Commit Graph

102 Commits

Author SHA1 Message Date
Ettore Di Giacinto
128694213f
feat: llama.cpp gRPC C++ backend (#1170)
* wip: llama.cpp c++ gRPC server

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

* make it work, attach it to the build process

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

* update deps

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

* fix: add protobuf dep

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

* try fix protobuf on cmake

* cmake: workarounds

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

* add packages

* cmake: use fixed version of grpc

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

* cmake(grpc): install locally

* install grpc

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

* install required deps for grpc on debian bullseye

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

* debug

* debug

* Fixups

* no need to install cmake manually

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

* ci: fixup macOS

* use brew whenever possible

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

* macOS fixups

* debug

* fix container build

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

* workaround

* try mac

https://stackoverflow.com/questions/23905661/on-mac-g-clang-fails-to-search-usr-local-include-and-usr-local-lib-by-def

* Disable temp. arm64 docker image builds

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-10-16 21:46:29 +02:00
Ettore Di Giacinto
63418c1afc
ci: cleanup worker (#1166)
**Description**

Tries to make CI green again

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-10-12 18:09:56 +02:00
renovate[bot]
54688db994
chore(deps): update docker/metadata-action action to v5 (#1045)
[![Mend
Renovate](https://app.renovatebot.com/images/banner.svg)](https://renovatebot.com)

This PR contains the following updates:

| Package | Type | Update | Change |
|---|---|---|---|
| [docker/metadata-action](https://togithub.com/docker/metadata-action)
| action | major | `v4` -> `v5` |

---

### Release Notes

<details>
<summary>docker/metadata-action (docker/metadata-action)</summary>

### [`v5`](https://togithub.com/docker/metadata-action/compare/v4...v5)

[Compare
Source](https://togithub.com/docker/metadata-action/compare/v4...v5)

</details>

---

### Configuration

📅 **Schedule**: Branch creation - At any time (no schedule defined),
Automerge - At any time (no schedule defined).

🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.

♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.

🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.

---

- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box

---

This PR has been generated by [Mend
Renovate](https://www.mend.io/free-developer-tools/renovate/). View
repository job log
[here](https://developer.mend.io/github/go-skynet/LocalAI).

<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzNi44My4wIiwidXBkYXRlZEluVmVyIjoiMzYuODMuMCIsInRhcmdldEJyYW5jaCI6Im1hc3RlciJ9-->

Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-09-14 10:40:51 +02:00
renovate[bot]
813eaa867c
chore(deps): update docker/login-action action to v3 (#1040)
[![Mend
Renovate](https://app.renovatebot.com/images/banner.svg)](https://renovatebot.com)

This PR contains the following updates:

| Package | Type | Update | Change |
|---|---|---|---|
| [docker/login-action](https://togithub.com/docker/login-action) |
action | major | `v2` -> `v3` |

---

### Release Notes

<details>
<summary>docker/login-action (docker/login-action)</summary>

### [`v3`](https://togithub.com/docker/login-action/compare/v2...v3)

[Compare
Source](https://togithub.com/docker/login-action/compare/v2...v3)

</details>

---

### Configuration

📅 **Schedule**: Branch creation - At any time (no schedule defined),
Automerge - At any time (no schedule defined).

🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.

♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.

🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.

---

- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box

---

This PR has been generated by [Mend
Renovate](https://www.mend.io/free-developer-tools/renovate/). View
repository job log
[here](https://developer.mend.io/github/go-skynet/LocalAI).

<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzNi44My4wIiwidXBkYXRlZEluVmVyIjoiMzYuODMuMCIsInRhcmdldEJyYW5jaCI6Im1hc3RlciJ9-->

Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-09-13 09:17:50 +02:00
renovate[bot]
abffb16292
chore(deps): update docker/build-push-action action to v5 (#1039)
[![Mend
Renovate](https://app.renovatebot.com/images/banner.svg)](https://renovatebot.com)

This PR contains the following updates:

| Package | Type | Update | Change |
|---|---|---|---|
|
[docker/build-push-action](https://togithub.com/docker/build-push-action)
| action | major | `v4` -> `v5` |

---

### Release Notes

<details>
<summary>docker/build-push-action (docker/build-push-action)</summary>

###
[`v5`](https://togithub.com/docker/build-push-action/compare/v4...v5)

[Compare
Source](https://togithub.com/docker/build-push-action/compare/v4...v5)

</details>

---

### Configuration

📅 **Schedule**: Branch creation - At any time (no schedule defined),
Automerge - At any time (no schedule defined).

🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.

♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.

🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.

---

- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box

---

This PR has been generated by [Mend
Renovate](https://www.mend.io/free-developer-tools/renovate/). View
repository job log
[here](https://developer.mend.io/github/go-skynet/LocalAI).

<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzNi44My4wIiwidXBkYXRlZEluVmVyIjoiMzYuODMuMCIsInRhcmdldEJyYW5jaCI6Im1hc3RlciJ9-->

Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-09-13 09:17:28 +02:00
Ettore Di Giacinto
1120847f72
feat: bump llama.cpp, add gguf support (#943)
**Description**

This PR syncs up the `llama` backend to use `gguf`
(https://github.com/go-skynet/go-llama.cpp/pull/180). It also adds
`llama-stable` to the targets so we can still load ggml. It adapts the
current tests to use the `llama-backend` for ggml and uses a `gguf`
model to run tests on the new backend.

In order to consume the new version of go-llama.cpp, it also bump go to
1.21 (images, pipelines, etc)

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-08-24 01:18:58 +02:00
Dave
a9ca70ad4a
infra: add setup-go@4, test against 1.20.x (go.mod) and stable (1.21) (#935) 2023-08-21 22:16:47 +02:00
Ettore Di Giacinto
fa4de05c14 fix: symlink libphonemize in the container
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-28 19:40:21 +02:00
Ettore Di Giacinto
569c1d1163
feat: add rope settings and negative prompt, drop grammar backend (#797)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-25 19:05:27 +02:00
Ettore Di Giacinto
92fca8ae74 ci: release space before build
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-21 22:56:43 +02:00
Ettore Di Giacinto
e459f114cd fix: fix tests, small refactors
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-20 23:52:04 +02:00
Ettore Di Giacinto
3feb632eb4
refactor: rename "llama-master" and "llama" (#776)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-20 00:36:16 +02:00
Ettore Di Giacinto
6352448b72
feat: add llama-master backend (#752)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-17 23:58:15 +02:00
Ettore Di Giacinto
cb5d6f6e3a ci: track updates for new deps
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-15 10:04:09 +02:00
Ettore Di Giacinto
98e73ed67a fix: CI fixes
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-15 01:19:43 +02:00
Ettore Di Giacinto
189cb3a7be feat: run all tests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-15 01:19:43 +02:00
Ettore Di Giacinto
d3d3187e51
feat: fix CUDA images and update go-llama to use full GPU offloading (#618)
Signed-off-by: mudler <mudler@localai.io>
Co-authored-by: mudler <mudler@localai.io>
2023-06-18 08:27:29 +02:00
Ettore Di Giacinto
2880221bb3
ci: drop macOS dependencies (#581)
Signed-off-by: mudler <mudler@mocaccino.org>
2023-06-13 09:31:11 +02:00
Ettore Di Giacinto
d9130def39
fix: correctly assign ffmpeg image tag (#499) 2023-06-04 21:07:12 +02:00
Ettore Di Giacinto
1bb85377e4
feat: add ffmpeg images (#492)
Signed-off-by: mudler <mudler@mocaccino.org>
