Yuhong Sun
fa0d19cc8c
LLM Chunk Filtering ( #735 )
2023-11-18 17:12:24 -08:00
Weves
37c5f24d91
Fix logout redirect
2023-11-17 16:43:24 -08:00
Yuhong Sun
be5ef77896
Optional Anonymous Telemetry ( #727 )
2023-11-16 09:22:36 -08:00
Weves
0a0e672b35
Fix no letsencrypt
2023-11-13 14:32:51 -08:00
Yuhong Sun
69644b266e
Hybrid Search Alpha Parameter ( #714 )
2023-11-09 17:11:10 -08:00
Yuhong Sun
0125d8a0f6
Source Filter Extraction ( #708 )
2023-11-07 14:21:04 -08:00
Chris Weaver
f5bf2e6374
Fix experimental checkpointing + move check for disabled connector to the start of the batch ( #703 )
2023-11-06 17:14:31 -08:00
Yuhong Sun
7433dddac3
Model Server ( #695 )
...
Provides the ability to pull out the NLP models into a separate model server which can then be hosted on a GPU instance if desired.
2023-11-06 16:36:09 -08:00
Yuhong Sun
927dffecb5
Prompt Layer Rework ( #688 )
2023-11-02 23:26:47 -07:00
Weves
80eedebe86
Add env variables to dev docker compose file
2023-11-01 22:00:32 -07:00
Yuhong Sun
fbf7c642a3
Reworking the LLM layer ( #666 )
2023-10-31 18:22:42 -07:00
Sam Jakos
c6663d83d5
Fix nginx conf in docker-compose.prod
2023-10-31 08:50:52 -07:00
Yuhong Sun
64ebaf2dda
Pin Vespa Version ( #651 )
2023-10-29 14:30:33 -07:00
Weves
ad6ea1679a
Sleep for a little before starting nginx
2023-10-27 16:40:33 -07:00
Yuhong Sun
7bc34ce182
Fix Container Name ( #633 )
2023-10-25 23:22:24 -07:00
Yuhong Sun
604e511c09
Alternative solution to up the number of threads for torch ( #632 )
2023-10-25 22:30:57 -07:00
Chris Weaver
a8b7155b5e
Add support for non-letsencrypt-based https in docker compose setup ( #628 )
2023-10-25 20:35:47 -07:00
Yuhong Sun
9a51745fc9
Updated Contributing for Celery ( #629 )
2023-10-25 18:26:02 -07:00
Chris Weaver
ef2b445201
Support Confluence data center + allow for specifying labels to ignore ( #624 )
2023-10-24 17:40:42 -07:00
Yuhong Sun
e279918f95
Introduce Time Filters ( #610 )
2023-10-22 15:06:52 -07:00
Yuhong Sun
6a449f1fb1
Introduce Recency Bias ( #592 )
2023-10-19 12:54:35 -07:00
Yuhong Sun
e73739547a
Fix Kubernetes Templates ( #584 )
2023-10-17 13:32:00 -07:00
Chris Weaver
e519dfc849
Torch more cpus ( #583 )
2023-10-17 09:53:20 -07:00
Weves
d2f7dff464
Add max upload size to HTTPS NGINX listener
2023-10-15 12:52:13 -07:00
Yuhong Sun
31d5fc6d31
Officially support Slack DMs to DanswerBot ( #556 )
2023-10-10 18:07:29 -07:00
Weves
5deb12523e
Allow large file uploads
2023-10-10 09:11:07 -07:00
Yuhong Sun
744c95e1e1
Remove Stopword Highlighting ( #546 )
2023-10-09 18:54:40 -07:00
Yuhong Sun
09ba0a49b3
Default not respond to every channel( #527 )
2023-10-06 14:54:34 -07:00
Weves
5a63b689eb
Add DANSWER_BOT_ONLY_ANSWER_WHEN_SLACK_BOT_CONFIG_IS_PRESENT to dev compose
2023-10-05 11:52:31 -07:00
Weves
732f5efb12
Fix AUTH_TYPE env variable bug on frontend
2023-10-03 17:35:50 -07:00
Yuhong Sun
351475de28
Consolidate versions for easier extension ( #495 )
2023-10-01 23:49:38 -07:00
Weves
c4e4e88301
Add NOTION_CONNECTOR_ENABLE_RECURSIVE_PAGE_LOOKUP to the .dev deployment setup
2023-09-25 23:21:41 -07:00
Yuhong Sun
8b95e2631d
Make Cross Encoders Optional ( #476 )
2023-09-23 17:17:54 -07:00
Andrea Nassi
0e65688166
Change max upload size setting ( #410 )
...
