mteb 2.1.9__py3-none-any.whl → 2.1.10__py3-none-any.whl

mteb/tasks/retrieval/kat/georgian_faq_retrieval.py

@@ -46,10 +46,17 @@ class GeorgianFAQRetrieval(AbsTaskRetrieval):
             split=_EVAL_SPLIT,
             revision=self.metadata.dataset["revision"],
         )
-        question_ids = {
-            question: _id for _id, question in enumerate(set(data["question"]))
-        }
-        answer_ids = {answer: _id for _id, answer in enumerate(set(data["answer"]))}
+
+        question_ids = {}
+        answer_ids = {}
+
+        for row in data:
+            question = row["question"]
+            answer = row["answer"]
+            if question not in question_ids:
+                question_ids[question] = len(question_ids)
+            if answer not in answer_ids:
+                answer_ids[answer] = len(answer_ids)
 
         for row in data:
             question = row["question"]

mteb/tasks/retrieval/multilingual/belebele_retrieval.py

@@ -230,10 +230,11 @@ class BelebeleRetrieval(AbsTaskRetrieval):
             ds_corpus = self.dataset[lang_corpus]
             ds_question = self.dataset[lang_question]
 
-            question_ids = {
-                question: _id
-                for _id, question in enumerate(set(ds_question["question"]))
-            }
+            question_ids = {}
+            for row in ds_question:
+                question = row["question"]
+                if question not in question_ids:
+                    question_ids[question] = len(question_ids)
 
             link_to_context_id = {}
             context_idx = 0

mteb/tasks/retrieval/multilingual/public_health_qa_retrieval.py

@@ -32,10 +32,15 @@ def _load_publichealthqa_data(
             split=split,
             revision=revision,
         )
-        question_ids = {
-            question: _id for _id, question in enumerate(set(data["question"]))
-        }
-        answer_ids = {answer: _id for _id, answer in enumerate(set(data["answer"]))}
+
+        question_ids = {}
+        answer_ids = {}
+
+        for row in data:
+            if row["question"] is not None and row["question"] not in question_ids:
+                question_ids[row["question"]] = len(question_ids)
+            if row["answer"] is not None and row["answer"] not in answer_ids:
+                answer_ids[row["answer"]] = len(answer_ids)
 
         for row in data:
             if row["question"] is None or row["answer"] is None:

{mteb-2.1.9.dist-info → mteb-2.1.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mteb
-Version: 2.1.9
+Version: 2.1.10
 Summary: Massive Text Embedding Benchmark
 Author-email: MTEB Contributors <niklas@huggingface.co>, Kenneth Enevoldsen <kenneth.enevoldsen@cas.au.dk>, Nouamane Tazi <nouamane@huggingface.co>, Nils Reimers <info@nils-reimers.de>
 Maintainer-email: Kenneth Enevoldsen <kenneth.enevoldsen@cas.au.dk>, Roman Solomatin <risolomatin@gmail.com>, Isaac Chung <chungisaac1217@gmail.com>

