Commit Graph

2022 Commits

Author SHA1 Message Date
Ettore Di Giacinto
db42a93dab
models(gallery): add smegmma-deluxe-9b-v1 (#2784)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-12 12:37:55 +02:00
Ettore Di Giacinto
dcccfc2cce
models(gallery): add arliai-llama-3-8b-formax-v1.0 (#2783)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-12 12:22:17 +02:00
Ettore Di Giacinto
96127e9967
models(gallery): add replete-coder-instruct-8b-merged (#2782)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-12 12:15:27 +02:00
Ettore Di Giacinto
41bce28d5f
ci: add workflow to check PR style
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-07-12 10:01:27 +02:00
Loric
a00e9a82ae
Update remaining git clones to git fetch (#2779)
Signed-off-by: Loric <117862619+LoricOSC@users.noreply.github.com>
2024-07-12 06:43:58 +00:00
Ettore Di Giacinto
95e31fd279
feat(install.sh): support federated install (#2752)
* feat(install.sh): support federated install

This allows to support federation by exposing:

- FEDERATED: true/false to share the instance
- FEDERATED_SERVER: true/false to start the federated load balancer (it
  forwards requests to the federation)

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

* docs: update installer parameters

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Dave <dave@gray101.com>
2024-07-12 08:42:21 +02:00
Dave
fb04347d3b
fixes to check_and_update.py script (#2778)
* fixes to `check_and_update.py`  script

---------

Signed-off-by: Dave Lee <dave@gray101.com>
2024-07-12 08:40:45 +02:00
LocalAI [bot]
f5bcba70da
⬆️ Update ggerganov/llama.cpp (#2774)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-07-11 23:42:09 +00:00
Ettore Di Giacinto
d5846c8639
fix(ci): fixup correct path for check_and_update.py (#2777)
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-07-11 23:05:43 +02:00
Ettore Di Giacinto
664b2e352b
fix(ci): small fixups to checksum_checker.sh (#2776)
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-07-11 22:59:52 +02:00
Ettore Di Giacinto
dcbdc12cc9
Update bump_deps.yaml
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-07-11 22:59:02 +02:00
Loric
c87fca3ec1
Git fetch specific branch instead of full tree during build (#2748)
* Git fetch specific branch instead of full tree during build

* Recursively create directores for all sources

---------

Signed-off-by: Dave <dave@gray101.com>
Signed-off-by: Dave Lee <dave@gray101.com>
Co-authored-by: Shane <dev@null.com>
Co-authored-by: Dave <dave@gray101.com>
2024-07-11 20:51:59 +00:00
Ettore Di Giacinto
642f6cee75
feat(webui): show also models without a config in the welcome page (#2772)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-11 19:55:01 +02:00
Ettore Di Giacinto
03efa26ff5
ci: Do not test the full matrix on PRs (#2771)
* ci: Do not test the full matrix on PR

Hipblas and sycl take long time to build from scratch as for now. Until
we find a way to speedup image building we are going to test these only
on master, and not for every open PR.

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

* ci: do not run release workflow twice

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-11 19:08:39 +02:00
Ettore Di Giacinto
b6b8ab6c21
feat(models): pull models from urls (#2750)
* feat(models): pull models from urls

When using `run` now we can point directly to hf models via URL, for
instance:

```bash
local-ai run
huggingface://TheBloke/TinyLlama-1.1B-Chat-v0.3-GGUF/tinyllama-1.1b-chat-v0.3.Q2_K.gguf
```

Will pull the gguf model and place it in the models folder - of course
this depends on the fact that the gguf file should be automatically
detected by our guesser mechanism in order to this to make effective.

Similarly now galleries can refer to single files in the API requests.

This also changes the download code and `yaml` files now are treated in
the same way, so now config files are saved with the appropriate name
(and not hashed anymore).

