0784fa661b
feat(core): add --host option to specify the host Tabby server will listen on. ( #1021 )
...
* Add --host option to specify the host Tabby server will listen on.
* [autofix.ci] apply automated fixes
---------
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2023-12-11 16:13:06 +08:00
c92b9e11c3
chore: fix rust build warning
2023-12-11 12:42:57 +08:00
b2a92f1cf7
test(golden): switch to cargo-insta for better developer experience ( #1018 )
2023-12-11 04:40:41 +00:00
e0d0133d86
feat: support build tabby on windows ( #948 )
...
* feat: update config to support build on windows
* resolve comment
* update release.yml
* resolve comment
2023-12-11 12:14:49 +08:00
63068724bf
fix: ci build in github runner, simply ignore tild related unit test ( #1002 )
2023-12-10 03:48:33 +00:00
1fa0106ca3
feat: fork aim-downloader into crates/aim-downloader to make it compatible with windows ( #996 )
...
* feat: support build on windows
* revert change
* feat: migrate aim source code
* revert change
* [autofix.ci] apply automated fixes
* fix test
* remove test dir, skip test
* fix test
---------
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2023-12-10 10:48:21 +08:00
6c6a2c803f
feat: make all features in webserver requires auth ( #992 )
...
* feat: require auth for webserver features
* cleanup frontend
* feat: add flag --webserver
* implement admin
* update format
2023-12-08 17:49:10 +00:00
f4224f0417
feat(tabby): add auth token support in swagger ui ( #988 )
2023-12-08 11:55:54 +00:00
928f1c527c
fix: normalize javascript / typescript / jsx /tsx in query side ( #980 )
2023-12-08 03:04:09 +00:00
9aed0dee08
feat: Add support for 7840U iGPU type ( #960 )
...
rocminfo reports that my AMD Ryzen 7 PRO 7840U w/ Radeon 780M Graphics GPU version is gfx1103
2023-12-06 23:11:05 +00:00
5c52a71f77
refactor: extract ServiceLocator interface ( #933 )
...
* refactor: cleanup the dependency chain - ServerContext should be the only thing being public in server mod
* refactor ServiceLocator
* refactor: extract worker.rs
* refactor: move db as private repo of server
* rename server -> service
2023-12-01 22:16:59 +08:00
1a9cbdcc3c
feat(ee): implement auth claims ( #932 )
...
* feat(ee): implement auth claims
* fix test
* [autofix.ci] apply automated fixes
---------
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2023-12-01 12:46:01 +00:00
2c2c95ccd7
fix: output unicode characters error ( #925 )
2023-12-01 12:18:26 +08:00
ffd5ef3449
fix: avoid llama.cpp's racing ( #923 )
2023-11-30 23:52:20 +08:00
4bcc411e07
chore: fix autofix for goldentests ( #921 )
...
* chore: fix autofix for goldentests
* [autofix.ci] apply automated fixes
* [autofix.ci] apply automated fixes (attempt 2/3)
---------
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2023-11-30 18:20:36 +08:00
8d1303d6e4
fix: properly recycle request id ( #920 )
2023-11-30 17:01:52 +08:00
30d2ba5f00
test: add chat golden test ( #919 )
...
* test: add chat golden test
* update
2023-11-30 08:26:55 +00:00
9c905e4849
feat: add rocm support ( #913 )
...
* Added build configurations for Intel and AMD hardware
* Improved rocm build
* Added options for OneAPI and ROCm
* Build llama using icx
* [autofix.ci] apply automated fixes
* Fixed rocm image
* Build ROCm
* Tried to adjust compile flags for SYCL
* Removed references to oneAPI
* Provide info about the used device for ROCm
* Added ROCm documentation
* Addressed review comments
* Refactored to expose generic accelerator information
* Pull request cleanup
* cleanup
* cleanup
* Delete .github/workflows/docker-cuda.yml
* Delete .github/workflows/docker-rocm.yml
* Delete crates/tabby-common/src/api/accelerator.rs
* update
* cleanup
* update
* update
* update
* update
---------
Co-authored-by: Cromefire_ <cromefire+git@pm.me>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2023-11-29 03:27:03 +00:00
2b131ad1d2
refactor: handle max output length in StopCondition ( #910 )
...
* refactor: handle max output length in StopCondition
* trim stop words
* [autofix.ci] apply automated fixes
---------
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2023-11-28 16:57:16 +08:00
e92a8c8005
Release 0.7.0-dev
...
http-api-bindings@0.7.0-dev
juniper-axum@0.7.0-dev
llama-cpp-bindings@0.7.0-dev
tabby@0.7.0-dev
tabby-common@0.7.0-dev
tabby-download@0.7.0-dev
tabby-inference@0.7.0-dev
tabby-scheduler@0.7.0-dev
tabby-webserver@0.7.0-dev
Generated by cargo-workspaces
2023-11-27 14:58:58 +08:00
b1481b0e2e
chore: release 0.6.0 ( #882 )
...