2023-06-04 14:00:21 +02:00
Ettore Di Giacinto
8fb86c13bc
feat: Enable static builds for Linux binaries (#487)
Signed-off-by: mudler <mudler@mocaccino.org>
2023-06-03 23:46:07 +02:00
Sébastien Prud'homme
eee3f83d98
ci: build Docker image variants (#456)
Signed-off-by: Sébastien Prud'homme <sebastien.prudhomme@gmail.com>
2023-05-31 19:51:02 +02:00
Sébastien Prud'homme
171b50bb1c
ci: fix typo in variable name (#424)
Signed-off-by: Sébastien Prud'homme <sebastien.prudhomme@gmail.com>
2023-05-29 23:11:29 +02:00
Ettore Di Giacinto
9decd0813c
feat: update go-gpt2 (#359)
Signed-off-by: mudler <mudler@mocaccino.org>
2023-05-23 21:47:47 +02:00
Ettore Di Giacinto
43d3fb3eba
ci: add binary releases pipelines (#358) 2023-05-23 17:12:48 +02:00
Ettore Di Giacinto
1fade53a61
feat: minor enhancements to /models/apply (#297) 2023-05-19 08:31:11 +02:00
Ettore Di Giacinto
3f739575d8
Minor fixes (#285) 2023-05-17 21:01:46 +02:00
Ettore Di Giacinto
fd1df4e971
whisper: add tests and allow to set upload size (#237) 2023-05-12 10:04:20 +02:00
Ettore Di Giacinto
59e3c02002
make use of new bindings for gpt4all (#232) 2023-05-11 14:31:19 +02:00
Ettore Di Giacinto
11675932ac
feat: add dolly/redpajama/bloomz models support (#214) 2023-05-11 01:12:58 +02:00
Ettore Di Giacinto
f8ee20991c
feat: add bert.cpp embeddings (#222) 2023-05-10 15:20:21 +02:00
Ettore Di Giacinto
9f426578cf
feat: add transcript endpoint (#211) 2023-05-09 11:43:50 +02:00
mudler
6352308882 ci: minor fixups 2023-05-04 15:08:20 +02:00
mudler
a8172a0f4e ci: fix typo 2023-05-04 15:04:41 +02:00
mudler
ebcd10d66f ci: manually update deps 2023-05-04 15:01:29 +02:00
Ettore Di Giacinto
220d6fd59b
feat: add stream events (#152) 2023-05-02 20:03:35 +02:00
renovate[bot]
4e2061636e
chore(deps): update actions/checkout action to v3 (#82)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-04-25 07:46:29 +02:00
Ettore Di Giacinto
676e15f785
fix: make MacOS builds work (#61) 2023-04-22 11:05:23 +02:00
Ettore Di Giacinto
1c872ec326
feat: add CI/tests (#58)
Signed-off-by: mudler <mudler@mocaccino.org>
2023-04-22 00:44:52 +02:00
Ettore Di Giacinto
80f50e6ccd
Rename project to LocalAI (#35)
Signed-off-by: mudler <mudler@c3os.io>
2023-04-19 18:43:10 +02:00
mudler
a9cd6b3ca3 ci: Fix tag detection for 'latest' 2023-04-13 01:37:09 +02:00
mudler
a896a2b5ad Drop armv7 builds 2023-04-13 01:21:40 +02:00
mudler
16f1281d38 Minor workflow fixes 2023-04-13 01:16:13 +02:00
mudler
8042e9a2d6 Add docker-compose
Fixes #14

Signed-off-by: mudler <mudler@c3os.io>
2023-04-13 01:13:14 +02:00
mudler
6394d85ca2 Lower conversion parallelism 2023-03-23 19:22:23 +01:00
mudler
2b6a5aef5f Lower earthly parallelism 2023-03-23 19:17:15 +01:00
mudler
d191ecb9fe Disable release pipeline 2023-03-23 19:14:39 +01:00
mudler
6ca13f0227 Cleanup workers to have more free space 2023-03-20 10:12:31 +01:00
mudler
8da01d768c Update Earthly versions 2023-03-20 00:40:32 +01:00
mudler
e764c3225c Workaround Earthly issue 2023-03-20 00:24:37 +01:00
mudler
291a8a6d2e Multi-platform Earthly build must be in a target 2023-03-19 23:52:00 +01:00
mudler
896da59b87 Add GitHub action workflows 2023-03-19 23:50:31 +01:00