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

* Adapt tests

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-11 15:04:05 +02:00
LocalAI [bot]
b60acabb82
⬆️ Update ggerganov/whisper.cpp (#2756)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-07-11 11:46:46 +00:00
LocalAI [bot]
e7eb81beeb
⬆️ Update ggerganov/llama.cpp (#2767)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-07-11 10:42:32 +00:00
LocalAI [bot]
e56110543b
feat(swagger): update swagger (#2766)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Dave <dave@gray101.com>
2024-07-11 08:56:55 +00:00
Dave
fd0bc21c3e
fix abseil test issue [attempt 3] (#2769)
* use a sed hack to jam a missing line in place for grpc's abseil version.

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

---------

Signed-off-by: Dave Lee <dave@gray101.com>
2024-07-11 01:40:54 +00:00
Ettore Di Giacinto
3bc5652b27
models(gallery): add hathor_tahsin-l3-8b-v0.85 (#2762)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-10 15:44:56 +02:00
Ettore Di Giacinto
59ef426fbf
feat(model-list): be consistent, skip known files from listing (#2760)
fix(model-list): be consistent, skip known files from listing

This changeset does two things:

- Removes the dependency of listing models from the OpenAI schema.
- Tries to reduce confusion between ListModels() in model loader and in
  the service - now there is only one ListModels which is in services
and does not depend anymore on the OpenAI schema
- The OpenAI-schema functions were moved nearby the OpenAI specific
  endpoints that needs the schema
- Drops the ListModel Service structure as there was no real need for
  it.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-10 15:28:39 +02:00
Ettore Di Giacinto
28c6daf916
ci(deps): add libgmock-dev (#2761)
* Revert "ci(grpc): disable ABSEIL tests (#2759)"

This reverts commit cbb93bd8ec.

* Revert "fix: arm builds via disabling abseil tests (#2758)"

This reverts commit 8d046de287.

* Revert "ci(arm64): fix gRPC build by adding googletest to CMakefile (#2754)"

This reverts commit 401ee553f4.

* ci(gmock): install libgmock-dev

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-10 15:23:23 +02:00
Dave
133987b1fb
feat: HF /scan endpoint (#2566)
* start by checking /scan during the checksum update

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

* add back in golang side features: downloader/uri gets struct and scan function, gallery uses it, and secscan/models calls it.

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

* add a param to scan specific urls - useful for debugging

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

* helpful printouts

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

* fix offsets

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

* fix error and naming

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

* expose error

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

* fix json tags

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

* slight wording change

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

* go mod tidy - getting warnings

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

* split out python to make editing easier, add some simple code  to delete contaminated entries from gallery

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

* o7 to my favorite part of our old name, go-skynet

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

* merge fix

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

* merge fix

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

* merge fix

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

* address review comments

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

* forgot secscan could accept multiple URL at once

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

* invert naming and actually use it

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

* missed cli/models.go

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

* Update .github/check_and_update.py

Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Signed-off-by: Dave <dave@gray101.com>

---------

Signed-off-by: Dave Lee <dave@gray101.com>
Signed-off-by: Dave <dave@gray101.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-07-10 13:18:32 +02:00
Ettore Di Giacinto
cbb93bd8ec
ci(grpc): disable ABSEIL tests (#2759)
* ci(grpc): disable ABSEIL tests

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

* debug

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-10 13:15:33 +02:00
LocalAI [bot]
7223284323
⬆️ Update ggerganov/llama.cpp (#2755)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-07-10 11:39:33 +02:00
Dave
8d046de287
fix: arm builds via disabling abseil tests (#2758)
fix: disable abseil tests

Signed-off-by: Dave Lee <dave@gray101.com>
2024-07-10 08:43:27 +02:00
Ettore Di Giacinto
2845baecd5
fix(cuda): downgrade default version from 12.5 to 12.4 (#2707)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-09 23:13:29 +02:00
Ettore Di Giacinto
d5a56f04be
feat(p2p): allow to disable DHT and use only LAN (#2751)
This allows LocalAI to be less noisy avoiding to connect outside.
Needed if e.g. there is no plan into using p2p across separate networks.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-09 23:10:02 +02:00
Ettore Di Giacinto
f120a0c9f9
docs(swagger): enhance coverage of APIs (#2753)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-09 23:09:49 +02:00
Ettore Di Giacinto
401ee553f4
ci(arm64): fix gRPC build by adding googletest to CMakefile (#2754)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-09 19:47:14 +02:00
LocalAI [bot]
e3c89ac9cd
⬆️ Update ggerganov/llama.cpp (#2747)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-07-09 10:41:34 +00:00
LocalAI [bot]
b59841cf69
⬆️ Update ggerganov/whisper.cpp (#2746)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-07-09 00:51:58 +00:00
Ettore Di Giacinto
cca881ec49
feat(p2p): Federation and AI swarms (#2723)
* Wip p2p enhancements

