equality check

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: use sonarqube Dockerfile recommendations

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

---------

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
 2024-04-23 18:43:00 +02:00
fakezeta
8e36fe9b6f
Transformers Backend: max_tokens adherence to OpenAI API (#2108) 
max token adherence to OpenAI API

improve adherence to OpenAI API when max tokens is omitted or equal to 0 in the request
 2024-04-23 18:42:17 +02:00
Ettore Di Giacinto
0d8bf91699
feat: Galleries UI (#2104) 
* WIP: add models to webui

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

* Register routes

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

* fix: don't cache models

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

* small fixups

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

* fix: fixup multiple installs (strings.Clone)

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-23 09:22:58 +02:00
LocalAI [bot]
bd507678be
⬆️ Update docs version mudler/LocalAI (#2105) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-04-22 22:04:57 +00:00
Taikono-Himazin
b6f0e80d54
Update text-generation.md (#2095) 
Signed-off-by: Taikono-Himazin <kazu@po.harenet.ne.jp>
 2024-04-22 16:37:13 +02:00
jtwolfe
729378ca98
AMD/ROCm Documentation update + formatting fix (#2100) 
* Update aio-images.md

Signed-off-by: jtwolfe <jamie.t.wolfe@gmail.com>

* Update aio-images.md

Signed-off-by: jtwolfe <jamie.t.wolfe@gmail.com>

* Update aio-images.md

Signed-off-by: jtwolfe <jamie.t.wolfe@gmail.com>

* Update GPU-acceleration.md

Signed-off-by: jtwolfe <jamie.t.wolfe@gmail.com>

* Update GPU-acceleration.md

Signed-off-by: jtwolfe <jamie.t.wolfe@gmail.com>

* Update GPU-acceleration.md

Signed-off-by: jtwolfe <jamie.t.wolfe@gmail.com>

* Update GPU-acceleration.md

Signed-off-by: jtwolfe <jamie.t.wolfe@gmail.com>

* Update GPU-acceleration.md

Signed-off-by: jtwolfe <jamie.t.wolfe@gmail.com>

* Update GPU-acceleration.md

Signed-off-by: jtwolfe <jamie.t.wolfe@gmail.com>

---------

Signed-off-by: jtwolfe <jamie.t.wolfe@gmail.com>
 2024-04-22 15:47:51 +02:00
Ikko Eltociear Ashimine
220958a87c
fix: typo in models.go (#2099) 2024-04-22 04:34:59 +00:00
Ettore Di Giacinto
f3f6535aad
fix: rename fiber entrypoint from http/api to http/app (#2096) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Dave <dave@gray101.com>
 2024-04-21 22:39:28 +02:00
Dave
228bc4903f
fix: action-tmate detached (#2092) 
connect-timeout-seconds works best with `detached: true`

Signed-off-by: Dave <dave@gray101.com>
 2024-04-21 22:39:17 +02:00
LocalAI [bot]
38c9abed8b
⬆️ Update ggerganov/llama.cpp (#2089) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-04-21 16:35:30 +00:00
fakezeta
66b002458d
Transformer Backend: Implementing use_tokenizer_template and stop_prompts options (#2090) 
* fix regression #1971

fixes regression #1971 introduced by intel_extension_for_transformers==1.4

* UseTokenizerTemplate and StopPrompt

Implementation of use_tokenizer_template and stopwords options
 2024-04-21 16:20:25 +00:00
Ettore Di Giacinto
39814cab32
Update README.md 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-04-21 16:46:13 +02:00
Ettore Di Giacinto
180cd4ccda
fix(llama.cpp-ggml): fixup max_tokens for old backend (#2094) 
fix(llama.cpp-ggml): set 0 as default for `max_tokens`

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-21 16:34:00 +02:00
Ettore Di Giacinto
284ad026b1
refactor(routes): split routes registration (#2077) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-21 01:19:57 +02:00
Ettore Di Giacinto
afa1bca1e3
fix(llama.cpp): set -1 as default for max tokens (#2087) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-20 20:20:10 +02:00
Taikono-Himazin
03adc1f60d
Add tensor_parallel_size setting to vllm setting items (#2085) 
Signed-off-by: Taikono-Himazin <kazu@po.harenet.ne.jp>
 2024-04-20 14:37:02 +00:00
Ettore Di Giacinto
b319ed58b0
models(gallery): add gallery (#2078) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-20 15:22:54 +02:00
cryptk
8d30b39811
feat: fiber logs with zerlog and add trace level (#2082) 
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
 2024-04-20 10:43:37 +02:00
Dave
1038f7469c
fix: action-tmate: use connect-timeout-sections and limit-access-to-actor (#2083) 
fix for action-tmate: connect-timeout-sections and limit-access-to-actor

