cognee/evals/comparative_eval/helpers
lxobr cfe9c949a7
feat: unify comparative evals (#916)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->
- Comparative Framework: Independent benchmarking system for evaluating
different RAG/QA systems
- HotpotQA Dataset: 50 instances corpus and corresponding QA pairs for
standardized evaluation
- Base Class: Abstract QABenchmarkRAG with async pipeline for document
ingestion and question answering
- Three Benchmarks: Standalone implementations for Mem0, LightRAG, and
Graphiti with specific dependencies

## 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>
2025-06-11 10:06:09 +02:00
..
calculate_aggregate_metrics.py feat: unify comparative evals (#916) 2025-06-11 10:06:09 +02:00
convert_metrics.py feat: unify comparative evals (#916) 2025-06-11 10:06:09 +02:00
modal_evaluate_answers.py feat: unify comparative evals (#916) 2025-06-11 10:06:09 +02:00