454 Commits

Author SHA1 Message Date
Weves
54ee323e59 Fix duplicate documents with Slack connector v0.1.3 2023-08-10 10:54:12 -07:00
Yuhong Sun
a03818e6f6
Fix Google Colab Demo (#275) 2023-08-09 01:35:48 -07:00
Chris Weaver
89f71ac335
Support deletion of documents when a connector is deleted (#271) 2023-08-09 00:53:42 -07:00
Yuhong Sun
b6dec6dcdb
Standardize model config naming (#274) 2023-08-08 00:18:13 -07:00
Yuhong Sun
02c3139bc9
Add Request Model Class for Google Colab Demo (#273)
Need to add the blog links later
2023-08-08 00:09:11 -07:00
Sid Ravinutala
ca72027b28
Allow slack channels to be specified (#238)
Adds the capability to specify specific channels to index when using the Slack connector
2023-08-07 22:09:27 -07:00
Yuhong Sun
3bfc72484d
Support for Request accessed GenAI Models (#270) 2023-08-06 18:31:47 -07:00
Pratik Kabra
0e667d3384
Huggingface Inference backend internal models (#265) 2023-08-05 11:33:19 -07:00
Weves
df62648bbf Increase timeout for answer generation for slack bot 2023-08-04 18:14:52 -07:00
Weves
70a379b601 Set OAuth type to google by default v0.1.2 2023-08-01 11:03:13 -07:00
Chris Weaver
132a9f750d
Add Github Action to run mypy / reorder-python-imports / black on all PRs (#251)
Also fixes import ordering (previously, local imports weren't grouped together as they should have been)
2023-07-29 16:53:38 -07:00
Yuhong Sun
87fe6f7575
Add ingestion metrics (#256) 2023-07-29 16:37:22 -07:00
Yuhong Sun
eec4e21bad
Update README.md 2023-07-29 14:16:54 -07:00
Yuhong Sun
fe40e72b5c
Require Semantic Identifier to not be None (#255) 2023-07-29 14:12:30 -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
jabdoa2
878d4e367f
prevent crash when semantic_identifier is None (#201)
This is a workaround around intermittent issues where sementic_identifier becomes None for some reason. It usually recovers when documents are rescraped.

Obviously, we do not yet understand the issue and are interested in a better solution.
2023-07-29 12:37:02 -07:00
Yuhong Sun
17e2008027
Add TODOs and minor style changes to web connector (#254) 2023-07-29 12:35:38 -07:00
jabdoa2
0d7d54fddb
Improve Web Connector Output, Add Config Options and add OAuth Backend Flow (#199) 2023-07-29 12:21:23 -07:00
cqian-github
b6b549357f
Update Contributing.md with Windows Commands (#252)
Co-authored-by: AD\cqian <cqian@ucsd.edu>
2023-07-28 19:03:25 -07:00
Chris Weaver
3e8f5fa47e
Fix a few bugs with Google Drive polling (#250)
- Adds some offset to the `start` for the Google Drive connector to give time for `modifiedTime` to propagate so we don't miss updates
- Moves fetching folders into a separate call since folder `modifiedTime` doesn't get updated when a file in the folder is updated
- Uses `connector_credential_pair.last_successful_index_time` instead of `updated_at` to determine the `start` for poll connectors
2023-07-28 18:27:32 -07:00
lokeshwar lakhineni
62afbcb178
added shell command for windows (#194) 2023-07-28 18:02:27 -07:00
Yuhong Sun
55adde5e27
Fix import location and mypy issue (#249) 2023-07-28 16:06:25 -07:00
Yuhong Sun
2a339ec34b
Prevent too many tokens to GPT (#245) 2023-07-28 16:00:26 -07:00
Weves
d53ce3bda1 Fix arg to GuruIcon 2023-07-28 14:37:43 -07:00
Yuhong Sun
d03ac44744
Guru Connector (#177)
Co-authored-by: Weves <chrisweaver101@gmail.com>
2023-07-28 14:27:02 -07:00
Weves
555f8bbf08 Allow shared files for drive connector 2023-07-27 17:20:34 -07:00
Yuhong Sun
4d0732395d
Standalone Script to Test OpenAI API Key (#243) 2023-07-27 16:33:04 -07:00
Yuhong Sun
2a0d3b38e9
Google Drive Connector Debug Logging (#241) 2023-07-27 09:27:57 -07:00
Chris Weaver
3b546ba1c3
Make Google Drive connectors editable (#237) 2023-07-26 22:20:12 -07:00
Weves
9e6467a0c9 Fix specifying folders for Google Drive connector 2023-07-26 21:39:31 -07:00
meherhendi
1a22666810
Adding vscode run & debug config (#216)
Also adds `.env` to `.gitignore` files outside of the `deployment` dir
2023-07-26 12:35:31 -07:00
Weves
d5f172c292 Handle google drive connectors without folder_path 2023-07-26 12:15:06 -07:00
Yuhong Sun
273802eff0
Disable Gpt4all due to mac not supporting it currently (#233) 2023-07-25 22:19:15 -07:00
Yuhong Sun
e019db0bc7
Indexing Job has timezone discrepancy with DB making Poll timeframes incorrect (#231) 2023-07-23 21:59:00 -07:00
Yuhong Sun
59f27e83bf
Merge pull request #227 from IDinsight/docx-googledrive
Added support for docx in Google Drive
2023-07-23 21:33:41 -07:00
Sid Ravinutala
d6d3d5291b added docx2txt 2023-07-24 01:42:39 +00:00
Sid Ravinutala
a4b47e0243 added support for docx in gdrive
rebase from main
2023-07-24 01:41:35 +00:00
Yuhong Sun
d6ca865034
Support GPT4All in memory (#230) 2023-07-23 12:26:14 -07:00
Weves
6684f1e5d5 Use approved icon colors 2023-07-22 19:22:05 -07:00
Chris Weaver
dd084d40f6
Product board connector (#228)
Also fixes misc mypy issues across the repo
2023-07-22 13:00:51 -07:00
Yuhong Sun
25a028c4a7
Merge pull request #195 from pkabra/notion-connector
Notion connector
2023-07-21 00:04:12 -07:00
Pratik Kabra
b33c8b1d7c Reorg public-private functions 2023-07-20 18:04:48 -05:00
Pratik Kabra
610fe6ebc4 Prettier fixes for web 2023-07-20 18:02:41 -05:00
Pratik Kabra
7ad98480be Black fixes for python files 2023-07-20 18:01:23 -05:00
Pratik Kabra
ab3bb13493 Fix notion titles missing in some cases 2023-07-20 17:58:09 -05:00
Yuhong Sun
0708002953
Check for Credential delete before running queued index attempt (#221) 2023-07-19 23:52:48 -07:00
Yuhong Sun
191c166ab6
Merge pull request #200 from jabdoa2/do_not_crash_when_deleting_source
catch crash when deleting a datasource
2023-07-19 23:46:14 -07:00
Chris Weaver
4958962855
Merge pull request #208 from chrisedington/ce/slack-archive-fix
Fix: Don't include archived Slack channels
2023-07-19 21:47:25 -07:00
Yuhong Sun
c41421ccf4
Add model caching to docker compose prod (#219) 2023-07-19 20:01:23 -07:00
Yuhong Sun
aed88e8b9e
Merge pull request #198 from jabdoa2/cache_models_for_development
cache models for faster development cycles in docker compose
2023-07-19 19:57:06 -07:00