---------
Co-authored-by: Gabriele Capitani <gabrielecapitani2005@gmail.com>
2023-09-09 17:01:44 -07:00
Chris Weaver
b06e53a51e
Feed in docs till we reach a token limit ( #401 )
2023-09-05 15:20:42 -07:00
Chris Weaver
0fcac74df1
Add WEB_DOMAIN env variable to dev compose file ( #395 )
2023-09-04 10:43:06 -07:00
Weves
faa73b3088
Add env variables for slack bot to .dev compose file
2023-08-30 17:43:02 -07:00
Weves
cea3e1f3d5
Add support for multiple allowed email domains + make slack bot logs go to stdout
2023-08-30 13:47:46 -07:00
Yuhong Sun
a2ec1e2cda
Vespa Deployment ( #330 )
...
Large Change!
2023-08-26 15:35:19 -07:00
Chris Weaver
e307275774
Add support for multiple indexing workers ( #322 )
2023-08-22 18:11:31 -07:00
Chris Weaver
f541a3ee85
Continue on some connector failures ( #314 )
2023-08-18 17:59:33 -07:00
Weves
78b49f546c
Make LOG_LEVEL work for .dev docker compose deployment
2023-08-15 16:19:03 -07:00
Yuhong Sun
b73d19f35f
Fix Azure OpenAI Docker Deployment ( #302 )
2023-08-15 01:06:23 -07:00
Yuhong Sun
59db40cf36
Add Azure OpenAI parameters to background job for Slackbot ( #294 )
2023-08-14 14:37:02 -07:00
Matthew Holland
204d89a148
Azure OpenAI integration ( #293 )
2023-08-14 14:30:44 -07:00
James Choncholas
758015baa5
Allow setting QA_TIMEOUT from env var ( #258 )
...
Co-authored-by: Yuhong Sun <yuhongsun96@gmail.com>
2023-08-13 10:37:32 -07:00
Yuhong Sun
3bfc72484d
Support for Request accessed GenAI Models ( #270 )
2023-08-06 18:31:47 -07:00
Weves
70a379b601
Set OAuth type to google by default
2023-08-01 11:03:13 -07:00
jabdoa2
63780113d3
Add support for openid connect ( #206 )
...
This allow using Danswer in typical (non-google) enterprise environments.
* Access Tokens can be very large. A token without claims is already 1100 bytes for me (larger than allowed in danswer by default). With roles I got a 12kB token. For that reason I changed the field to TEXT in the database.
* Danswer used to swallow most errors when OIDC would fail. Nodejs forwards a request to the backend and swallows all errors. Even within the backend we catched all ValueErrors and only returned the last exception with the request. Added full stack trace logging to allow debugging issues with userinfo and other endpoints.
* Allow changing name of the login provider on the login button.
* Changed variables and URLs to generic OAUTH_XX (without google in the name) but kept compatibility with the existing google integration
* Tested again Keycloak with OpenID Connect
Next steps:
* Claim to role mappings
* Auto login/SSO (Login button is just an extra click)
2023-07-29 14:04:32 -07:00
Yuhong Sun
273802eff0
Disable Gpt4all due to mac not supporting it currently ( #233 )
2023-07-25 22:19:15 -07:00
