<!-- .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>
<!-- .github/pull_request_template.md -->
## Description
<!-- Provide a clear description of the changes in this PR -->
## 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: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
<!-- .github/pull_request_template.md -->
## Description
Adds subgraph retriever to graph based completion searches
## 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.
<!-- .github/pull_request_template.md -->
## Description
<!-- Provide a clear description of the changes in this PR -->
- Expose top_k as an optional argument of run_question_answering
- Update retrievers to handle the parameters
## 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**
- Enhanced answer generation and document retrieval capabilities by
introducing an optional parameter that allows users to specify the
number of top results. This improvement adds flexibility when retrieving
question responses and associated context, adapting the output based on
user preference.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
<!-- .github/pull_request_template.md -->
## Description
<!-- Provide a clear description of the changes in this PR -->
- Refactored `brute_force_triplet_search`, extracting memory projection.
- Built **TripletSearchContextProvider** (extends
**BaseContextProvider**) to create a single memory projection and
perform a triplet search for each entity.
- Refactored `entity_completion` into **EntityCompletionRetriever**
(extends **BaseRetriever**).
- Added **SummarizedTripletSearchContextProvider** (extends
**TripletSearchContextProvider**) for an alternative summarized output
format.
- Developed and tested an example showcasing both context providers,
comparing raw triplets, summaries, and standard search results.
## 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**
- Enhanced text summarization now delivers clearer, more concise
overviews of search results.
- Improved search performance with optimized context retrieval and
memory reuse for faster, more reliable results.
- Introduced advanced entity-based completion for generating more
relevant, context-aware responses.
- **Refactor**
- Streamlined internal workflows and error handling to ensure a smoother
overall experience.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: Boris <boris@topoteretes.com>
<!-- .github/pull_request_template.md -->
## Description
<!-- Provide a clear description of the changes in this PR -->
- Created the `BaseRetriever` class to unify all the retrievers and
searches.
- Implemented seven specialized retrievers (summaries, chunks,
completions, graph, graph-summary, insights, code) with consistent
get_context/get_completion interfaces.
- Added json context dumping feature in the current completion
implementations to enable context comparisons.
- Built a comparison framework to validate old vs new implementations.
## 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**
- Introduced multiple retrieval classes for enhanced search
capabilities, including `BaseRetriever`, `ChunksRetriever`,
`CodeRetriever`, `CompletionRetriever`, `GraphCompletionRetriever`,
`GraphSummaryCompletionRetriever`, `InsightsRetriever`, and
`SummariesRetriever`.
- Enhanced query completions with optional context saving for improved
data persistence.
- Implemented advanced tools to compare retrieval outcomes across
different implementations.
- **Refactor**
- Streamlined internal module organization and updated references for
increased maintainability and consistency.
- Added comments indicating future maintenance tasks related to code
merging.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
