Commit Graph

1670 Commits

Author SHA1 Message Date
Ettore Di Giacinto
530bec9c64
feat(llama.cpp): do not specify backends to autoload and add llama.cpp variants (#2232)
* feat(initializer): do not specify backends to autoload

We can simply try to autoload the backends extracted in the asset dir.
This will allow to build variants of the same backend (for e.g. with different instructions sets),
so to have a single binary for all the variants.

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

* refactor(prepare): refactor out llama.cpp prepare steps

Make it so are idempotent and that we can re-build

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

* [TEST] feat(build): build noavx version along

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

* build: make build parallel

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

* build: do not override CMAKE_ARGS

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

* build: add fallback variant

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

* Fixups

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

* fix(huggingface-langchain): fail if no token is set

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

* fix(huggingface-langchain): rename

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

* fix: do not autoload local-store

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

* fix: give priority between the listed backends

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

---------

Signed-off-by: mudler <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-04 17:56:12 +02:00
fakezeta
fa10302dd2
docs: updated Transformer parameters description (#2234)
updated Transformer parameters
2024-05-04 10:45:25 +02:00
Ettore Di Giacinto
54faaa87ea
fix(webui): correct documentation URL for text2img (#2233)
Signed-off-by: mudler <mudler@localai.io>
Co-authored-by: Dave <dave@gray101.com>
2024-05-04 00:25:13 +00:00
dependabot[bot]
daba8a85f9
build(deps): bump tqdm from 4.65.0 to 4.66.3 in /examples/langchain/langchainpy-localai-example in the pip group across 1 directory (#2231)
build(deps): bump tqdm

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


Updates `tqdm` from 4.65.0 to 4.66.3
- [Release notes](https://github.com/tqdm/tqdm/releases)
- [Commits](https://github.com/tqdm/tqdm/compare/v4.65.0...v4.66.3)

---
updated-dependencies:
- dependency-name: tqdm
  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>
2024-05-03 23:15:06 +00:00
LocalAI [bot]
ac0f3d6e82
⬆️ Update ggerganov/whisper.cpp (#2230)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-05-03 22:16:26 +00:00
LocalAI [bot]
da0b6a89ae
⬆️ Update ggerganov/llama.cpp (#2229)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-05-03 21:39:28 +00:00
LocalAI [bot]
929a68c06d
⬆️ Update docs version mudler/LocalAI (#2228)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-05-03 21:18:11 +00:00
cryptk
a0aa5d01a1
feat: update ROCM and use smaller image (#2196)
* feat: update ROCM and use smaller image

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

* fix: add call to ldconfig to fix AMDs broken library packages

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

---------

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-05-03 18:46:49 +02:00
Ettore Di Giacinto
dc834cc9d2
Update README.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-03 09:42:35 +02:00
Ettore Di Giacinto
b58274b8a2
feat(ui): support multilineand style ul (#2226)
* feat(ui/chat): handle multiline in the input field

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

* feat(ui/chat): correctly display multiline messages

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

* feat(ui/chat): add list style

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

---------

Signed-off-by: mudler <mudler@localai.io>
2024-05-03 00:43:02 +02:00
Ettore Di Giacinto
a31d00d904
feat(aio): switch to llama3-based for LLM (#2225)
Signed-off-by: mudler <mudler@localai.io>
2024-05-03 00:41:45 +02:00
LocalAI [bot]
2cc1bd85af
⬆️ Update ggerganov/llama.cpp (#2224)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-05-02 21:23:40 +00:00
Ettore Di Giacinto
2c5a46bc34
feat(ux): Add chat, tts, and image-gen pages to the WebUI (#2222)
* feat(webui): Add chat page

