Skip to content

feat: add lightweight GraphRAG benchmark #77

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
Postroggy wants to merge 18 commits into from
Closed

feat: add lightweight GraphRAG benchmark #77

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
18 commits
Select commit Hold shift + click to select a range
801db09
feat: graphrag benchmark
Postroggy Jul 1, 2026
8d02321
feat(benchmark): reproducible LLM-Judge client and metric direction r…
Postroggy Jul 5, 2026
782a597
feat(benchmark): add GraphExtractFlow normalization and fail-fast doc…
Postroggy Jul 5, 2026
8a6bcb7
local: keep experimental scripts, docs and pipeline changes (not for …
Postroggy Jul 5, 2026
b97d083
feat(benchmark): add extraction adapter and schema normalization
Postroggy Jul 5, 2026
2689732
feat(benchmark): add retrieval context adapter from WkFlowState
Postroggy Jul 5, 2026
6447d1f
feat(benchmark): include failed and degraded samples in Markdown report
Postroggy Jul 5, 2026
f6e9b64
refactor(benchmark): make degraded-sample detection mode-aware
Postroggy Jul 5, 2026
448d44d
refactor(benchmark): rename degraded samples to low-performing samples
Postroggy Jul 5, 2026
a0abdfb
fix(benchmark): remove misleading low-performing section and add metr…
Postroggy Jul 5, 2026
209c388
revert(local): remove non-benchmark scripts/docs and restore other mo…
Postroggy Jul 5, 2026
930a149
style(benchmark): fix ruff import sorting in graph_extract and retrie…
Postroggy Jul 5, 2026
60b695a
Revert "revert(local): remove non-benchmark scripts/docs and restore …
Postroggy Jul 5, 2026
bb750d0
revert(cleanup): undo the accidental revert and restore benchmark-onl…
Postroggy Jul 5, 2026
dca5b3d
feat(benchmark): analytical markdown reporter with dimension roll-up
Postroggy Jul 5, 2026
f616f48
feat(benchmark): add jitter_baseline.py for demo compare
Postroggy Jul 5, 2026
4cecd7d
fix(benchmark): improve retrieval data pipeline and syntax_validity b…
Postroggy Jul 6, 2026
9eb31fd
feat(benchmark): add LLM-based extraction metrics (SemanticEntityF1, …
Postroggy Jul 6, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -140,6 +140,7 @@ celerybeat.pid
config_prompt.yaml*

# AI-IDE prompt files (generated from AGENTS.md)
AGENTS.local.md

# Claude Projects
CLAUDE.md
Expand Down Expand Up @@ -216,3 +217,7 @@ cython_debug/
*.out
*.zip
*.tar.gz

# External benchmark datasets (generated JSON inputs + experiment outputs, local only)
hugegraph-llm/benchmark_data/

657 changes: 657 additions & 0 deletions hugegraph-llm/BENCHMARK_DATASETS.md
View file
Open in desktop

Large diffs are not rendered by default.

849 changes: 849 additions & 0 deletions hugegraph-llm/GRAPHRAG_BENCHMARK.md
View file
Open in desktop

Large diffs are not rendered by default.

Loading
Loading