Commit Graph

116 Commits

Author SHA1 Message Date
4b45164496 Background Index Attempt Creation (#1010) 2024-01-28 23:14:20 -08:00
bcc40224fa Embed Dim Env Var (#988) 2024-01-23 19:32:51 -08:00
f5be0cc2c0 Tiny Mail From Fix (#953) 2024-01-15 22:03:38 -08:00
621967d2b6 Add MAIL_FROM env variable (#949)
Co-authored-by: Roman Tyshyk <roman.tyshyk@711media.de>
2024-01-15 21:53:03 -08:00
44905d36e5 Slack Rate Limit Options (#952) 2024-01-15 21:47:24 -08:00
cf4c3c57ed Log size limit to prevent more disk usage (#941) 2024-01-13 15:22:01 -08:00
0056cdcf44 GitHub Base URL (#922) 2024-01-09 22:31:07 -08:00
e473ad0412 Go back to localhost:3000 2024-01-08 15:35:52 -08:00
a29c1ff05c Change WEB_DOMAIN default to 127.0.0.1 instead of localhost (#901)
Got it, thanks for the contribution! Neither of us (maintainers) use Windows so we weren't aware of this. Thanks a bunch for pointing it out and fixing it!
2024-01-05 23:50:57 -08:00
6b6b3daab7 Reenable option to run Danswer without Gen AI (#906) 2024-01-03 18:31:16 -08:00
2e6be57880 Model Server CVEs (#898) 2023-12-29 21:14:08 -08:00
b352d83b8c Increase max upload size 2023-12-29 21:11:57 -08:00
dab3ba8a41 Add support for basic auth on FE 2023-12-25 21:19:59 -08:00
016a087b10 Refactor environment variable handling using ConfigMap for Kubernetes deployment (#515)
---------

Co-authored-by: Reese Jenner <reesevader@hotmail.co.uk>
Co-authored-by: Yuhong Sun <yuhongsun96@gmail.com>
2023-12-22 21:33:36 -08:00
6650f01dc6 Multilingual Docs Updates (#856) 2023-12-22 00:26:00 -08:00
56406a0b53 Bump Vespa to 8.277.17 (#851) 2023-12-21 17:23:27 -08:00
eb31c08461 Update Vespa to 8.267.29 (#812) 2023-12-21 17:18:16 -08:00
2180a40bd3 Disable Chain of Thought for now (#837) 2023-12-18 21:44:47 -08:00
5957b888a5 DanswerBot Chat (#831) 2023-12-17 18:18:48 -08:00
65fde8f1b3 Chat Backend (#801) 2023-12-14 22:14:37 -08:00
e3ac373f05 Make Default Fast LLM not identical to main LLM (#818) 2023-12-06 16:14:04 -08:00
9e9a578921 Option to speed up DanswerBot by turning off chain of thought (#816) 2023-12-05 00:43:45 -08:00
c2727a3f19 Custom OpenAI Model Server (#782) 2023-11-29 01:41:56 -08:00
d291fea020 Turn off Reranking for Streaming Flows (#770) 2023-11-26 16:45:23 -08:00
65d38ac8c3 Slack to respect LLM chunk filter settings (#768) 2023-11-26 01:06:12 -08:00
ac2ed31726 Indexing Jobs to have shorter lived DB sessions (#766) 2023-11-24 21:38:16 -08:00
a5729e2fa6 Add new model server env vars to the compose file 2023-11-24 00:12:04 -08:00
1225c663eb Add new env variable to compose file 2023-11-20 21:40:54 -08:00
8e5e11a554 Add md files to File Connector (#749) 2023-11-20 19:56:06 -08:00
68160d49dd Small mods to enable deployment on AWS EKS 2023-11-20 01:42:48 -08:00
0cc3d65839 Add option to run a faster/cheaper LLM for secondary flows (#742) 2023-11-19 17:48:42 -08:00
6fb07d20cc Multilingual Query Expansion (#737) 2023-11-19 10:55:55 -08:00
fa0d19cc8c LLM Chunk Filtering (#735) 2023-11-18 17:12:24 -08:00
37c5f24d91 Fix logout redirect 2023-11-17 16:43:24 -08:00
be5ef77896 Optional Anonymous Telemetry (#727) 2023-11-16 09:22:36 -08:00
0a0e672b35 Fix no letsencrypt 2023-11-13 14:32:51 -08:00
69644b266e Hybrid Search Alpha Parameter (#714) 2023-11-09 17:11:10 -08:00
0125d8a0f6 Source Filter Extraction (#708) 2023-11-07 14:21:04 -08:00
f5bf2e6374 Fix experimental checkpointing + move check for disabled connector to the start of the batch (#703) 2023-11-06 17:14:31 -08:00
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
927dffecb5 Prompt Layer Rework (#688) 2023-11-02 23:26:47 -07:00
80eedebe86 Add env variables to dev docker compose file 2023-11-01 22:00:32 -07:00
fbf7c642a3 Reworking the LLM layer (#666) 2023-10-31 18:22:42 -07:00
c6663d83d5 Fix nginx conf in docker-compose.prod 2023-10-31 08:50:52 -07:00
64ebaf2dda Pin Vespa Version (#651) 2023-10-29 14:30:33 -07:00
ad6ea1679a Sleep for a little before starting nginx 2023-10-27 16:40:33 -07:00
7bc34ce182 Fix Container Name (#633) 2023-10-25 23:22:24 -07:00
604e511c09 Alternative solution to up the number of threads for torch (#632) 2023-10-25 22:30:57 -07:00
a8b7155b5e Add support for non-letsencrypt-based https in docker compose setup (#628) 2023-10-25 20:35:47 -07:00
9a51745fc9 Updated Contributing for Celery (#629) 2023-10-25 18:26:02 -07:00