Commit graph

1895 commits

Author SHA1 Message Date
Geoff-Robin
667bbd775e Added cron job and removed obvious comments 2025-10-06 04:12:32 +05:30
Geoff-Robin
4d5146c802 Added Documentation 2025-10-06 04:00:15 +05:30
Geoff-Robin
0f64f6804d Done adding cron job web scraping 2025-10-06 03:45:09 +05:30
Geoff-Robin
e5633bc368 corrected F402 error pointed out by ruff check 2025-10-06 03:44:24 +05:30
Geoff-Robin
f449fce0f1 Done with scraping_task successfully 2025-10-06 02:27:20 +05:30
Geoff-Robin
f148b1df89 Added support for multiple base_url extraction 2025-10-05 20:13:44 +05:30
Geoff-Robin
c2aa95521c removed structured argument 2025-10-05 20:00:19 +05:30
Geoff-Robin
2cba31a086 Tested and Debugged scraping usage in cognee.add() pipeline 2025-10-04 21:26:25 +05:30
Geoff-Robin
ab6fc65406 Added global context for bs4crawler and tavily config 2025-10-04 19:40:37 +05:30
Geoff-Robin
da7ebc4574 Removed asyncio import 2025-10-04 15:10:46 +05:30
Geoff-Robin
fbef6675bc removed unused Dict import from typing 2025-10-04 15:10:05 +05:30
Geoff-Robin
20fb77316c Done with integration with add workflow when incremental_loading is set to False 2025-10-04 15:01:13 +05:30
Geoff-Robin
1ab9d24cf0 Changed bs4_connector.py to bs4_crawler.py 2025-10-03 12:33:13 +05:30
Daulet Amirkhanov
38070c489b fix test_cli_edge_cases.py, test_delete_all_with_user_id unit test 2025-10-02 17:44:01 +01:00
Geoff-Robin
edd119ef97 first iteration of bs4_connector.py done 2025-10-02 22:04:50 +05:30
Daulet Amirkhanov
a92f4bdf3f fix: update failing tests and refactor delete_preview implementation 2025-10-02 15:05:39 +01:00
Daulet Amirkhanov
d5dd6c2fc2
Merge branch 'dev' into feature/delete-preview 2025-10-02 12:02:16 +01:00
Andrej Milicevic
a744f8d435 test: Rollback pgvector test. Was failing for some reason. 2025-10-02 09:54:30 +02:00
shehab-badawy
9c87a10848 feat: Add delete preview for --dataset-name and --all flags
This commit introduces the preview functionality for the  command. The preview displays a summary of what will be deleted before asking for user confirmation.

The feature is fully functional for the following flags:
-  / : Correctly counts the number of data entries within the specified dataset.
- : Correctly counts the total number of datasets, data entries, and users in the system.

The logic for the  flag is a work in progress. The current implementation uses a placeholder and needs a method to query a user directly by their ID to be completed.
2025-10-02 01:44:11 -04:00
Geoff-Robin
c283977035 switched httpx AsyncClient to fetch webpage 2025-10-02 02:01:46 +05:30
Geoff-Robin
60499c439c Added logging 2025-10-02 01:54:56 +05:30
Geoff-Robin
925bd38195 Setup models.py and utils.py 2025-10-02 01:32:00 +05:30
Andrej Milicevic
6f0756f312 test: Rollback deduplication test 2025-10-01 18:10:57 +02:00
Andrej Milicevic
5b46f86be5 test: Removed long text string about qunatum computers from tests. Used a file instead. 2025-10-01 17:59:53 +02:00
Daulet Amirkhanov
0bf3490d63 chore: update cognee-cli to use MCP Docker image from main. Bring back deprecation warnings 2025-10-01 16:16:06 +01:00
Igor Ilic
3dba072c49
fix: resolve formatting issue (#1486)
<!-- .github/pull_request_template.md -->