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

* feat(webui): Add image-gen page

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

* feat(webui): Add tts page

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-02 21:14:10 +02:00
Ettore Di Giacinto
f7f8b4804b
models(gallery): Add Hermes-2-Pro-Llama-3-8B-GGUF (#2218)
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-02 18:31:13 +02:00
Ettore Di Giacinto
e5bd9a76c7
models(gallery): add wizardlm2 (#2209)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-02 18:31:02 +02:00
fakezeta
4690b534e0
feat: user defined inference device for CUDA and OpenVINO (#2212)
user defined inference device

configuration via main_gpu parameter
2024-05-02 09:54:29 +02:00
LocalAI [bot]
6a7a7996bb
⬆️ Update ggerganov/llama.cpp (#2213)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-05-01 21:19:44 +00:00
Ettore Di Giacinto
962ebbaf77
models(gallery): fixup phi-3 sha
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-01 23:06:58 +02:00
LocalAI [bot]
f90d56d371
⬆️ Update ggerganov/llama.cpp (#2203)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-04-30 21:53:31 +00:00
Ettore Di Giacinto
445cfd4db3
models(gallery): add guillaumetell (#2195)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-04-30 23:24:41 +02:00
Ettore Di Giacinto
b24d44dc56
models(gallery): add suzume-llama-3-8B-multilingual-gguf (#2194)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-04-30 23:24:28 +02:00
Ettore Di Giacinto
cd31f8d865
models(gallery): add lexifun (#2193)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-04-30 23:24:13 +02:00
Chris Jowett
970cb3a219 chore: update go-stablediffusion to latest commit with Make jobserver fix
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-30 15:59:28 -05:00
cryptk
f7aabf1b50
fix: bring everything onto the same GRPC version to fix tests (#2199)
fix: more places where we are installing grpc that need a version specified
fix: attempt to fix metal tests
fix: metal/brew is forcing an update, they don't have 1.58 available anymore

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-30 19:12:15 +00:00
fakezeta
e38610e521
feat: OpenVINO acceleration for embeddings in transformer backend (#2190)
OpenVINO acceleration for embeddings

New argument type: OVModelForFeatureExtraction
2024-04-30 10:13:04 +02:00
cryptk
3754f154ee
feat: organize Dockerfile into distinct sections (#2181)
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-30 10:12:19 +02:00
LocalAI [bot]
29d7812344
⬆️ Update ggerganov/whisper.cpp (#2188)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-04-29 22:16:04 +00:00
cryptk
5fd46175dc
fix: ensure GNUMake jobserver is passed through to whisper.cpp build (#2187)
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-29 16:40:50 -05:00
LocalAI [bot]
52a268c38c
⬆️ Update ggerganov/llama.cpp (#2189)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-04-29 21:36:30 +00:00
dependabot[bot]
53c3842bc2
build(deps): bump dependabot/fetch-metadata from 2.0.0 to 2.1.0 (#2186)
Bumps [dependabot/fetch-metadata](https://github.com/dependabot/fetch-metadata) from 2.0.0 to 2.1.0.
- [Release notes](https://github.com/dependabot/fetch-metadata/releases)
- [Commits](https://github.com/dependabot/fetch-metadata/compare/v2.0.0...v2.1.0)

---
updated-dependencies:
- dependency-name: dependabot/fetch-metadata
  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>
2024-04-29 21:12:37 +00:00
Dave
c4f958e11b
refactor(application): introduce application global state (#2072)
* start breaking up the giant channel refactor now that it's better understood - easier to merge bites

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

* add concurrency and base64 back in, along with new base64 tests.

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

* Automatic rename of whisper.go's Result to TranscriptResult

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

* remove pkg/concurrency - significant changes coming in split 2

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

* fix comments

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

* add list_model service as another low-risk service to get it out of the way

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

* split backend config loader into seperate file from the actual config struct. No changes yet, just reduce cognative load with smaller files of logical blocks

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

* rename state.go ==> application.go

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

* fix lost import?

