cognee/evals
lxobr 9cc357ac1c
Feat/cog 1365 unify retrievers (#572)
<!-- .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>
2025-02-27 12:13:21 +01:00
..
cloud
eval_framework feat: add experimental cognify pipeline [COG-1293] (#541) 2025-02-25 16:14:27 +01:00
test_datasets/initial_test
__init__.py
deepeval_metrics.py
EC2_README.md
eval_on_hotpot.py feat: Add gemini support [COG-1023] (#485) 2025-01-31 18:03:23 +01:00
eval_swe_bench.py Feat/cog 1365 unify retrievers (#572) 2025-02-27 12:13:21 +01:00
eval_utils.py
generate_test_set.py
multimetric_qa_eval_run.py Feat: [COG-1074] fix multimetric eval bug (#463) 2025-01-28 13:05:22 +01:00
official_hotpot_metrics.py Incremental eval of cognee pipeline (#445) 2025-01-17 14:16:48 +01:00
promptfoo_config_template.yaml
promptfoo_metrics.py Feat: Save and load contexts and answers for eval (#462) 2025-01-22 16:17:01 +01:00
promptfoo_wrapper.py
promptfooprompt.json
qa_context_provider_utils.py Feat/cog 1365 unify retrievers (#572) 2025-02-27 12:13:21 +01:00
qa_dataset_utils.py
qa_eval_parameters.json feat: Add gemini support [COG-1023] (#485) 2025-01-31 18:03:23 +01:00
qa_eval_utils.py Feat: [COG-1074] fix multimetric eval bug (#463) 2025-01-28 13:05:22 +01:00
qa_metrics_utils.py Run eval on a set of parameters and save them as png and json (#443) 2025-01-17 00:18:51 +01:00
run_qa_eval.py Feat: Save and load contexts and answers for eval (#462) 2025-01-22 16:17:01 +01:00
simple_rag_vs_cognee_eval.py refactor: Refactor search so graph completion is used by default (#505) 2025-02-07 17:16:34 +01:00