{mteb-2.1.9.dist-info → mteb-2.1.10.dist-info}/RECORD

@@ -2326,12 +2326,12 @@ mteb/tasks/retrieval/jpn/nlp_journal_abs_intro_retrieval.py,sha256=EEOQpTC6vEPUL
 mteb/tasks/retrieval/jpn/nlp_journal_title_abs_retrieval.py,sha256=JOOW_5pRKHzVn8wTOY0fhxLJ6Ns7wlQHoGHGIYVovAQ,3056
 mteb/tasks/retrieval/jpn/nlp_journal_title_intro_retrieval.py,sha256=aVFTFiANWrIz68FjHv9KBqlhpWlsmi9EAP052gECzaU,3078
 mteb/tasks/retrieval/kat/__init__.py,sha256=H4phkKqg_yZzkK7T62aCMBzjbGZzLKJ-MngrQlPbW3A,93
-mteb/tasks/retrieval/kat/georgian_faq_retrieval.py,sha256=XKEmWaMuxJraXfMF4k7S8CFy3KdLUphad7z8Nz29jp4,2345
+mteb/tasks/retrieval/kat/georgian_faq_retrieval.py,sha256=4zyodSYCtHtBW9WKIGxFZaTXDrtHuaf3uyfIsDRGBqM,2494
 mteb/tasks/retrieval/kor/__init__.py,sha256=zNjAS2VRjeYX5u4vqev6dGOo_R3i9uSzxAsduZ0po4I,138
 mteb/tasks/retrieval/kor/auto_rag_retrieval.py,sha256=tgffW8zMpDSv1FCOdS4_4SL5zKQj70JVSt_RKs3CgKY,1576
 mteb/tasks/retrieval/kor/ko_strategy_qa.py,sha256=jk13ORetYtF0q36h8ljD6TeTHUwvK5F5ZbDoMCP3eWk,1156
 mteb/tasks/retrieval/multilingual/__init__.py,sha256=mfVGkoB4DO5ktlg8ia-4nImFVmZcqXh1XkgCkIff0tY,6765
-mteb/tasks/retrieval/multilingual/belebele_retrieval.py,sha256=AEShsRxcoCNC2C02dj-go6eFr008NLZ2cnebAmdo4Sk,6956
+mteb/tasks/retrieval/multilingual/belebele_retrieval.py,sha256=gaVLEwuLEwMutMi9V-obpiYKbpllX2QNm2j3MVeebfE,7027
 mteb/tasks/retrieval/multilingual/cross_lingual_semantic_discrimination_wmt19.py,sha256=_6r34ZvRiLVENYcrd87NjilybGaetBwKFEbO29zYmBU,4676
 mteb/tasks/retrieval/multilingual/cross_lingual_semantic_discrimination_wmt21.py,sha256=Puy0PjpRr4M_Bbxdl7oWfa7pQGM04zaRaTNlnhyKejM,4677
 mteb/tasks/retrieval/multilingual/cur_ev1_retrieval.py,sha256=dwzo2sqjamM_xkSiC-jbapyhDFezSJpM4S8KfBsuLPk,4562
@@ -2346,7 +2346,7 @@ mteb/tasks/retrieval/multilingual/mr_tidy_retrieval.py,sha256=3uGnj3O92_02zXZnPW
 mteb/tasks/retrieval/multilingual/multi_long_doc_retrieval.py,sha256=xF4GjBmJVgw6c8VGVh-5QLN_4i_NKeoAzqRWmA_pfnw,2440
 mteb/tasks/retrieval/multilingual/neu_clir2022_retrieval.py,sha256=bkGMvMxG2toYL98kv85BvVpSZ-rVeWvB5FFIzXhdPO4,2749
 mteb/tasks/retrieval/multilingual/neu_clir2023_retrieval.py,sha256=0cALhuU3ZU5c_y7tDIyiMc7Onv-qC7YwfnimZVb8-rg,2793
-mteb/tasks/retrieval/multilingual/public_health_qa_retrieval.py,sha256=CGOTbGuwYNrzbefB76QY88fnb8CdJkN9bPhAssNtLvA,3502
+mteb/tasks/retrieval/multilingual/public_health_qa_retrieval.py,sha256=LJGpx4RkSJPXldN0SlMA6PbG1x8R2l-Hupc9q1xfleg,3667
 mteb/tasks/retrieval/multilingual/ru_sci_bench_retrieval.py,sha256=Mmcvrt_1cIxPfHZfUzSURPZyaaweGiB02im1ZszlS6M,6837
 mteb/tasks/retrieval/multilingual/statcan_dialogue_dataset_retrieval.py,sha256=iFUQUlO_ogBdQBVYBQW3o-AJDQ792yg1pJtRxA5I3Qo,3796
 mteb/tasks/retrieval/multilingual/vdr_multilingual_retrieval.py,sha256=UduWKefwP7bPYxiDlztPEvSWXmTdw0xElglMbPY6XhA,4449
@@ -2554,9 +2554,9 @@ mteb/types/_metadata.py,sha256=NN-W0S6a5TDV7UkpRx1pyWtGF4TyyCyoPUfHOwdeci8,2290
 mteb/types/_result.py,sha256=CRAUc5IvqI3_9SyXDwv-PWLCXwXdZem9RePeYESRtuw,996
 mteb/types/_string_validators.py,sha256=PY-dYq4E8O50VS3bLYdldPWp400fl_WzUjfVSkNWe8U,523
 mteb/types/statistics.py,sha256=YwJsxTf1eaCI_RE-J37a-gK5wDeGAsmkeZKoZCFihSo,3755
-mteb-2.1.9.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mteb-2.1.9.dist-info/METADATA,sha256=yUOXi6O_wkyskXKnHDcDB6SqLZg5Q5Nc_a_qK7Pngpc,13573
-mteb-2.1.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mteb-2.1.9.dist-info/entry_points.txt,sha256=8IJoEJFKoDHmVnNev-qJ9pp4Ln7_1-ma9QsXnzVCzGU,39
-mteb-2.1.9.dist-info/top_level.txt,sha256=OLVIjcQAlWBz0bdmutKlWHLF42FF0hp4uVAg3ZyiG4U,5
-mteb-2.1.9.dist-info/RECORD,,
+mteb-2.1.10.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mteb-2.1.10.dist-info/METADATA,sha256=LClBepxtjXoGssnPn6QgdAukEqJerTX67OC7zoKhdiE,13574
+mteb-2.1.10.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mteb-2.1.10.dist-info/entry_points.txt,sha256=8IJoEJFKoDHmVnNev-qJ9pp4Ln7_1-ma9QsXnzVCzGU,39
+mteb-2.1.10.dist-info/top_level.txt,sha256=OLVIjcQAlWBz0bdmutKlWHLF42FF0hp4uVAg3ZyiG4U,5
+mteb-2.1.10.dist-info/RECORD,,