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

---------

Signed-off-by: Dave Lee <dave@gray101.com>
2024-04-29 17:42:37 +00:00
Ettore Di Giacinto
147440b39b
docs: add reference for concurrent requests
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-04-29 18:31:50 +02:00
Ettore Di Giacinto
baff5ff8c2
models(gallery): add openvino models (#2184)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-04-29 18:17:47 +02:00
Ettore Di Giacinto
ea13863221
models(gallery): add llama3-32k (#2183)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-04-29 18:17:39 +02:00
cryptk
93ca56086e
update go-tinydream to latest commit (#2182)
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-29 15:17:09 +02:00
Dave
11c48a0004
fix: security scanner warning noise: error handlers part 2 (#2145)
check off a few more error handlers

Signed-off-by: Dave Lee <dave@gray101.com>
2024-04-29 15:11:42 +02:00
fakezeta
b7ea9602f5
fix: undefined symbol: iJIT_NotifyEvent in import torch ##2153 (#2179)
* add  extra index to Intel repository

* Update install.sh
2024-04-29 15:11:09 +02:00
Dave
982dc6a2bd
fix: github bump_docs.sh regex to drop emoji and other text (#2180)
fix: bump_docs regex

Signed-off-by: Dave Lee <dave@gray101.com>
2024-04-29 03:55:29 +00:00
Sijia Lu
74d903acca
[Documentations] Removed invalid numberings from troubleshooting mac (#2174)
* updated troubleshooting mac

Signed-off-by: LeonSijiaLu <leonsijialu1@gmail.com>

* prepend -

Signed-off-by: LeonSijiaLu <leonsijialu1@gmail.com>

---------

Signed-off-by: LeonSijiaLu <leonsijialu1@gmail.com>
2024-04-29 02:21:51 +00:00
LocalAI [bot]
5fef3b0ff1
⬆️ Update ggerganov/whisper.cpp (#2177)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-04-28 22:32:45 +00:00
Ettore Di Giacinto
0674893649
Update .env
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-04-28 23:56:10 +02:00
Ettore Di Giacinto
e8d44447ad
feat(gallery): support model deletion (#2173)
* feat(gallery): op now supports deletion of models

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

* Wire things with WebUI(WIP)

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

* minor improvements

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-04-28 23:42:46 +02:00
Ettore Di Giacinto
a24cd4fda0
docs: enhance and condense few sections (#2178)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-04-28 23:41:59 +02:00
LocalAI [bot]
01860674c4
⬆️ Update ggerganov/llama.cpp (#2176)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-04-28 21:41:12 +00:00
cryptk
987b7ad42d
feat: only keep the build artifacts from the grpc build (#2172)
* feat: only keep the build artifacts from the grpc build

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

* feat: remove separate Cache GRPC build step

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

* feat: remove docker inspect step, it is leftover from previous debugging

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

---------

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-28 19:24:16 +00:00
cryptk
21974fe1d3
fix: swap to WHISPER_CUDA per deprecation message from whisper.cpp (#2170)
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-04-28 17:51:53 +00:00
Sijia Lu
26e1892521
Issue-1720: Updated Build on mac documentations (#2171)
updated build on macs documentation

Signed-off-by: LeonSijiaLu <leonsijialu1@gmail.com>
2024-04-28 19:38:02 +02:00
Ettore Di Giacinto
a78cd67737
Update quickstart.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-04-28 19:30:23 +02:00
Ettore Di Giacinto
5e243ceaeb
docs: update gallery, add rerankers (#2166)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-04-28 15:54:15 +02:00
QuinnPiers
1a0a6f60a7
docs: update model-gallery.md with correct gallery file (#2163)
* Update model-gallery.md with correct gallery file

The readme points to a file that hasn't been updated in months so when there are announcements about new models, user's won't get them pointing to the old file. Point to the updated files instead.

Signed-off-by: QuinnPiers <167640194+QuinnPiers@users.noreply.github.com>

* Update model-gallery.md

second pass with more understanding

Signed-off-by: QuinnPiers <167640194+QuinnPiers@users.noreply.github.com>

* Update model-gallery.md

Signed-off-by: QuinnPiers <167640194+QuinnPiers@users.noreply.github.com>

* Update model-gallery.md

Signed-off-by: QuinnPiers <167640194+QuinnPiers@users.noreply.github.com>

---------

Signed-off-by: QuinnPiers <167640194+QuinnPiers@users.noreply.github.com>
2024-04-28 12:34:15 +02:00