## Description
ruff formatting

## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [ ] **I have tested my changes thoroughly before submitting this PR**
- [ ] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-09-30 18:12:57 +02:00
Igor Ilic
7ab000d891 refactor: Add test for updating of docs and visualization 2025-09-30 18:12:22 +02:00
EricXiao
d868912df5
Merge branch 'dev' into feat/add-pdfproloader 2025-09-30 23:24:14 +08:00
Geoff-Robin
6348c9d8de Created models.py 2025-09-30 20:46:26 +05:30
Igor Ilic
f88289c425 fix: Resolve issue with processing for gpt4 series models 2025-09-30 14:05:12 +02:00
Andrej Milicevic
c8e6c1024b chore: Fix formatting. 2025-09-30 12:05:43 +02:00
Andrej Milicevic
e74ee55137 test: Add test to CI 2025-09-30 12:04:41 +02:00
Andrej Milicevic
0b5b0e5544 fix: PR comment changes 2025-09-30 11:40:42 +02:00
EricXiao
4938ad9fe9 Merge branch 'dev' into feat/add-pdfproloader
Signed-off-by: EricXiao <taoiaox@gmail.com>
2025-09-30 17:08:28 +08:00
Igor Ilic
74bc7c9420 refactor: set node_set to None for endpoint 2025-09-29 21:22:21 +02:00
Vasilije
52265a67f2
Merge branch 'dev' into feature/windows-compatibility-fixes 2025-09-29 20:51:17 +02:00
Igor Ilic
9524109029 Merge branch 'dev' into update-endpoint 2025-09-29 20:44:44 +02:00
Igor Ilic
3c7cc597e3 Merge branch 'update-endpoint' of github.com:topoteretes/cognee into update-endpoint 2025-09-29 20:42:42 +02:00
Igor Ilic
e333a860ba refactor: Add documentation for update endpoint 2025-09-29 20:42:25 +02:00
Igor Ilic
52c978faeb
docs: Multi user authorization example (#1466)
<!-- .github/pull_request_template.md -->

## Description
Add return value of creating role and tenant, add detailed permissions
example to Cognee

## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [x] **I have tested my changes thoroughly before submitting this PR**
- [x] **This PR contains minimal changes necessary to address the
issue/feature**
- [x] My code follows the project's coding standards and style
guidelines
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] I have added necessary documentation (if applicable)
- [x] All new and existing tests pass
- [x] I have searched existing PRs to ensure this change hasn't been
submitted already
- [x] I have linked any relevant issues in the description
- [x] My commits have clear and descriptive messages

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Co-authored-by: Boris <boris@topoteretes.com>
Co-authored-by: Hande <159312713+hande-k@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
2025-09-29 20:15:50 +02:00
Andrej Milicevic
d352807a9d fix: Fix docling import so other executions don't fail 2025-09-29 17:57:58 +02:00
Igor Ilic
213bab5307
Merge branch 'dev' into fix-gpt-5-series 2025-09-29 17:57:38 +02:00
Andrej Milicevic
8ef3bf6393 feat: Add Docling as an ingestion option to cognee add. 2025-09-29 17:32:25 +02:00
Igor Ilic
6bc5c6f162 refactor: Use latest JSON tool type for structured outputs 2025-09-29 17:06:01 +02:00
Igor Ilic
bd4a605849
Merge branch 'dev' into update-endpoint 2025-09-29 14:53:02 +02:00
Igor Ilic
4c8e3b8bb3 refactor: Add docstring to update function 2025-09-29 14:40:41 +02:00
Igor Ilic
f2e216cdf7 fix: Resolve issues with GPT5 models 2025-09-29 14:11:06 +02:00
Igor Ilic
db39a43975
fix: Resolve schema migration for Neo4j (#1482)
<!-- .github/pull_request_template.md -->

## Description
Fix Neo4j issue with migrating DB schema

## Type of Change
<!-- Please check the relevant option -->
- [x] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [x] **I have tested my changes thoroughly before submitting this PR**
- [x] **This PR contains minimal changes necessary to address the
issue/feature**
- [x] My code follows the project's coding standards and style
guidelines
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] I have added necessary documentation (if applicable)
- [x] All new and existing tests pass
- [x] I have searched existing PRs to ensure this change hasn't been
submitted already
- [x] I have linked any relevant issues in the description
- [x] My commits have clear and descriptive messages

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-09-29 13:50:11 +02:00
Igor Ilic
240925c5d4
Merge branch 'dev' into feature/cog-2837-rework-limit0-for-vector-adapters 2025-09-29 10:41:50 +02:00
Aniruddha Mandal
3b57a3fcfe Merge branch 'dev' into feature/mistral_llm_provider 2025-09-29 13:08:08 +05:30