<!-- .github/pull_request_template.md -->
## Description
This PR introduces triplet embeddings via a new
create_triplet_embeddings memify pipeline.
The pipeline reads the graph in batches, extracts properties from graph
elements based on their datapoint types, and generates combined triplet
embeddings. These embeddings are stored in the vector database as a new
collection.
Changes in This PR:
-Added a new create_triplet_embeddings memify pipeline.
-Added a new get_triplet_datapoints memify task.
-Introduced a new triplet_completion search type.
-Added full test coverage
--Unit tests: memify task, pipeline, and retriever
--Integration tests: memify task, pipeline, and retriever
--End-to-end tests: updated session history tests and multi-DB search
tests; added tests for triplet_completion and memify pipeline execution
Acceptance Criteria and Testing
Scenario 1:
-Run default add, cognify pipelines
-Run create triplet embeddings memify pipeline
-Verify the vector DB contains a non empty Triplet_text collection.
-Use the new triplet_completion search type and confirm it works
correctly.
Scenario 2:
-Run the default add and cognify pipelines.
-Do not run the triplet embeddings memify pipeline.
-Attempt to use the triplet_completion search type.
-You should receive an error indicating that the triplet embeddings
memify pipeline must be executed first.
## 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
* **New Features**
* Triplet-based search with LLM-powered completions (TRIPLET_COMPLETION)
* Batch triplet retrieval and a triplet embeddings pipeline for
extraction, indexing, and optional background processing
* Context retrieval from triplet embeddings with optional caching and
conversation-history support
* New Triplet data type exposed for indexing and search
* **Examples**
* End-to-end example demonstrating triplet embeddings extraction and
TRIPLET_COMPLETION search
* **Tests**
* Unit and integration tests covering triplet extraction, retrieval,
embedding pipeline, and completion flows
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: Pavel Zorin <pazonec@yandex.ru>
- Remove unused connect_args parameter from __init__
- Programmatic parameter was dead code (never called by users)
- Users call get_relational_engine() which doesn't expose connect_args
- Keep DATABASE_CONNECT_ARGS env var support (actually used in production)
- Simplify implementation and reduce complexity
- Update docstring to reflect env-var-only approach
- Add production examples to docstring
Signed-off-by: ketanjain7981 <ketan.jain@think41.com>
The run_in_background parameter was defined in MemifyPayloadDTO but was
never passed to the cognee_memify function call, making the parameter
effectively unused. This fix passes the parameter so users can actually
run memify operations in the background.
Signed-off-by: Mike Potter <mpotter1@gmail.com>
<!-- .github/pull_request_template.md -->
This PR introduces wide vector and graph structure filtering
capabilities. With these changes, the graph completion retriever and all
retrievers that inherit from it will now filter relevant vector elements
and subgraphs based on the query. This improvement significantly
increases search speed for large graphs while maintaining—and in some
cases slightly improving—accuracy.
Changes in This PR:
-Introduced new wide_search_top_k parameter: Controls the initial search
space size
-Added graph adapter level filtering method: Enables relevant subgraph
filtering while maintaining backward compatibility. For community or
custom graph adapters that don't implement this method, the system
gracefully falls back to the original search behavior.
-Updated modal dashboard and evaluation framework: Fixed compatibility
issues.
Added comprehensive unit tests: Introduced unit tests for
brute_force_triplet_search (previously untested) and expanded the
CogneeGraph test suite.
Integration tests: Existing integration tests verify end-to-end search
functionality (no changes required).
Acceptance Criteria and Testing
To verify the new search behavior, run search queries with different
wide_search_top_k parameters while logging is enabled:
None: Triggers a full graph search (default behavior)
1: Projects a minimal subgraph (demonstrates maximum filtering)
Custom values: Test intermediate levels of filtering
Internal Testing and results:
Performance and accuracy benchmarks are available upon request. The
implementation demonstrates measurable improvements in query latency for
large graphs without sacrificing result quality.
## 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
- [x] 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.
---------
Co-authored-by: Pavel Zorin <pazonec@yandex.ru>