Signed-off-by: Dave Lee <dave@gray101.com>
 2024-04-20 08:42:02 +00:00
cryptk
b9e7708643
feat: enable polling configs for systems with broken fsnotify (docker volumes on windows) (#2081) 
* feat: enable polling configs for systems with broken fsnotify (docker volumes on windows)

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: update logging to make it clear that the config file is being polled

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

---------

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
 2024-04-19 19:31:15 -05:00
LocalAI [bot]
1e37101930
⬆️ Update ggerganov/llama.cpp (#2080) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-04-20 00:05:16 +00:00
Ettore Di Giacinto
b2772509b4
models(llama3): add llama3 to embedded models (#2074) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-19 18:23:44 +02:00
Ettore Di Giacinto
27ec84827c
refactor(template): isolate and add tests (#2069) 
* refactor(template): isolate and add tests

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Dave <dave@gray101.com>
Co-authored-by: Dave <dave@gray101.com>
 2024-04-19 02:40:18 +00:00
cryptk
852316c5a6
fix: move the GRPC cache generation workflow into it's own concurrency group (#2071) 
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
 2024-04-18 20:52:34 -04:00
LocalAI [bot]
e9448005a5
⬆️ Update ggerganov/llama.cpp (#2051) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-04-18 21:30:55 +00:00
Ettore Di Giacinto
bbea62b907
feat(functions): support models with no grammar, add tests (#2068) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-18 22:43:12 +02:00
cryptk
13012cfa70
feat: better control of GRPC docker cache (#2070) 
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
 2024-04-18 16:19:36 -04:00
dependabot[bot]
8f2681f904
build(deps): bump aiohttp from 3.9.2 to 3.9.4 in /examples/langchain/langchainpy-localai-example in the pip group across 1 directory (#2067) 
build(deps): bump aiohttp

Bumps the pip group with 1 update in the /examples/langchain/langchainpy-localai-example directory: [aiohttp](https://github.com/aio-libs/aiohttp).


Updates `aiohttp` from 3.9.2 to 3.9.4
- [Release notes](https://github.com/aio-libs/aiohttp/releases)
- [Changelog](https://github.com/aio-libs/aiohttp/blob/master/CHANGES.rst)
- [Commits](https://github.com/aio-libs/aiohttp/compare/v3.9.2...v3.9.4)

---
updated-dependencies:
- dependency-name: aiohttp
  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>
 2024-04-18 17:17:33 +00:00
Ettore Di Giacinto
f9c75d4878
tests: add template tests (#2063) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-18 10:57:24 +02:00
cryptk
502c1eedaa
feat: refactor the dynamic json configs for api_keys and external_backends (#2055) 
* feat: refactor the dynamic json configs for api_keys and external_backends

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: remove commented code

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

---------

Signed-off-by: Chris Jowett <421501+cryptk@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>
 2024-04-18 03:21:55 +00:00
cryptk
e9f090257c
fix: adjust some sources names to match the naming of their repositories (#2061) 
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
 2024-04-18 01:59:05 +00:00
Ettore Di Giacinto
af9e5a2d05
Revert #1963 (#2056) 
* Revert "fix(fncall): fix regression introduced in #1963 (#2048)"

This reverts commit 6b06d4e0af.

* Revert "fix: action-tmate back to upstream, dead code removal (#2038)"

This reverts commit fdec8a9d00.

* Revert "feat(grpc): return consumed token count and update response accordingly (#2035)"

This reverts commit e843d7df0e.

* Revert "refactor: backend/service split, channel-based llm flow (#1963)"

This reverts commit eed5706994.

* feat(grpc): return consumed token count and update response accordingly

Fixes: #1920

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-04-17 23:33:49 +02:00
LocalAI [bot]
af8c705ecd
⬆️ Update ggerganov/whisper.cpp (#2060) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-04-17 21:17:25 +00:00