LLM/DocsGPT
1
0
Fork 0
mirror of https://github.com/arc53/DocsGPT.git synced 2026-05-08 15:04:04 +00:00
Code Issues Packages Projects Releases Wiki Activity
4,465 Commits 48 Branches 20 Tags
6fa3acb1caaca0ff15cdbbb91b0d4c4e761414b9
Commit Graph

117 Commits

Author SHA1 Message Date
Alex
21996af626 stt init (#2306) 
* stt init

* fix: limits

* fix: errors

* fix: error messages
 2026-03-17 14:27:48 +00:00
Manish Madan
918bbf0369 Sharepoint (#2283) 
* feat: add Microsoft Entra ID integration

- Updated .env-template and settings.py for Microsoft Entra ID configuration.
- Enhanced ConnectorsCallback to support SharePoint authentication.
- Introduced SharePointAuth and SharePointLoader classes.
- Added required dependencies in requirements.txt.

* feat: agent templates and seeding premade agents (#1910)

* feat: agent templates and seeding premade agents

* fix: ensure ObjectId is used for source reference in agent configuration

* fix: improve source handling in DatabaseSeeder and update tool config processing

* feat: add prompt handling in DatabaseSeeder for agent configuration

* Docs premade agents

* link to prescraped docs

* feat: add template agent retrieval and adopt agent functionality

* feat: simplify agent descriptions in premade_agents.yaml  added docs

---------

Co-authored-by: Pavel <pabin@yandex.ru>
Co-authored-by: Alex <a@tushynski.me>

* feat: add GitHub access token support and fix file content fetching logic (#2032)

* feat: add init for Share Point connector module

* chore(deps): bump mermaid from 11.6.0 to 11.12.0 in /frontend

Bumps [mermaid](https://github.com/mermaid-js/mermaid) from 11.6.0 to 11.12.0.
- [Release notes](https://github.com/mermaid-js/mermaid/releases)
- [Commits](https://github.com/mermaid-js/mermaid/compare/mermaid@11.6.0...mermaid@11.12.0)

---
updated-dependencies:
- dependency-name: mermaid
  dependency-version: 11.12.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

* Feat: Notification section (#2033)

* Feature/Notification-section

* fix notification ui and add local storage variable to save the state

* add notification component to app.tsx

* refactor: remove MICROSOFT_REDIRECT_URI and update SharePointAuth to use CONNECTOR_REDIRECT_BASE_URI

* feat: Add button to cancel LLM response (#1978)

* feat: Add button to cancel LLM response
- Replace text area with cancel button when loading.
- Add useEffect to change elipsis in cancel button text.
- Add new SVG icon for cancel response.
- Button colors match Figma designs.

* fix: Cancel button UI matches new design
- Delete cancel-response svg.
- Change previous cancel button to match the new Figma design.
- Remove console log in handleCancel function.

* fix: Adjust cancel button rounding

* feat: Update UI for send button
- Add SendArrowIcon component, enables dynamic svg color changes
- Replace original icon
- Update colors and hover effects

* (fix:send-button) minor blink in transition

---------

Co-authored-by: Manish Madan <manishmadan321@gmail.com>

* feat: add SharePoint integration with session validation and UI components

* (feat:oneDrive) file loading for ingestion

* feat(oneDrive): shared user files

* (feat:oneDrive) rm shared file support, as sharedWithMe is degraded

* (feat:sharepoint) shared files for work msa

* (feat:sharepoint) retry on auth failure, decorator

* (fix) tests/ruff

* test: fix sharepoint loader expecting client id

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Abhishek Malviya <abfeb8@gmail.com>
Co-authored-by: Siddhant Rai <47355538+siiddhantt@users.noreply.github.com>
Co-authored-by: Pavel <pabin@yandex.ru>
Co-authored-by: Alex <a@tushynski.me>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Mariam Saeed <69825646+Mariam-Saeed@users.noreply.github.com>
Co-authored-by: Rahul <rahulgithub96@gmail.com>
 2026-03-12 14:46:26 +00:00
Alex
f61d112cea feat: process pdfs synthetically im model does not support file natively (#2263) 
* feat: process pdfs synthetically im model does not support file natively

* fix: small code optimisations
 2026-01-15 02:30:33 +02:00
Alex
2c55c6cd9a fix: tiktoken import in markdown parser 2026-01-12 23:04:20 +00:00
Alex
df57053613 feat: improve crawlers and update chunk filtering (#2250) 2026-01-06 00:52:12 +02:00
Alex
05c835ed02 feat: enable OCR for docling when parsing attachments and update file extractor (#2246) 2025-12-31 02:08:49 +02:00
Alex
9e7f1ad1c0 Add Amazon S3 support and synchronization features (#2244) 
* Add Amazon S3 support and synchronization features

* refactor: remove unused variable in load_data test
 2025-12-30 20:26:51 +02:00
Alex
aef3e0b4bb chore: update workflow permissions and fix paths in settings (#2227) 
* chore: update workflow permissions and fix paths in settings

* dep

* dep upgraes
 2025-12-25 14:26:01 +02:00
Alex
98e949d2fd Patches (#2218) 
* feat: implement URL validation to prevent SSRF

* feat: add zip extraction security

* ruff fixes
 2025-12-24 17:05:35 +02:00
Alex
ccd29b7d4e feat: implement Docling parsers (#2202) 
* feat: implement Docling parsers

