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

p99

Browse Source
This commit is contained in:
team 1
2026-05-12 08:25:59 +02:00
parent e072a8e15e
commit 3d0092b753
10 changed files with 664 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/evals/cases/answer_guard.ndjson Normal file
View File

@@ -0,0 +1,4 @@
{"id":"answer_guard_noise_no_evidence_001","type":"answer_guard","prompt":"dsgfsdgfsdgf","assert":{"max_results":0}}
{"id":"answer_guard_mythical_medium_no_direct_evidence_001","type":"answer_guard","prompt":"gibt es einen testomat für drachenblut","assert":{"must_not_include_terms":["drachenblut"]}}
{"id":"answer_guard_lunar_water_no_direct_evidence_001","type":"answer_guard","prompt":"welcher testomat misst mondwasser im vakuum","assert":{"must_not_include_terms":["mondwasser","vakuum"]}}
{"id":"answer_guard_delivery_not_sdb_001","type":"answer_guard","prompt":"lieferbedingungen versand testomat","assert":{"min_results":1,"must_include_one_of_document_ids":["26ddf03d-9108-4a65-aa0e-a5df7613fa77"],"must_not_include_document_ids":["7166592f-85f2-425c-997b-73e323ae184d"],"must_not_include_terms":["sicherheitsdatenblatt"]}}

4
tests/evals/cases/followup.ndjson Normal file
View File

@@ -0,0 +1,4 @@
{"id":"followup_indicator_price_001","type":"followup","prompt":"was kostet der indikator","history":[{"prompt":"Was ist der niedrigste Grenzwert für die Wasserhärte, welcher mit einem Testomaten überwacht werden kann?","answer":"Der niedrigste Grenzwert für die Wasserhärte beträgt 0,02 °dH. Dieser Wert wird vom Testomat 808 gemessen."},{"prompt":"mit welchem indikator","answer":"Der niedrigste messbare Grenzwert für Wasserhärte mit dem Testomat 808 wird mit dem Indikatortyp 300 erreicht."}],"assert":{"expected_query":"testomat 808 300 indikator","must_include_terms":["testomat","808","300","indikator"],"must_not_include_terms":["300 s","301","302","303","testomat 2000"]}}
{"id":"followup_main_device_price_001","type":"followup","prompt":"und was kostet das gerät selber","history":[{"prompt":"was kostet der indikator","answer":"Shop-Suche abgeschlossen. Gesendete Suchquery: testomat 808 300 indikator. Testomat® 808 Indikator 300 500 ml, Produkt-Nummer 141001. Testomat® 808 Indikator 300 2 x 100 ml, Produkt-Nummer 140001. Der zugehörige Testomat ist Testomat 808."}],"assert":{"expected_query":"testomat 808","must_include_terms":["testomat","808"],"must_not_include_terms":["indikator","300","141001","140001"]}}
{"id":"followup_weak_shop_information_anchor_001","type":"followup","prompt":"suche im shop nach der information","history":[{"prompt":"welche grenzwerte kann der testomat 2000 thcl messen","answer":"Der relevante Produktanker ist Testomat 2000 THCL. Das Gerät ist für Chlorüberwachung / freies Chlor relevant."}],"assert":{"expected_query":"testomat 2000 thcl","must_include_terms":["testomat","2000","thcl"],"must_not_equal_query":"information","must_not_include_terms":["information"]}}
{"id":"followup_product_links_split_001","type":"followup","prompt":"gebe mir links zu den produkten aus dem shop","history":[{"prompt":"gerät zur messung Prozesswasser in medizinischen Geräten","answer":"Geeignete Produktanker sind Testomat 2000 Self Clean, Testomat 2000 CAL und Testomat 808."}],"assert":{"expected_individual_queries":["testomat 2000 self clean","testomat 2000 cal","testomat 808"],"expected_individual_queries_exact":true,"min_individual_queries":3,"max_individual_queries":3,"must_not_include_terms":["links zu aus"]}}

5
tests/evals/cases/shop_query.ndjson Normal file
View File

@@ -0,0 +1,5 @@
{"id":"shop_query_indicator_exact_001","type":"shop_query","prompt":"was kostet der Testomat 808 Indikator 300","assert":{"must_include_terms":["testomat","808","300","indikator"],"must_not_include_terms":["300 s","301","302","303","gerät selber"]}}
{"id":"shop_query_brewing_water_cleanup_001","type":"shop_query","prompt":"ich möchte für brauerei das brauwasser messen","assert":{"expected_query":"brauerei brauwasser","must_include_terms":["brauerei","brauwasser"],"must_not_include_terms":["möchte","messen","think"]}}
{"id":"shop_query_swimming_pool_typo_001","type":"shop_query","prompt":"ich würde gern chlor im schwinnbad messen","assert":{"expected_query":"chlor schwimmbad","must_include_terms":["chlor","schwimmbad"],"must_not_include_terms":["schwinnbad","messen"]}}
{"id":"shop_query_lab_cl_acronym_001","type":"shop_query","prompt":"Zeige mir die Preise zu Testomat LAB CL.","assert":{"expected_query":"testomat lab cl","must_include_terms":["testomat","lab","cl"],"must_not_equal_query":"testomat"}}
{"id":"shop_query_sio2_anchor_001","type":"shop_query","prompt":"suche gerät kühlsysteme Silikatüberwachung","assert":{"expected_query":"testomat 808 sio2","must_include_terms":["testomat","808","sio2"],"must_not_include_terms":["kühlsysteme","silikatüberwachung"]}}