* add loadtest
* release 0.6.0
* Release 0.6.0-rc.0
http-api-bindings@0.6.0-rc.0
juniper-axum@0.6.0-rc.0
llama-cpp-bindings@0.6.0-rc.0
tabby@0.6.0-rc.0
tabby-common@0.6.0-rc.0
tabby-download@0.6.0-rc.0
tabby-inference@0.6.0-rc.0
tabby-scheduler@0.6.0-rc.0
tabby-webserver@0.6.0-rc.0
Generated by cargo-workspaces
* Release 0.6.0-rc.1
http-api-bindings@0.6.0-rc.1
juniper-axum@0.6.0-rc.1
llama-cpp-bindings@0.6.0-rc.1
tabby@0.6.0-rc.1
tabby-common@0.6.0-rc.1
tabby-download@0.6.0-rc.1
tabby-inference@0.6.0-rc.1
tabby-scheduler@0.6.0-rc.1
tabby-webserver@0.6.0-rc.1
Generated by cargo-workspaces
* Release 0.6.0-rc.2
http-api-bindings@0.6.0-rc.2
juniper-axum@0.6.0-rc.2
llama-cpp-bindings@0.6.0-rc.2
tabby@0.6.0-rc.2
tabby-common@0.6.0-rc.2
tabby-download@0.6.0-rc.2
tabby-inference@0.6.0-rc.2
tabby-scheduler@0.6.0-rc.2
tabby-webserver@0.6.0-rc.2
Generated by cargo-workspaces
* Release 0.6.0
http-api-bindings@0.6.0
juniper-axum@0.6.0
llama-cpp-bindings@0.6.0
tabby@0.6.0
tabby-common@0.6.0
tabby-download@0.6.0
tabby-inference@0.6.0
tabby-scheduler@0.6.0
tabby-webserver@0.6.0
Generated by cargo-workspaces
2023-11-27 14:57:45 +08:00
23a49beaa9
feat(ci): support manylinux build for cpu / cuda ( #899 )
2023-11-26 16:37:12 +08:00
2212171825
feat: add clipboard segment ( #898 )
...
* feat: add clipboard segment
* [autofix.ci] apply automated fixes
---------
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2023-11-26 11:27:03 +08:00
a7202318b1
refactor: make language optional in TextGenerationOptions ( #897 )
...
* refactor: make language optional in TextGenerationOptions
* [autofix.ci] apply automated fixes
---------
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2023-11-26 11:17:31 +08:00
e78cc1f844
feat: add api to serve files under repositories ( #851 )
...
* feat: add api to serve files under repositories
* resolve comments
* resolve comments
* Update repositories.rs
* Update lib.rs
* resolve comment
---------
Co-authored-by: Meng Zhang <meng@tabbyml.com>
2023-11-24 01:58:56 +00:00
821ca2dead
fix: Skip creating `usage_anonymous_id` when TABBY_DISABLE_USAGE_COLLECTION is set ( #864 )
...
* dont write file if tracking is disabled
* remove comment, id is optional
* Update usage.rs
---------
Co-authored-by: Meng Zhang <meng@tabbyml.com>
2023-11-23 15:46:07 +00:00
2192cc718f
feat: implement rust cargo.lock dependency extraction ( #874 )
...
* feat: implement rust cargo.lock dependency extraction
* [autofix.ci] apply automated fixes
---------
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2023-11-23 08:35:19 +00:00
bb4ffe937b
refactor: remove useless crates/tabby/Cargo.lock
2023-11-23 15:33:05 +08:00
3bddd9fa64
fix: axum middlewares only handles routes that are registered
2023-11-23 09:31:39 +08:00
b9cb5a025e
feat: add support for Kotlin language ( #813 )
...
* feat: add support for Kotlin
* Update programming-languages.md
* Update Cargo.toml
* fix: kotlin missing TAGGING_QUERY
* docs: remove 0.5.0 warning as tabby adapt same format for remote / local storage
* feat: make --model optional, so user can start a chat only instance (#817 )
* fix: mark tabby-ui as yarn managed
* fix: rust build caused by 1.74.0 release (#819 )
* chore: exclude experimental directory for language stats
* chore: exclude ee/tabby-webserver/ui to language stats
* fix: move db path, fix compile error (#820 )
* feat(vscode): Add dont-show-again for warnings. Add online help links. (#821 )
* refactor: delete contrib/jetson/Dockerfile as it's no longer compatible post 0.5
feel free to sending pr of adding it back if you get it work with llama.cpp based docker image
* feat(vim): update tabby-agent. (#824 )
* feat(intellij): Add dont-show-again for warnings. Add more online help links. (#823 )
* feat: implement basic dependency detection for python / rust (#825 )
* refactor: extract tags mod for dataset.rs
* feat: implement basic dependency detection for python / rust
* fix: keep only direct dependency, clean up path (#827 )
* feat: add support for Kotlin
* Update Cargo.toml
* fix: adjustment post rebase
* fix: added kotlin.scm to cover query tags
* fix: updated kotlin.scm
* remove definition import
Co-authored-by: Meng Zhang <meng@tabbyml.com>
* remove typealias
Co-authored-by: Meng Zhang <meng@tabbyml.com>
---------
Co-authored-by: Meng Zhang <meng@tabbyml.com>
Co-authored-by: Eric <illuminating.me@gmail.com>
Co-authored-by: Zhiming Ma <codes.icy@gmail.com>
2023-11-23 09:31:23 +08:00
b35d286d9e
fix: save_model_info failed if dir not exist ( #845 )
2023-11-20 04:27:30 +00:00
d8e83d0610
refactor: extract run_app function ( #843 )
...
