Commit graph

2142 commits

Author SHA1 Message Date
Igor Ilic
6a7d8ba106
Merge branch 'dev' into multi-tenancy 2025-11-05 12:17:49 +01:00
hajdul88
eaf8d718b0
feat: introduces memify pipeline to save cache sessions into cognee (#1731)
<!-- .github/pull_request_template.md -->

## Description
This PR introduces a new memify pipeline to save cache sessions in
cognee. The QA sessions are added to the main knowledge base as separate
documents.


## 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):

## Screenshots/Videos (if applicable)
None

## 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.
2025-11-05 10:27:54 +01:00
Igor Ilic
c2aaec2a82 refactor: Resolve issue with permissions example 2025-11-04 23:34:51 +01:00
Igor Ilic
7782f246d3 refactor: Update permissions example to work with new changes 2025-11-04 20:54:00 +01:00
Igor Ilic
f002d3bf0e refactor: Update permissions example 2025-11-04 20:24:16 +01:00
Igor Ilic
a6487cfdc1
Merge branch 'dev' into multi-tenancy 2025-11-04 18:01:19 +01:00
Igor Ilic
bee2fe3ba7
feat: Add initial custom pipeline (#1716)
<!-- .github/pull_request_template.md -->

## Description
Add run_custom_pipeline to have a way to execute a custom collection of tasks in Cognee

## 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.
2025-11-04 17:58:34 +01:00
Igor Ilic
cd32b492a4 refactor: Add filtering of non current tenant results when authorizing dataset 2025-11-04 17:56:01 +01:00
Igor Ilic
f4117c42e9 fix: Resolve issue with entity extraction test 2025-11-04 16:43:41 +01:00
Igor Ilic
69ee8ae0a9 Merge branch 'multi-tenancy' of github.com:topoteretes/cognee into multi-tenancy 2025-11-04 16:42:55 +01:00
Igor Ilic
64c7b857d6
Merge branch 'dev' into multi-tenancy 2025-11-04 16:42:51 +01:00
Igor Ilic
9d771acc24 refactor: filter out search results 2025-11-04 13:35:50 +01:00
Vasilije
0ef2d51246
fix: Add logs to docker (#1656)
<!-- .github/pull_request_template.md -->

## Description
Adds detailed logging to docker

## 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):

## 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.
2025-11-04 13:31:00 +01:00
Igor Ilic
ea675f29d6 fix: Resolve typo in accessing dictionary for dataset_id 2025-11-04 13:15:49 +01:00
Igor Ilic
ac257dca1d refactor: Account for async change for identify function 2025-11-04 13:13:42 +01:00
Igor Ilic
ff388179fb feat: Add dataset_id calculation that handles legacy dataset_id 2025-11-04 13:11:57 +01:00
Igor Ilic
b0f85c9e99 feat: add legacy and modern data_id calculating 2025-11-04 13:01:10 +01:00
Igor Ilic
e3b707a0c2 refactor: Change variable names, add setting of current tenant to be optional for tenant creation 2025-11-04 12:20:17 +01:00
Igor Ilic
41bbf5fdd8
Merge branch 'dev' into multi-tenancy 2025-10-30 18:12:21 +01:00
Hande
995e7aa483
fix: update unsupported vector db log (#1708)
<!-- .github/pull_request_template.md -->

## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->

## 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.
2025-10-30 17:38:28 +01:00
Igor Ilic
d58f85e431
Update dev from main (#1707)
<!-- .github/pull_request_template.md -->

## Description
Merge main into dev branch

## 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.
2025-10-30 17:35:07 +01:00
Igor Ilic
5007a2a298 refactor: dont use file name from metadata 2025-10-30 14:49:58 +01:00
Igor Ilic
081cab27b1 refactor: add x-wav support 2025-10-30 14:46:02 +01:00
Igor Ilic
e2457ef277 fix: Resolve issue with text classification 2025-10-30 14:27:01 +01:00
lxobr
6223ecf05b
feat: optimize repeated entity extraction (#1682)
<!-- .github/pull_request_template.md -->

## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->

- Added an `edge_text` field to edges that auto-fills from
`relationship_type` if not provided.
- Containts edges now store descriptions for better embedding
- Updated and refactored indexing so that edge_text gets embedded and
exposed
- Updated retrieval to use the new embeddings 
- Added a test to verify edge_text exists in the graph with the correct
format.

