Commit Graph

656 Commits

Author SHA1 Message Date
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
Aman Gupta Karmani
12fe0932c4
feat: cancel stream generation if client disappears (#792) 2023-07-24 23:10:54 +02:00
finger42
72e3e236de
Added CPU information to entrypoint.sh (#794) 2023-07-23 19:27:55 +00:00
Ettore Di Giacinto
ab59b238b3
fix: update README 2023-07-23 18:58:24 +02:00
ci-robbot [bot]
bed9570e48
⬆️ Update nomic-ai/gpt4all (#785)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-23 09:51:42 +02:00
Dave
c6bf67f446
feat(llama2): add template for chat messages (#782)
Co-authored-by: Aman Karmani <aman@tmm1.net>

Lays some of the groundwork for LLAMA2 compatibility as well as other future models with complex prompting schemes.

Started small refactoring in pkg/model/loader.go regarding template loading. Currently still a part of ModelLoader, but should be easy to add template loading for situations other than overall prompt templates and the new chat-specific per-message templates
Adds support for new chat-endpoint-specific, per-message templates as an alternative to the existing Role: XYZ sprintf method.
Includes a temporary prompt template as an example, since I have a few questions before we merge in the model-gallery side changes (see )
Minor debug logging changes.
2023-07-22 11:31:39 -04:00
ci-robbot [bot]
5ee186b8e5
⬆️ Update go-skynet/go-llama.cpp (#723)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-22 00:55:33 +02:00
Ettore Di Giacinto
94817b557c
fix: make completions endpoint more close to OpenAI specification (#790)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-22 00:53:52 +02:00
Ettore Di Giacinto
26e1496075
Update README.md 2023-07-21 23:10:02 +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
Stepan
7fa5b8401d
[Telegram-bot example] Fix lint for command docker-compose (#787)
Co-authored-by: Stepan Zhashkov <steven.z@spectral-team.com>
2023-07-21 20:56:04 +02:00
Ettore Di Giacinto
0eac0402e1
feat: backends improvements (#778) 2023-07-21 20:55:49 +02:00
Ettore Di Giacinto
c71c729bc2 debug 2023-07-21 10:53:26 +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
982a7e86a8 feat: add huggingface embeddings backend
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-20 22:10:42 +02:00
Ettore Di Giacinto
94916749c5 feat: add external grpc and model autoloading 2023-07-20 22:10:12 +02:00
Ettore Di Giacinto
5ce5f87a26
fix: move metal file to grpcs assets (#777)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-20 22:00:07 +02:00
Ettore Di Giacinto
1d2ae46ddc tests: clean up logs
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-20 01:36:34 +02:00
ci-robbot [bot]
71ac331f90
⬆️ Update nomic-ai/gpt4all (#775)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-20 01:22:44 +02:00
Ettore Di Giacinto
47cc95fc9f feat: add all backends to autoload
Now since gRPCs are not crashing the main thread we can just greedly
attempt all the backends we have available.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-20 00:40:28 +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
236497e331
feat: resolve JSONSchema refs (planners) (#774) 2023-07-19 22:56:13 +02:00
ci-robbot [bot]
a38dc497b2
⬆️ Update go-skynet/go-llama.cpp (#770)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-19 19:44:33 +02:00
ci-robbot [bot]
28ed52fa94
⬆️ Update nomic-ai/gpt4all (#769)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-19 19:44:21 +02:00
Enzo Einhorn
e995b95c94
[build] pass build type to cmake on libtransformers.a build (#741)
Co-authored-by: Enzo Einhorn <enzo.einhorn@hiventive.com>
2023-07-18 19:04:19 +02:00
Ettore Di Giacinto
8379cce209
example(functions): Add OpenAI functions example (#767) 2023-07-18 00:04:21 +02:00
ci-robbot [bot]
3c6b798522
⬆️ Update nomic-ai/gpt4all (#759)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-17 23:58:40 +02:00
ci-robbot [bot]
c18770a61a
⬆️ Update go-skynet/go-bert.cpp (#758)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-17 23:58:25 +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
renovate[bot]
fb6cce487f
fix(deps): update module github.com/gofiber/fiber/v2 to v2.48.0 (#757)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-07-16 22:02:30 +02:00
renovate[bot]
3079cc4167
fix(deps): update github.com/go-skynet/go-bert.cpp digest to 6abe312 (#756)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-07-16 22:01:53 +02:00
ci-robbot [bot]
27ef8b1eb7
⬆️ Update go-skynet/go-ggml-transformers.cpp (#711)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-16 09:57:16 +02:00
ci-robbot [bot]
c00435d72b
⬆️ Update nomic-ai/gpt4all (#735)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-16 09:57:00 +02:00
Ettore Di Giacinto
d0e67cce75 fix: make last stream message to send empty content
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-16 00:09:28 +02:00
renovate[bot]
6ec315e540
fix(deps): update github.com/go-skynet/go-llama.cpp digest to 6c97625 (#733)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-07-15 22:53:41 +02:00
renovate[bot]
cf4e6f909c
fix(deps): update github.com/nomic-ai/gpt4all/gpt4all-bindings/golang digest to cfd70b6 (#734)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-07-15 22:53:28 +02:00
renovate[bot]
b3a99166fd
fix(deps): update github.com/tmc/langchaingo digest to dcf7ecd (#736)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-07-15 22:53:18 +02:00
renovate[bot]
107008331e
fix(deps): update github.com/mudler/go-ggllm.cpp digest to 862477d (#745)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-07-15 22:53:05 +02:00
ci-robbot [bot]
accd9f9044
⬆️ Update donomii/go-rwkv.cpp (#750)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-15 22:52:45 +02:00
Ettore Di Giacinto
17294ae5e5
fix: make first stream message to send empty content (#751)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-15 22:50:52 +02:00
renovate[bot]
3c3a9b765a
fix(deps): update github.com/go-skynet/go-ggml-transformers.cpp digest to ffb09d7 (#744)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-07-15 16:16:13 +02:00
renovate[bot]
526c5bcdad
fix(deps): update module gopkg.in/yaml.v2 to v3 (#299)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-07-15 16:15:40 +02:00
renovate[bot]
a1bbe75d43
fix(deps): update module github.com/sashabaranov/go-openai to v1.14.0 (#739)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-07-15 16:15:17 +02:00
renovate[bot]
572a311639
fix(deps): update module google.golang.org/protobuf to v1.31.0 (#746)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-07-15 16:14:49 +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
e3cabb555d
feat: gRPC-based backends (#743) 2023-07-15 09:50:43 +02:00
Ettore Di Giacinto
f193f56564 fix: fix copy
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-15 01:19:43 +02:00
Ettore Di Giacinto
c0a91ab548 fix: fix LDFLAGS for rwkv.cpp
Previously the libs were added by other deps that made the linker add
those as well (by chance).

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-15 01:19:43 +02:00
Ettore Di Giacinto
26e510bf28 fix: Makefile
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-15 01:19:43 +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