c889a57b6b
Test Suites / Build CI Environment (push) Has been cancelled
Test Suites / Basic Tests (push) Has been cancelled
Test Suites / End-to-End Tests (push) Has been cancelled
Test Suites / CLI Tests (push) Has been cancelled
Test Suites / Slow End-to-End Tests (push) Has been cancelled
Test Suites / Graph Database Tests (push) Has been cancelled
Test Suites / Vector DB Tests (push) Has been cancelled
Test Suites / Temporal Graph Test (push) Has been cancelled
Test Suites / Search Test on Different DBs (push) Has been cancelled
Test Suites / Example Tests (push) Has been cancelled
Test Suites / Notebook Tests (push) Has been cancelled
Test Suites / OS and Python Tests Ubuntu (push) Has been cancelled
Test Suites / OS and Python Tests Extended (push) Has been cancelled
Test Suites / LLM Test Suite (push) Has been cancelled
Test Suites / S3 File Storage Test (push) Has been cancelled
Test Suites / Run Integration Tests (push) Has been cancelled
Test Suites / MCP Tests (push) Has been cancelled
Test Suites / Docker Compose Test (push) Has been cancelled
Test Suites / Docker CI test (push) Has been cancelled
Test Suites / Relational DB Migration Tests (push) Has been cancelled
Test Suites / Distributed Cognee Test (push) Has been cancelled
Test Suites / DB Examples Tests (push) Has been cancelled
Test Suites / Test Completion Status (push) Has been cancelled
Test Suites / Claude Code Review (push) Has been cancelled
Test Suites / basic checks (push) Has been cancelled
build | Build and Push Cognee MCP Docker Image to dockerhub / docker-build-and-push (push) Has been cancelled
Scorecard supply-chain security / Scorecard analysis (push) Has been cancelled
build | Build and Push Docker Image to dockerhub / docker-build-and-push (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges Core Functionality (3.11) (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges Core Functionality (3.12) (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges with Different Graph Databases (kuzu, kuzu) (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges with Different Graph Databases (neo4j, neo4j) (push) Has been cancelled
Weighted Edges Tests / Test Weighted Edges Examples (push) Has been cancelled
Weighted Edges Tests / Code Quality for Weighted Edges (push) Has been cancelled
95 lines
1.7 KiB
JSON
95 lines
1.7 KiB
JSON
[
|
|
{
|
|
"system": "Cognee Graph Completion CoT",
|
|
"Human-like Correctness": 0.925,
|
|
"Human-like Correctness Error": [
|
|
0.911,
|
|
0.94
|
|
],
|
|
"DeepEval Correctness": 0.846,
|
|
"DeepEval Correctness Error": [
|
|
0.83,
|
|
0.863
|
|
],
|
|
"DeepEval EM": 0.687,
|
|
"DeepEval EM Error": [
|
|
0.661,
|
|
0.717
|
|
],
|
|
"DeepEval F1": 0.841,
|
|
"DeepEval F1 Error": [
|
|
0.821,
|
|
0.861
|
|
]
|
|
},
|
|
{
|
|
"system": "Cognee Graph Completion Context Extension",
|
|
"Human-like Correctness": 0.871,
|
|
"Human-like Correctness Error": [
|
|
0.852,
|
|
0.891
|
|
],
|
|
"DeepEval Correctness": 0.785,
|
|
"DeepEval Correctness Error": [
|
|
0.765,
|
|
0.805
|
|
],
|
|
"DeepEval EM": 0.617,
|
|
"DeepEval EM Error": [
|
|
0.589,
|
|
0.645
|
|
],
|
|
"DeepEval F1": 0.776,
|
|
"DeepEval F1 Error": [
|
|
0.755,
|
|
0.797
|
|
]
|
|
},
|
|
{
|
|
"system": "Cognee Graph Completion",
|
|
"Human-like Correctness": 0.805,
|
|
"Human-like Correctness Error": [
|
|
0.783,
|
|
0.827
|
|
],
|
|
"DeepEval Correctness": 0.743,
|
|
"DeepEval Correctness Error": [
|
|
0.723,
|
|
0.765
|
|
],
|
|
"DeepEval EM": 0.596,
|
|
"DeepEval EM Error": [
|
|
0.569,
|
|
0.625
|
|
],
|
|
"DeepEval F1": 0.724,
|
|
"DeepEval F1 Error": [
|
|
0.698,
|
|
0.749
|
|
]
|
|
},
|
|
{
|
|
"system": "Cognee (Previous Non-Optimized Evaluation)",
|
|
"Human-like Correctness": 0.738,
|
|
"Human-like Correctness Error": [
|
|
0.626,
|
|
0.842
|
|
],
|
|
"DeepEval Correctness": 0.569,
|
|
"DeepEval Correctness Error": [
|
|
0.494,
|
|
0.642
|
|
],
|
|
"DeepEval EM": 0.04,
|
|
"DeepEval EM Error": [
|
|
0.0,
|
|
0.1
|
|
],
|
|
"DeepEval F1": 0.203,
|
|
"DeepEval F1 Error": [
|
|
0.155,
|
|
0.255
|
|
]
|
|
}
|
|
]
|