* get online state

* Pass-by token to show in the dashboard

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

* Style

* Minor fixups

* parametrize SearchID

* Refactoring

* Allow to expose/bind more services

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

* Add federation

* Display federated mode in the WebUI

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

* Small fixups

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

* make federated nodes visible from the WebUI

* Fix version display

* improve web page

* live page update

* visual enhancements

* enhancements

* visual enhancements

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-08 22:04:06 +02:00
Ettore Di Giacinto
dd95ae130f
Update README.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-07-08 08:25:16 +02:00
LocalAI [bot]
185ab93b0d
⬆️ Update ggerganov/llama.cpp (#2744)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-07-08 00:13:49 +00:00
Ettore Di Giacinto
bb38f051e6
Update README.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-07-07 23:01:01 +02:00
Ettore Di Giacinto
2a05c39adf
models(gallery): add smegmma-9b-v1 (#2743)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-07 15:24:16 +02:00
Ettore Di Giacinto
deb5311373
models(gallery): add nymph_8b-i1 (#2742)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-07 15:19:57 +02:00
Ettore Di Giacinto
bdfebfe0f4
models(gallery): add l3-uncen-merger-omelette-rp-v0.2-8b (#2741)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-07 15:15:20 +02:00
Ettore Di Giacinto
3a88299cfe
models(gallery): add llama-3-perky-pat-instruct-8b (#2740)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-07 15:10:37 +02:00
Ettore Di Giacinto
748e4cb6b1
models(gallery): add llama3-8b-instruct-replete-adapted (#2739)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-07 14:53:02 +02:00
Ettore Di Giacinto
7c554be4ea
models(gallery): add hathor_respawn-l3-8b-v0.8 (#2738)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-07 14:47:33 +02:00
LocalAI [bot]
6011845ee9
⬆️ Update ggerganov/llama.cpp (#2736)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-07-07 06:54:17 +00:00
Ettore Di Giacinto
c184f23621
models(gallery): add llama-3_8b_unaligned_alpha_rp_soup-i1 (#2734)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-06 15:31:00 +02:00
LocalAI [bot]
8cec0304ee
⬆️ Update ggerganov/llama.cpp (#2725)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-07-06 01:42:25 +00:00
Ettore Di Giacinto
dc51869c61
models(gallery): add l3-8b-lunaris-v1 (#2729)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-05 23:48:48 +02:00
Ettore Di Giacinto
f881d25630
models(gallery): add llama-3_8b_unaligned_alpha (#2727)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-05 23:35:40 +02:00
Ettore Di Giacinto
683c306f90
ci(Makefile): adds tts in binary releases (#2695)
* ci(Makefile): run tts and stablediffusion in dist

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

* re-add macos-13

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

* rely on detection

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

* move logic to a script

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

* missing some libs still

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-05 23:19:24 +02:00
Mauro Morales
a985d8c239
Allows to remove a backend from the list (#2721)
* Allows to remove a backend from the list

Signed-off-by: Mauro Morales <contact@mauromorales.com>

* Update Makefile

Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Signed-off-by: Mauro Morales <contact@mauromorales.com>

---------

Signed-off-by: Mauro Morales <contact@mauromorales.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-07-05 17:19:38 +00:00
Simon Siebert
17608ea6aa
Using exec when starting a backend instead of spawning a new process (#2720)
Co-authored-by: Simon Siebert <ansiebert@deloitte.de>
2024-07-05 16:59:18 +00:00