* refactor: extract run_app function
* lint
* change route to /metrics
* refactor
2023-11-20 01:00:35 +00:00
6dabecc3ee
feat: add Prometheus support to Tabby. ( #838 )
...
* Added Prometheus support to Tabby.
1) Added `axum-prometheus` to Cargo.toml
2) Added `metrics.rs` as a simple route to produce a metrics endpoint with prometheus-formatted events
3) Added `/v1/metrics` endpoint with API doc entry
4) Added the `PrometheusLayer` to the root layers.
This change effectively allows for external Prometheus to scrape metrics from Tabby during execution in order to monitor operations (resources, timings and overall usage).
* changed application/text to text/plain to adhere to rfc1341
* Update Makefile
* Update Makefile
* Update Makefile
* Update Makefile
* Update Makefile
* Update Makefile
* - Reworked code to fit upstream changes
- Added Prometheus layer and handle to worker.rs
* Update CHANGELOG.md
* [autofix.ci] apply automated fixes
* Simplified worker metrics route definition
* [autofix.ci] apply automated fixes
* [autofix.ci] apply automated fixes (attempt 2/3)
---------
Co-authored-by: Meng Zhang <meng@tabbyml.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2023-11-19 15:40:57 -08:00
b56ad6eda9
fix: cors / otlp should be applied on all serve endpoints ( #839 )
2023-11-19 21:47:23 +00:00
a12f741565
feat: use remote code search in workers ( #833 )
...
* refactor: lift tabby::api::code to tabby_common::api::code
* feat: use remote code search in workers
* update
* handle errors
2023-11-18 23:45:00 +00:00
b862d9d100
feat: support worker events logging ( #831 )
...
* refactor: lift tabby::api::event to tabby_common::api::event
* feat: allow worker write logs to webserver::api::Hub service
* refactor: implement RawEventLogger on HubClient directly
* fix: build context in request's scope
2023-11-18 23:17:54 +00:00
530e142d63
fix: keep only direct dependency, clean up path ( #827 )
2023-11-18 08:50:16 +00:00
1fe0922c72
feat: implement basic dependency detection for python / rust ( #825 )
...
* refactor: extract tags mod for dataset.rs
* feat: implement basic dependency detection for python / rust
2023-11-18 08:05:48 +00:00
fcfa13136a
fix: move db path, fix compile error ( #820 )
2023-11-17 18:08:07 -08:00
25621547a7
feat: make --model optional, so user can start a chat only instance ( #817 )
2023-11-17 22:35:58 +00:00
ce338c7436
feat: validate token during worker registration ( #803 )
...
* feat: validate token during worker registration
* [autofix.ci] apply automated fixes
* [autofix.ci] apply automated fixes (attempt 2/3)
* resolve comments
* reslove comments
* format file, update schema file
* resolve comment
---------
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2023-11-16 23:05:39 -08:00
d0c9b56467
fix: chat model loading is wrongly distributed to --model ( #801 )
2023-11-16 03:35:12 +00:00
d41942975d
feat: match local model directory to MODEL_SPEC.md ( #800 )
2023-11-16 03:33:38 +00:00
abe0411f03
feat: add ee feature flag to distinguish the OSS and EE offering ( #789 )
...
* feat: add ee feature flag to distinguish the OSS offering and EE augmented offering
* [autofix.ci] apply automated fixes
* fix lint
---------
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2023-11-14 16:15:15 -08:00
bd072d8fb9
feat(ui): always display chat api endpoints in swagger doc ( #784 )
2023-11-14 21:10:41 +00:00
618009373b
refactor: use tarpc for easier worker <-> hub communication ( #781 )
...
* temp
* generic
* adapt client
* rename to api
* Revert "rename to api"
This reverts commit 8a51b24fecd76a78e6df576ec51605b8d8418975.
* refactor: remove uselss mutation
* remove useless connection
* cleanup api structure
* restructure
* add webserver api error
* webserver.rs -> server.rs
* rename service to Hub
* update schema
* update naming
* shrink features
* update
* mv worker.rs -> server/worker.rs
2023-11-14 12:48:20 -08:00
e521f0637c
feat: add worker command worker::completion and worker::chat ( #778 )
2023-11-13 23:21:57 +00:00
ebbe6e5af8
fix: helpful message when llama.cpp submodule is not present ( #719 ) ( #775 )
2023-11-13 07:51:46 +00:00
e0017cadec
refactor: extract routes/ to share routes between commands ( #774 )
...
* refactor: extract routes/ to share routes between commands
* refactor: extract events api
* extract EventLogger service
* lift api into sub packages
* services completions -> completion
* remove useless code
* fix test
2023-11-13 06:24:20 +00:00
bad87a99a2
refactor: serve/engine.rs => services/model.rs
2023-11-12 20:41:15 -08:00
Jason