<!-- .github/pull_request_template.md -->
## Description
<!-- Provide a clear description of the changes in this PR -->
This PR implements the 'FEELING_LUCKY' search type, which intelligently
routes user queries to the most appropriate search retriever, addressing
[#1162](https://github.com/topoteretes/cognee/issues/1162).
- implement new search type FEELING_LUCKY
- Add the select_search_type function to analyze queries and choose the
proper search type
- Integrate with an LLM for intelligent search type determination
- Add logging for the search type selection process
- Support fallback to RAG_COMPLETION when the LLM selection fails
- Add tests for the new search type
## How it works
When a user selects the 'FEELING_LUCKY' search type, the system first
sends their natural language query to an LLM-based classifier. This
classifier analyzes the query's intent (e.g., is it asking for a
relationship, a summary, or a factual answer?) and selects the optimal
SearchType, such as 'INSIGHTS' or 'GRAPH_COMPLETION'. The main search
function then proceeds using this dynamically selected type. If the
classification process fails, it gracefully falls back to the default
'RAG_COMPLETION' type.
## Testing
Tests can be run with:
```bash
python -m pytest cognee/tests/unit/modules/search/search_methods_test.py -k "feeling_lucky" -v
```
## 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.
Signed-off-by: EricXiao <taoiaox@gmail.com>
<!-- .github/pull_request_template.md -->
## Description
Cover current context structure with unit test so it is not changed
accidentally in the future
## 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 -->
## 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 <vas.markovic@gmail.com>
Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
<!-- .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: Igor Ilic <30923996+dexters1@users.noreply.github.com>
Co-authored-by: Igor Ilic <igorilic03@gmail.com>
## Summary
This PR fixes an asymmetry issue where files saved with `file://`
prefixes could not be read back, causing "file not found" errors.
## Problem
The Cognee framework has a bug where:
- `save_data_to_file.py` adds `file://` prefix when saving files
- `open_data_file.py` doesn't handle the `file://` prefix when reading
files
- This causes saved files to appear as "lost" with cryptic "file not
found" errors
## Solution
Added proper handling for `file://` URLs in `open_data_file.py` by:
- Checking if the file path starts with `"file://"`
- Stripping the prefix using `replace("file://", "", 1)`
- Following the same pattern as S3 URL handling
## Changes
- Modified
`cognee/modules/data/processing/document_types/open_data_file.py` to
handle `file://` URLs
- Added comprehensive unit tests in
`cognee/tests/unit/modules/data/test_open_data_file.py`
## Testing
Added 6 test cases covering:
- Regular file paths (ensuring backward compatibility)
- file:// URLs in text mode
- file:// URLs in binary mode
- file:// URLs with specific encoding
- Nonexistent files with file:// URLs
- Edge case with multiple file:// prefixes
All tests pass successfully.
## Notes
- This is a minimal fix that maintains backward compatibility
- The fix follows the existing pattern used for S3 URL handling
- No breaking changes to the API
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
Signed-off-by: Hashem Aldhaheri <aenawi@gmail.com>
<!-- .github/pull_request_template.md -->
## Description
Set default db to kuzu and remove networkx adapter due to community repo
adapter
## 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
Replaces Owlready2 with RDFLib
## 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: Igor Ilic <igorilic03@gmail.com>
<!-- .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: Boris Arzentar <borisarzentar@gmail.com>
Co-authored-by: Boris <boris@topoteretes.com>
<!-- .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.
---------
Signed-off-by: Diego B Theuerkauf <diego.theuerkauf@tuebingen.mpg.de>
Co-authored-by: Igor Ilic <30923996+dexters1@users.noreply.github.com>
Co-authored-by: Boris Arzentar <borisarzentar@gmail.com>
Co-authored-by: Boris <boris@topoteretes.com>
Co-authored-by: Igor Ilic <igorilic03@gmail.com>
Co-authored-by: Hande <159312713+hande-k@users.noreply.github.com>
Co-authored-by: Matea Pesic <80577904+matea16@users.noreply.github.com>
Co-authored-by: hajdul88 <52442977+hajdul88@users.noreply.github.com>
Co-authored-by: Daniel Molnar <soobrosa@gmail.com>
Co-authored-by: Diego Baptista Theuerkauf <34717973+diegoabt@users.noreply.github.com>
Co-authored-by: Dmitrii Galkin <36552323+dm1tryG@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: lxobr <122801072+lxobr@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions@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
Adds context extension search
## 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
Adds chain of thought retriever
## 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 -->
## 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 <vas.markovic@gmail.com>
Co-authored-by: Igor Ilic <30923996+dexters1@users.noreply.github.com>
Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
Co-authored-by: Igor Ilic <igorilic03@gmail.com>
Co-authored-by: Hande <159312713+hande-k@users.noreply.github.com>
Co-authored-by: Matea Pesic <80577904+matea16@users.noreply.github.com>
Co-authored-by: hajdul88 <52442977+hajdul88@users.noreply.github.com>
Co-authored-by: Daniel Molnar <soobrosa@gmail.com>
Co-authored-by: Diego Baptista Theuerkauf <34717973+diegoabt@users.noreply.github.com>
<!-- .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: Hande <159312713+hande-k@users.noreply.github.com>
Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
<!-- .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.
