cotran
63cc2ef3f3
fix bug
2024-12-09 13:33:10 -08:00
cotran
3b0ba352a9
Merge branch 'shuguang/main' of https://github.com/katanemo/arch into shuguang/main
2024-12-09 13:32:24 -08:00
CTran
9dd7f15eab
Cotran/integration ( #341 )
...
* add hallucination
* add test and fix bug
2024-12-09 13:30:52 -08:00
cotran
7bb6c8c750
add test and fix bug
2024-12-09 13:21:28 -08:00
Adil Hafeez
8f1b21124b
fix model_server cli and update version to 0.1.7
2024-12-09 12:11:17 -08:00
cotran
c12d63a109
working hallucination integration
2024-12-09 12:00:44 -08:00
Adil Hafeez
1299afd05c
add overrides module to model server
2024-12-09 11:52:57 -08:00
Adil Hafeez
0e22c3e7de
Merge branch 'main' into shuguang/main
2024-12-09 11:43:42 -08:00
cotran
423cfc0872
add hallucination
2024-12-09 11:33:41 -08:00
Shuguang Chen
1a3d33409b
Fix bugs
2024-12-09 11:19:09 -08:00
José Ulises Niño Rivera
cd1b561192
Break apart metrics into their own module ( #335 )
...
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
2024-12-09 10:46:46 -08:00
Shuguang Chen
e0d4ee7357
Update ArchFunctionHandler
2024-12-08 16:41:45 -08:00
Shuguang Chen
95e167c2f6
Refacotr model configs
2024-12-08 16:00:25 -08:00
Shuguang Chen
320f4612b8
Update cli and related utils
2024-12-08 11:16:34 -08:00
Shuguang Chen
b4f4695f16
Reorganize model_server
2024-12-08 09:21:53 -08:00
CTran
a40cdc7b75
Cotran/intent ( #339 )
...
* add else
* integrate hallucination
* remove test
2024-12-08 08:56:35 -08:00
José Ulises Niño Rivera
d002b2042a
Break apart common_types mod ( #334 )
...
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
2024-12-06 17:25:42 -08:00
Adil Hafeez
93d3d349a2
fix code bug ( #340 )
2024-12-06 17:20:59 -08:00
Adil Hafeez
af0e7d178b
update cli to 0.1.6 ( #338 )
2024-12-06 15:48:07 -08:00
Adil Hafeez
c186c3dfc0
update quick start rst to be in sync with readme.md ( #337 )
2024-12-06 15:15:26 -08:00
Adil Hafeez
a54db1a098
update getting started guide and add llm gateway and prompt gateway samples ( #330 )
2024-12-06 14:37:33 -08:00
Shuguang Chen
afec644789
Update the logic of intent detection
2024-12-06 14:14:44 -08:00
Shuguang Chen
79eafc0241
Update ArchBaseHandler
2024-12-06 14:07:01 -08:00
Aayush
9d8fe02729
fix the README for the weather_forecasting demo ( #336 )
...
* README fix
* add missing colon
2024-12-06 14:02:41 -08:00
Ikko Eltociear Ashimine
4e919613f1
docs: update README.md ( #332 )
...
minor fix
2024-12-06 13:44:33 -08:00
Aayush
885acc899f
322 add support for pydantic logfire for llm agent tracing ( #329 )
...
* set up otel-collector and implement sending to logfire
* moved rest of the files for the demo into the folder
* update docker-compose.yaml and run_demo.sh to properly check for LOGFIRE_API_KEY
* refactor weather_forecast demo to only be one demo
* add a default docker-compose for e2e tests
* update based on requested changes
* fix replace comma with colon in readme
* remove weather_forecast_service folder, and make logfire demo fail instantly if no key is set
* remove the unused weather forecast service folder
* Changed stop_demo to only stop one file at a time
* update readme with new demo stopping setup
* Revert changes to end behavior
* fix silly formatting mistake
2024-12-06 13:44:22 -08:00
Shuguang Chen
2fd8a5a06d
Update Arch-Guard and corresponding e2e test
2024-12-06 13:41:18 -08:00
Shuguang Chen
6dc92fbbc1
Add e2e test of function_calling endpoint
2024-12-06 11:54:01 -08:00
Shuguang Chen
818ec0a9db
Fix the issue of Arch-Intent
2024-12-06 11:53:46 -08:00
Shuguang Chen
4fcfd83639
Refine model_server
2024-12-05 15:19:41 -08:00
Shuguang Chen
a5bd005411
Fix a bug in function_calling.py
2024-12-05 12:06:56 -08:00
Shuguang Chen
09f7e1e604
Update guardrail_handler and its associated tests
2024-12-05 11:30:58 -08:00
Shuguang Chen
b686cf8b87
refactor model_handler
2024-12-05 11:00:22 -08:00
Shuguang Chen
afe1410b37
Init update on model_server
2024-12-04 16:41:30 -08:00
Shuguang Chen
1d9de28086
Update .gitignore
2024-12-02 15:12:33 -08:00
Salman Paracha
a0c159c9ba
updating doc versions, images and cleaning up section for prompt-guard ( #320 )
...
* updating doc versions, images and cleaning up section for prompt-guard
* updating based on feedback
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2024-12-01 23:02:08 -08:00
CTran
cadd3cdaf9
hallucination with log probs ( #281 )
...
* first init
* fix
* fix test
* new implemenetation
* fix bug
* fix bug
* fix bug
* address issue
* address issues
* address comments
* fix test
* fix
* move constatns
* remove consts
2024-11-27 15:17:02 -08:00
Peter Jausovec
f5cdafb7c8
update alertmanager version to v2, remove the merge artifacts ( #309 )
...
Signed-off-by: Peter Jausovec <peter.jausovec@solo.io>
2024-11-27 11:41:31 -08:00
Adil Hafeez
ec5326250e
correctly map stats port to host ( #311 )
2024-11-27 11:28:41 -08:00
Adil Hafeez
adec02e742
add note about hosted arch-fc ( #308 )
2024-11-26 14:19:10 -08:00
Adil Hafeez
704b928d61
release 0.1.5 ( #307 )
2024-11-26 13:28:52 -08:00
Adil Hafeez
0ff3d43008
remove dependency on docker-compose when starting up archgw ( #305 )
2024-11-26 13:13:02 -08:00
Adil Hafeez
726f1a3185
add schema change to use enum in arch_config ( #304 )
2024-11-25 17:51:25 -08:00
José Ulises Niño Rivera
be8c3c9ea3
Remove blanket unused imports from the common crate ( #292 )
...
* Remove blanket unused imports from the common crate
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
* updatE
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
---------
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
2024-11-25 17:19:06 -08:00
Adil Hafeez
9c6fcdb771
use fix prompt guards ( #303 )
2024-11-25 17:16:35 -08:00
Adil Hafeez
6f4a57b56d
update readme with python version ( #302 )
2024-11-25 16:01:40 -08:00
Salman Paracha
970db68575
updating readme and docs with note about Arch-Function ( #285 )
...
* updating readme and docs with note about Arch-Function
* minor fixes to README
* a few more minor updates to the README
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2024-11-19 08:43:56 -08:00
Adil Hafeez
33ab24292c
publish docker image on release only ( #284 )
2024-11-18 18:18:46 -08:00
Adil Hafeez
3d3d015aea
publish docker image ( #283 )
2024-11-18 17:55:47 -08:00
Adil Hafeez
36489b4adc
use envoy to publish traces ( #270 )
2024-11-18 17:55:39 -08:00
