Commit graph

4968 commits

Author SHA1 Message Date
Igor Ilic
1724997683 docs: Update README.md 2025-12-18 14:46:21 +01:00
Igor Ilic
eda9f26b2b
Merge branch 'main' into human-readable-search 2025-12-18 14:24:09 +01:00
Igor Ilic
cc41ef853c refactor: Update examples to use pprint 2025-12-18 14:17:24 +01:00
Vasilije
4caac4b8f0
refactor: Make graphs return optional in search (#1919)
<!-- .github/pull_request_template.md -->

## Description
- Have search results be more human readable by making graphs return
information optional

## Acceptance Criteria
<!--
* Key requirements to the new feature or modification;
* Proof that the changes work and meet the requirements;
* Include instructions on how to verify the changes. Describe how to
test it locally;
* Proof that it's sufficiently tested.
-->

## 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.


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **New Features**
* Added an optional verbose mode to search. When enabled, results
include additional graph details; disabled by default for cleaner
responses.

* **Tests**
* Added unit tests verifying access-controlled search returns correctly
shaped results for both verbose and non-verbose modes, including
presence/absence of graph details.

<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2025-12-18 13:50:33 +01:00
Igor Ilic
b5949580de refactor: add note about verbose in combined context search 2025-12-18 13:45:20 +01:00
hajdul88
8602ba1e93
Merge branch 'dev' into feature/cog-3532-empower-test_search-db-retrievers-tests-reorg-4 2025-12-18 13:25:19 +01:00
Igor Ilic
986b93fee4 docs: add docstring update for search 2025-12-18 13:24:39 +01:00
Igor Ilic
31e491bc88 test: Add test for verbose search 2025-12-18 13:04:17 +01:00
Igor Ilic
f2bc7ca992 refactor: change comment 2025-12-18 12:00:06 +01:00
Igor Ilic
dd9aad90cb refactor: Make graphs return optional 2025-12-18 11:57:40 +01:00
Vasilije
4d03fcfa9e
fix: Fix connection encoding (#1917)
<!-- .github/pull_request_template.md -->

## Description
Resolve issue with special characters like '#' and '@' in passwords for
Postgres

## Acceptance Criteria
<!--
* Key requirements to the new feature or modification;
* Proof that the changes work and meet the requirements;
* Include instructions on how to verify the changes. Describe how to
test it locally;
* Proof that it's sufficiently tested.
-->

## 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.


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

* **Refactor**
* Improved internal database connection handling for relational and
vector databases to enhance system stability and code maintainability.

<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2025-12-17 22:04:09 +01:00
Vasilije
2ef8094666
feat: Add custom label by contributor: apenade (#1913)
<!-- .github/pull_request_template.md -->

## Description
Add ability to define custom labels for Data in Cognee. Initial PR by
contributor: apenade

## Acceptance Criteria
<!--
* Key requirements to the new feature or modification;
* Proof that the changes work and meet the requirements;
* Include instructions on how to verify the changes. Describe how to
test it locally;
* Proof that it's sufficiently tested.
-->

## 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.


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

* **New Features**
* Added support for labeling individual data items during ingestion
workflows
* Expanded the add API to accept data items with optional custom labels
for better organization
* Labels are persisted and retrievable when accessing dataset
information
* Enhanced data retrieval to include label information in API responses

* **Tests**
* Added comprehensive end-to-end tests validating custom data labeling
functionality

<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2025-12-17 21:21:40 +01:00
Igor Ilic
d352ff0c28
Merge branch 'dev' into fix-connection-encoding 2025-12-17 21:08:45 +01:00
Igor Ilic
6e5e79f434 fix: Resolve connection issue with postgres when special characters are present 2025-12-17 21:07:23 +01:00
lxobr
46ff01021a feat: add multi-query support to score calculation 2025-12-17 19:09:02 +01:00
Christina_Raichel_Francis
931c5f3096 refactor: add test and example script 2025-12-17 18:02:35 +00:00
lxobr
69ab8e7ede feat: add multi-query support to graph distance mapping 2025-12-17 18:14:57 +01:00
lxobr
cc7ca45e73 feat: make vector_distance list based 2025-12-17 15:48:24 +01:00
Andrej Milicevic
929d88557e Merge branch 'dev' into feature/cog-3213-docs-set-up-guide-script-tests 2025-12-17 13:52:45 +01:00
Andrej Milicevic
431a83247f chore: remove unnecessary 'on push' setting 2025-12-17 13:50:43 +01:00
Andrej Milicevic
6958b4edd4 feat: add the triggers to release, after pypi publishing 2025-12-17 13:50:03 +01:00
Andrej Milicevic
a5a7ae2564 test: remove if 2025-12-17 13:16:46 +01:00
Andrej Milicevic
601f74db4f test: remove dependency from community trigger 2025-12-17 13:15:43 +01:00
Andrej Milicevic
e92d8f57b5 feat: add comunity test trigger 2025-12-17 13:14:14 +01:00
hajdul88
d8b4411aac
Merge branch 'dev' into feature/cog-3532-empower-test_search-db-retrievers-tests-reorg-4 2025-12-17 12:30:47 +01:00
hajdul88
f79ba53e1d
COG-3532 chore: retriever test reorganization + adding new tests (unit) (STEP 2) (#1892)
<!-- .github/pull_request_template.md -->

This PR restructures/adds unittests for the retrieval module. (STEP 2)

-Added missing unit tests for all core retrieval business logic

## 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)
<!-- 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.


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **Tests**
* Expanded and refactored retrieval module test suites with
comprehensive unit test coverage for ChunksRetriever,
SummariesRetriever, RagCompletionRetriever, TripletRetriever,
GraphCompletionRetriever, TemporalRetriever, and related components.
* Added new test modules for completion utilities, graph summary
retrieval, and user feedback functionality.
* Improved test robustness with edge case handling and error scenario
coverage.