<!-- .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: Daniel Molnar <soobrosa@gmail.com>
<!-- .github/pull_request_template.md -->
## Description
Add ability to define top-k for Cognee search types Insights, RAG and
GRAPH Completion
## 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
- handle empty distance list in brute force search
- unit tests
## 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: hajdul88 <52442977+hajdul88@users.noreply.github.com>
<!-- .github/pull_request_template.md -->
## Description
<!-- Provide a clear description of the changes in this PR -->
- Optimized to deduplicate nodes appearing in multiple triplets,
avoiding redundant text repetition
- Reimplemented `resolve_edges_to_text` with cleaner formatting
- Added `_top_n_words` method for extracting frequent words from text
- Created `_get_title` function to generate titles from text content
based on first words and word frequency
- Extracted node processing logic to `_get_nodes` helper method
- Created dedicated `stop_words` utility with common English stopwords
## 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
## Summary by CodeRabbit
- **New Features**
- Improved text output formatting that organizes content into clearly
defined sections for enhanced readability.
- Enhanced text processing capabilities, including refined title
generation and key phrase extraction.
- Introduced a comprehensive utility for managing common stop words,
further optimizing text analysis.
- **Bug Fixes**
- Updated tests to ensure accurate validation of new functionalities and
improved existing test coverage.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: hajdul88 <52442977+hajdul88@users.noreply.github.com>
<!-- .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
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
- **Chores**
- Removed unused code to streamline internal processes.
- **Tests**
- Added a comprehensive suite of tests to validate core retrieval and
search functionalities.
- Improved validation of response generation, context handling, and
error scenarios to ensure consistent and reliable performance.
These improvements enhance overall system stability and maintainability,
contributing to a smoother experience for end-users.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: vasilije <vas.markovic@gmail.com>
<!-- .github/pull_request_template.md -->
## Description
This PR contains the ontology feature integrated into cognify
## 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 ontology management with the introduction of the
`OntologyResolver` class for improved data handling and querying.
- Expanded ontology framework now provides enriched coverage of
technology and automotive domains, including new entities and
relationships.
- Updated entity models now include a validation flag to support
improved data integrity.
- Added support for specifying an ontology file path in relevant
functions to enhance flexibility.
- **Refactor**
- Streamlined integration of ontology processing across data extraction
and workflow routines.
- **Chores**
- Updated project dependencies to include `owlready2` for advanced
ontology functionality.
- **Tests**
- Introduced a new test suite for the `OntologyResolver` class to
validate its functionality under various conditions.
<!-- 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 -->
- 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>
<!-- .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
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
- **New Features**
• Graph visualizations now allow exporting to a user-specified file path
for more flexible output management.
• The text embedding process has been enhanced with an additional
tokenizer option for improved performance.
• A new `ExtendableDataPoint` class has been introduced for future
extensions.
• New JSON files for companies and individuals have been added to
facilitate testing and data processing.
- **Improvements**
• Search functionality now uses updated identifiers for more reliable
content retrieval.
• Metadata handling has been streamlined across various classes by
removing unnecessary type specifications.
• Enhanced serialization of properties in the Neo4j adapter for improved
handling of complex structures.
• The setup process for databases has been improved with a new
asynchronous setup function.
- **Chores**
• Dependency and configuration updates improve overall stability and
performance.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
<!-- .github/pull_request_template.md -->
## Description
This PR contains the improvement of the visualization endpoint
## 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**
- Launched an enhanced interactive network visualization utility that
renders dynamic, browser-based graphs. The new feature simplifies
execution by directly generating an HTML file showcasing the
visualization—complete with interactive elements and an on-screen
confirmation—providing a more intuitive and efficient experience.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
* fix: refactor get_graph_from_model to return nodes and edges correctly
* fix: add missing params
* fix: remove complex zip usage
* fix: add edges to data_point properties
* fix: handle rate limit error coming from llm model
* fix: fixes lost edges and nodes in get_graph_from_model
* fix: fixes database pruning issue in pgvector
* fix: fixes database pruning issue in pgvector (#261)
* feat: adds code summary embeddings to vector DB
* fix: cognee_demo notebook pipeline is not saving summaries
* feat: implements first version of codegraph retriever
* chore: implements minor changes mostly to make the code production ready
* fix: turns off raising duplicated edges unit test as we have these in our current codegraph generation
* feat: implements unit tests for description to codepart search
* fix: fixes edge property inconsistent access in codepart retriever
* chore: implements more precise typing for get_attribute method for cogneegraph
* chore: adds spacing to tests and changes the cogneegraph getter names
---------
Co-authored-by: Boris Arzentar <borisarzentar@gmail.com>
