import mteb

tasks = mteb.get_tasks(tasks=["WebFAQRetrieval"], languages=['vie'])
model = mteb.get_model("openai/text-embedding-3-small")
evaluation = mteb.MTEB(tasks=tasks)

evaluation.run(model, encode_kwargs={"batch_size": 32})

[/usr/local/lib/python3.11/dist-packages/mteb/evaluation/evaluators/RetrievalEvaluator.py](https://localhost:8080/#) in search(self, corpus, queries, top_k, task_name, instructions, request_qid, return_sorted, **kwargs)
    121             )
    122         else:
--> 123             query_embeddings = self.model.encode(
    124                 queries,  # type: ignore
    125                 task_name=task_name,

[/usr/local/lib/python3.11/dist-packages/mteb/evaluation/evaluators/RetrievalEvaluator.py](https://localhost:8080/#) in encode(self, sentences, task_name, prompt_type, **kwargs)
    421                 sentences, task_name, prompt_type=prompt_type, **kwargs
    422             )
--> 423         return self.model.encode(
    424             sentences, task_name=task_name, prompt_type=prompt_type, **kwargs
    425         )

[/usr/local/lib/python3.11/dist-packages/mteb/models/openai_models.py](https://localhost:8080/#) in encode(self, sentences, **kwargs)
    142         all_embeddings = np.zeros((len(sentences), self._embed_dim), dtype=np.float32)
    143         if mask:
--> 144             all_embeddings[mask] = no_empty_embeddings
    145         return all_embeddings
    146 

IndexError: too many indices for array