<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2025-12-17 12:30:15 +01:00
Christina_Raichel_Francis
ee29dd1f81 refactor: update cognee tasks to add frequency tracking script 2025-12-17 10:36:59 +00:00
Andrej Milicevic
999e6c0981 Merge branch 'dev' into feature/cog-3213-docs-set-up-guide-script-tests 2025-12-17 11:01:25 +01:00
hajdul88
b0454b49a9 Merge branch 'feature/cog-3532-empower-test_search-db-retrievers-tests-reorg-4' of github.com:topoteretes/cognee into feature/cog-3532-empower-test_search-db-retrievers-tests-reorg-4 2025-12-17 10:35:12 +01:00
hajdul88
94d5175570 feat: adds unit test for the prepare search result - search contract 2025-12-17 10:34:57 +01:00
hajdul88
623126eec1
Merge branch 'feature/cog-3532-empower-test_search-db-retrievers-tests-reorg-3' into feature/cog-3532-empower-test_search-db-retrievers-tests-reorg-4 2025-12-17 10:07:58 +01:00
Igor Ilic
cc872fc8de refactor: format PR 2025-12-16 21:04:15 +01:00
Igor Ilic
233afdd0a9
Merge branch 'dev' into add-custom-label-apenade 2025-12-16 21:01:42 +01:00
Igor Ilic
b77961b0f1 fix: Resolve issues with data label PR, add tests and upgrade migration 2025-12-16 20:59:17 +01:00
hajdul88
8f8f4c0b63
Merge branch 'dev' into feature/cog-3532-empower-test_search-db-retrievers-tests-reorg-3 2025-12-16 20:18:54 +01:00
Igor Ilic
56b03c89f3 Merge branch 'dev' into add-custom-label-apenade 2025-12-16 19:15:30 +01:00
Vasilije
aeda1d8eba
Test audio image transcription (#1911)
<!-- .github/pull_request_template.md -->

## Description
Run CI/CD for audio/image transcription PR from contributor
@rajeevrajeshuni

## Acceptance Criteria
<!--
* Key requirements to the new feature or modification;
* Proof that the changes work and meet the requirements;
* Include instructions on how to verify the changes. Describe how to
test it locally;
* Proof that it's sufficiently tested.
-->

## 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.


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

## Release Notes

* **New Features**
  * Added audio transcription capability across LLM providers.
  * Added image transcription and description capability.
  * Enhanced observability and monitoring for AI operations.

* **Breaking Changes**
* Removed synchronous structured output method; use asynchronous
alternative instead.

* **Refactor**
* Unified LLM provider architecture for improved consistency and
maintainability.

<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2025-12-16 19:06:38 +01:00
hajdul88
1500b1c693
Merge branch 'feature/cog-3532-empower-test_search-db-retrievers-tests-reorg-3' into feature/cog-3532-empower-test_search-db-retrievers-tests-reorg-4 2025-12-16 17:58:04 +01:00
hajdul88
18d0a41850 Update test_search.py 2025-12-16 17:49:43 +01:00
hajdul88
4ff2a35476 chore: moves unit tests into their correct directory 2025-12-16 17:33:20 +01:00
Igor Ilic
8027263e8b refactor: remove unused import 2025-12-16 16:54:27 +01:00
Igor Ilic
f27d07d902 refactor: remove mandatory transcription and image methods in LLMInterface 2025-12-16 16:53:56 +01:00
hajdul88
789fa90790 chore: covering search.py behavior with unit tests 2025-12-16 16:39:31 +01:00
Igor Ilic
3e041ec12f refactor: format code 2025-12-16 16:28:30 +01:00
Igor Ilic
f2cb68dd5e refactor: use async image and transcription handling 2025-12-16 16:27:13 +01:00
Igor Ilic
d92d6b9d8f refactor: remove optional return value 2025-12-16 16:02:15 +01:00
hajdul88
7892b48afe Update test_get_search_type_tools.py 2025-12-16 15:59:15 +01:00
Igor Ilic
a52873a71f refactor: make return type mandatory for transcription 2025-12-16 15:54:25 +01:00
hajdul88
48c2040f3d Delete test_get_search_type_tools_integration.py 2025-12-16 15:45:32 +01:00
hajdul88
757d5fca65
Merge branch 'feature/cog-3532-empower-test_search-db-retrievers-tests-reorg-3' into feature/cog-3532-empower-test_search-db-retrievers-tests-reorg-4 2025-12-16 15:43:05 +01:00