marek/MtoRagSystem
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

first test suite retrieval

Browse Source
This commit is contained in:
team2
2026-04-22 22:22:27 +02:00
parent 8127d33571
commit 47099a4407
4 changed files with 458 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

121
tests/evals/cases/retrieval.ndjson
View File

@@ -1,4 +1,117 @@
{"id":"retrieval_exact_doc_001","type":"retrieval","prompt":"Testomat 808","assert":{"selection_mode":"exact_document_title","min_results":1,"must_include_document_ids":["26129c01-c09f-4c71-9c80-7ddffb6c77fb"]}}
{"id":"retrieval_exact_doc_002","type":"retrieval","prompt":"Testomat EVO CALC","assert":{"selection_mode":"exact_document_title","min_results":1,"must_include_document_ids":["74fdad85-5e4e-4f08-8d95-402f3180ed55"]}}
{"id":"retrieval_exact_doc_003","type":"retrieval","prompt":"Wasserhärte Grenzwert Testomat","assert":{"selection_mode":"exact_document_title","min_results":1,"must_include_document_ids":["60706498-867b-41b8-8e76-63248178d265"]}}
{"id":"retrieval_noise_001","type":"retrieval","prompt":"dsgfsdgfsdgf","assert":{"max_results":0}}
{
"id": "retrieval_exact_doc_001",
"type": "retrieval",
"prompt": "phaseaaudit-md",
"assert": {
"selection_mode_in": [
"exact_document_title"
],
"min_results": 1,
"must_include_one_of_document_ids": [
"5914508a-5930-4f04-892b-323881d0daa7"
],
"must_include_any_terms": [
"enterprise",
"governance",
"vector-service"
]
}
}
{
"id": "retrieval_exact_doc_002",
"type": "retrieval",
"prompt": "ragsystemoverview-md",
"assert": {
"selection_mode_in": [
"exact_document_title"
],
"min_results": 1,
"must_include_one_of_document_ids": [
"7513fd82-eec6-4bfa-a730-41820b38b6b4"
],
"must_include_all_terms": [
"rag-system",
"dokumente"
]
}
}
{
"id": "retrieval_exact_doc_003",
"type": "retrieval",
"prompt": "matrixparams-md",
"assert": {
"selection_mode_in": [
"exact_document_title"
],
"min_results": 1,
"must_include_one_of_document_ids": [
"25276f4c-32bb-47a5-98b3-9d81aa722d2b"
],
"must_include_any_terms": [
"retrievalmaxchunks",
"retrievalvectortopk",
"hard_max_chunks"
]
}
}
{
"id": "retrieval_exact_doc_004",
"type": "retrieval",
"prompt": "readme-md",
"assert": {
"selection_mode_in": [
"exact_document_title"
],
"min_results": 1,
"must_include_one_of_document_ids": [
"8abe1f0d-54e6-41ad-967a-9ce8a0efc6da"
],
"must_include_any_terms": [
"deterministisches",
"faiss",
"vector-service"
]
}
}
{
"id": "retrieval_semantic_001",
"type": "retrieval",
"prompt": "wie funktioniert das system",
"assert": {
"min_results": 1,
"must_include_one_of_document_ids": [
"7513fd82-eec6-4bfa-a730-41820b38b6b4",
"8abe1f0d-54e6-41ad-967a-9ce8a0efc6da"
],
"must_include_any_terms": [
"rag-system",
"dokumente",
"indexierung"
]
}
}
{
"id": "retrieval_semantic_002",
"type": "retrieval",
"prompt": "welche parameter beeinflussen retrieval",
"assert": {
"min_results": 1,
"must_include_one_of_document_ids": [
"25276f4c-32bb-47a5-98b3-9d81aa722d2b",
"7513fd82-eec6-4bfa-a730-41820b38b6b4"
],
"must_include_any_terms": [
"retrievalmaxchunks",
"vectortopk",
"chunk"
]
}
}
{
"id": "retrieval_noise_001",
"type": "retrieval",
"prompt": "dsgfsdgfsdgf",
"assert": {
"max_results": 0
}
}