## 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
- [x] Code refactoring
- [x] 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 -->
- [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
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [x] 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.
2025-10-30 13:56:06 +01:00
Igor Ilic
a38853ae93 refactor: use same mechanism to determine file type 2025-10-29 19:45:17 +01:00
Igor Ilic
b15a073db7 fix: resolve issue with txt file type handling 2025-10-29 19:32:28 +01:00
Igor Ilic
2fa939a6d1
Merge branch 'dev' into fix_issue_with_base_config 2025-10-29 14:58:44 +01:00
Igor Ilic
51bc78c32e refactor: Change priority for Cognee logs 2025-10-29 14:53:42 +01:00
Vasilije
76396d5d27
fix: Remove custom pdf handling and rely on filetype library (#1694)
<!-- .github/pull_request_template.md -->

## Description
Remove custom PDF handling and let filetype handle PDF documents

## 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):

## 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.
2025-10-29 14:48:29 +01:00
Vasilije
4dbd01637e
add fix (#1693)
<!-- .github/pull_request_template.md -->

## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->

## 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.
2025-10-29 14:19:35 +01:00
Vasilije
dd286e0c94
refactor: Remove LanceDB fallback (#1683)
<!-- .github/pull_request_template.md -->

## Description
Remove fallback when provided vector adapter is not reckognized to use
LanceDB. When no adapter provider info is provided LanceDB will still be
used.

## 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
- [x] 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.
2025-10-29 14:19:14 +01:00
Igor Ilic
0cb334c9ae Merge branch 'dev' into fix_issue_with_base_config 2025-10-29 11:42:25 +01:00
vasilije
55d55946b0 add fix 2025-10-29 10:28:10 +01:00
Vasilije
4e0f392f3c
fix: Fix network visualization (#1687)
<!-- .github/pull_request_template.md -->

## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->

## 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.
2025-10-29 10:17:48 +01:00
Igor Ilic
f6f6893f82 refactor: Handle read-only file systems 2025-10-28 17:52:54 +01:00
Igor Ilic
14410c86cb fix: Remove custom pdf handling and rely on filetype library 2025-10-28 17:34:04 +01:00
vasilije
8efd152f4c fix network v 2025-10-28 16:03:43 +01:00
hajdul88
221a0dba01
feature: adds the concept of now to the qa for temporal queries (#1685)
<!-- .github/pull_request_template.md -->

## Description
 Adds the concept of now to the qa for temporal queries

## 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
- [x] 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.
2025-10-28 15:27:29 +01:00
Igor Ilic
15a0315375 refactor: Remove LanceDB fallback 2025-10-28 14:35:08 +01:00
hajdul88
65003a0a0b
Merge branch 'dev' into feature/cog-3254-add-multifile-ontology-handling 2025-10-28 09:58:17 +01:00
Vasilije
5684024d8c
refactor: Change id to be the relational database ID and not graph no… (#1669)
…de ID

<!-- .github/pull_request_template.md -->

## Description
Update description of relational database column to use relational
database ID value instead of graph node ID value

## 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.
2025-10-28 08:54:35 +01:00
Igor Ilic
8ba1aa5b7c
Merge branch 'dev' into read-only-file-system-support 2025-10-27 16:41:36 +01:00
hajdul88
2e6ee5d61e
feature: adds new tenant id (if available) to telemetry packages for basic cognee operations (#1676)
<!-- .github/pull_request_template.md -->

## Description
Adds new tenant id (if available) to telemetry packages for basic cognee
operations

## 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
- [x] 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 -->
- [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.
2025-10-27 16:38:23 +01:00
Igor Ilic
da10b0cd3d fix: Resolve issue for read only file systems 2025-10-27 16:37:37 +01:00
hajdul88
d224864e57 feat: extends ontology unit tests with multifile support tests + partially or fully missing ontology file list tests 2025-10-27 14:22:34 +01:00
hajdul88
6d55da00af ruff fix 2025-10-27 13:47:04 +01:00
hajdul88
6c576883b9 Update RDFLibOntologyResolver.py 2025-10-27 13:46:42 +01:00
hajdul88
61e47c0b2f feat: adds multifile ontology handling to OntologyResolver 2025-10-27 13:39:02 +01:00
Igor Ilic
a18370a0fc refactor: Remove reference to specific database row 2025-10-26 23:35:00 +01:00