* fix office

* docling-ocr-fix

* Docling smart ocr

* ruff fix

---------

Co-authored-by: Pavel <pabin@yandex.ru>
 2025-12-23 18:33:51 +02:00
Alex
e0a9f08632 refactor and deps (#2184) 2025-12-10 23:53:59 +02:00
Harshit Ranjan
695191d888 added error saving vector store (#2081) 
* added error saving vector store

* fixed code formating

* added tests for embedding pipeline
 2025-10-31 16:29:35 +02:00
Alex
03452ffd9f feat: add GitHub access token support and fix file content fetching logic (#2032) 2025-10-07 16:53:14 +03:00
ManishMadan2882
2d0e97b66d (feat:oauth) provider as state, not args 2025-09-25 04:55:25 +05:30
ManishMadan2882
d317f6473d (feat:gdrive) upload files only 2025-09-22 20:19:56 +05:30
ManishMadan2882
da2f8477e6 (feat:drive) oauth for drive.file scope, picker 2025-09-17 19:37:01 +05:30
ManishMadan2882
7896526f19 (feat:load_files) search feature 2025-09-05 10:35:23 +05:30
ManishMadan2882
f7f6042579 (feat:connector) paginate files 2025-09-04 07:58:12 +05:30
ManishMadan2882
7e2cbdd88c (feat:connector) redirect url as backend overhead 2025-09-03 09:57:13 +05:30
ManishMadan2882
f9b2c95695 (feat:connector) sync, simply re-ingest 2025-09-02 18:06:04 +05:30
ManishMadan2882
384ad3e0ac (feat:connector) raw sync flow 2025-09-02 13:34:31 +05:30
ManishMadan2882
f39ac9945f (feat:auth) follow connector-session 2025-08-28 00:53:19 +05:30
GH Action - Upstream Sync
f08067a161 Merge branch 'main' of https://github.com/arc53/DocsGPT 2025-08-27 01:36:38 +00:00
Alex
545caacfa3 feat: prevent NUL character ingestion failures 2025-08-26 23:30:57 +01:00
ManishMadan2882
578c68205a (feat:connectors) abstracting auth, base class 2025-08-26 02:46:36 +05:30
ManishMadan2882
f09f1433a9 (feat:connectors) separate layer 2025-08-26 01:38:36 +05:30
ManishMadan2882
2410bd8654 (fix:driveLoader) folder ingesting 2025-08-22 19:07:52 +05:30
ManishMadan2882
92d6ae54c3 (fix:google-oauth) no explicit datetime compare 2025-08-22 13:35:03 +05:30
ManishMadan2882
8c3f75e3e2 (feat:ingestion) google drive loader 2025-08-22 13:32:40 +05:30
ManishMadan2882
b2b04268e9 (feat:drive) oauth flow 2025-08-21 02:46:32 +05:30
GH Action - Upstream Sync
9903fad1e9 Merge branch 'main' of https://github.com/arc53/DocsGPT 2025-08-07 01:55:18 +00:00
Alex
9281fac898 fix: improve error logging for index creation and add PARSE_IMAGE_REMOTE setting 2025-08-06 10:40:20 +01:00
ManishMadan2882
ba260e3382 (fix:faiss) not save tmp dir 2025-08-06 02:53:39 +05:30
ManishMadan2882
1356d71839 (lint) ruff fix 2025-08-05 15:37:39 +05:30
ManishMadan2882
a61e44d175 (feat:dir_tree) improvement 2025-08-02 01:48:43 +05:30
ManishMadan2882
c92d778894 (feat:chunker) do not combine text 2025-07-31 02:13:55 +05:30
ManishMadan2882
bbce872ac5 (fix:chunker) combine metadata as well 2025-07-04 02:19:58 +05:30
ManishMadan2882
0f7ebcd8e4 (feat:dir-reader) store mime types, file size in db 2025-07-03 18:09:19 +05:30
ManishMadan2882
82fc19e7b7 (fix:dir-reader) conflict of same filename in dir 2025-07-03 17:28:12 +05:30
ManishMadan2882
2ef23fe1b3 (feat:dir-reader) maintain dir structure in db 2025-07-03 01:24:22 +05:30
ManishMadan2882
fd905b1a06 (feat:dir-reader) save tokens with filenames 2025-07-02 16:30:29 +05:30
ManishMadan2882
e1aa2cc0b8 (fix:ingestion) store file name as metadata, not path 2025-05-09 02:26:35 +05:30
Alex
481df4d604 fix: enhance error logging with exception info across multiple modules 2025-05-05 13:12:39 +01:00
Pavel
57a6fb31b2 periodic header injection 2025-03-31 22:28:04 +04:00
asminkarki012
c70be12bfd fix[csv_parser]:missing header 2025-03-28 22:46:11 +05:45
Alex
d47232246a fix: remove old pypdf 2025-02-06 19:59:42 +00:00
Pavel
fddee69f92 web loader fix 
Changes web loader to the correct output.
 2025-01-17 19:13:23 +03:00
Pavel
13fcbe3e74 scraper with markdownify 2025-01-15 01:08:09 +03:00
Alex
41b4c28430 fix: linting 2024-12-23 17:41:44 +00:00
Pavel
b41a989051 test version 2024-12-23 16:59:27 +00:00