mteb 2.3.6__py3-none-any.whl → 2.3.7__py3-none-any.whl

mteb/models/model_implementations/openai_models.py

@@ -91,10 +91,6 @@ class OpenAIModel(AbsEncoder):
 
         from openai import NotGiven
 
-        if self.model_name == "text-embedding-ada-002" and self._embed_dim is not None:
-            logger.warning(
-                "Reducing embedding size available only for text-embedding-3-* models"
-            )
         sentences = [text for batch in inputs for text in batch["text"]]
 
         mask_sents = [(i, t) for i, t in enumerate(sentences) if t.strip()]
@@ -122,13 +118,22 @@ class OpenAIModel(AbsEncoder):
 
         no_empty_embeddings = []
 
+        # Set dimensions only for models that support it
+        dimensions = (
+            self._embed_dim or NotGiven()
+            if not self.model_name == "text-embedding-ada-002"
+            else NotGiven()
+        )
+        default_kwargs = dict(
+            model=self.model_name,
+            encoding_format="float",
+            dimensions=dimensions,
+        )
+
         for sublist in tqdm(sublists, leave=False, disable=not show_progress_bar):
             try:
                 response = self._client.embeddings.create(
-                    input=sublist,
-                    model=self.model_name,
-                    encoding_format="float",
-                    dimensions=self._embed_dim or NotGiven(),
+                    input=sublist, **default_kwargs
                 )
             except Exception as e:
                 # Sleep due to too many requests
@@ -138,19 +143,13 @@ class OpenAIModel(AbsEncoder):
                 time.sleep(10)
                 try:
                     response = self._client.embeddings.create(
-                        input=sublist,
-                        model=self.model_name,
-                        encoding_format="float",
-                        dimensions=self._embed_dim or NotGiven(),
+                        input=sublist, **default_kwargs
                     )
                 except Exception as e:
                     logger.info("Sleeping for 60 seconds due to error", e)
                     time.sleep(60)
                     response = self._client.embeddings.create(
-                        input=sublist,
-                        model=self.model_name,
-                        encoding_format="float",
-                        dimensions=self._embed_dim or NotGiven(),
+                        input=sublist, **default_kwargs
                     )
             no_empty_embeddings.extend(self._to_numpy(response))
 

{mteb-2.3.6.dist-info → mteb-2.3.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mteb
-Version: 2.3.6
+Version: 2.3.7
 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-2.3.6.dist-info → mteb-2.3.7.dist-info}/RECORD

@@ -1516,7 +1516,7 @@ mteb/models/model_implementations/nomic_models.py,sha256=mT-v5Gs5-sRH8-ziCw_CtxB
 mteb/models/model_implementations/nomic_models_vision.py,sha256=gEEieMThvw4p-QhRH0G_9-WWTvj-jqOlgFsh6O07dbc,6731
 mteb/models/model_implementations/nvidia_llama_nemoretriever_colemb.py,sha256=14XSv7wGsitu0cF8P3A951gel_Py7PrKlRixkLS4qG4,6203
 mteb/models/model_implementations/nvidia_models.py,sha256=acVverAt77lURkILCVkCdXsWgY1BJoG1-ugB7yIhlIM,21555
-mteb/models/model_implementations/openai_models.py,sha256=2tJyEapIW-GtB3ZOXIHwGjSZGgJl2daE_UsbzH4NhBM,9620
+mteb/models/model_implementations/openai_models.py,sha256=loU6JByNUwRidq7lmcu8iGOtUQvzejw6HVLaF_IKCR0,9352
 mteb/models/model_implementations/openclip_models.py,sha256=W8XcokgLU1nSmMaWpYXkWWizVd3sQezcP02YtF2fXpo,11436
 mteb/models/model_implementations/opensearch_neural_sparse_models.py,sha256=fuxIjOx_kPoDps5C7LW3JllG-AZj4ktqeTNgJESHZh4,8351
 mteb/models/model_implementations/ops_moa_models.py,sha256=luWw1j2iTMx1z1ydLCjvCI89E9Yvge7ruEawivJTmfE,2413
@@ -2573,9 +2573,9 @@ 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-2.3.6.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mteb-2.3.6.dist-info/METADATA,sha256=urz0_67bNhVt17rvN3pZdvMFt_mvxI7MFvamWkNoNjM,13923
-mteb-2.3.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mteb-2.3.6.dist-info/entry_points.txt,sha256=8IJoEJFKoDHmVnNev-qJ9pp4Ln7_1-ma9QsXnzVCzGU,39
-mteb-2.3.6.dist-info/top_level.txt,sha256=OLVIjcQAlWBz0bdmutKlWHLF42FF0hp4uVAg3ZyiG4U,5
-mteb-2.3.6.dist-info/RECORD,,
+mteb-2.3.7.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mteb-2.3.7.dist-info/METADATA,sha256=8WsmZm9cDT-XjdHIF04XscnqFbTmCiudzikksCUJSiw,13923
+mteb-2.3.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mteb-2.3.7.dist-info/entry_points.txt,sha256=8IJoEJFKoDHmVnNev-qJ9pp4Ln7_1-ma9QsXnzVCzGU,39
+mteb-2.3.7.dist-info/top_level.txt,sha256=OLVIjcQAlWBz0bdmutKlWHLF42FF0hp4uVAg3ZyiG4U,5
+mteb-2.3.7.dist-info/RECORD,,