>>> from transformers import DPRContextEncoder, DPRContextEncoderTokenizer
>>> import torch
>>> torch.set_grad_enabled(False)
>>> ctx_encoder = DPRContextEncoder.from_pretrained("facebook/dpr-ctx_encoder-single-nq-base")
>>> ctx_tokenizer = DPRContextEncoderTokenizer.from_pretrained("facebook/dpr-ctx_encoder-single-nq-base")

>>> from datasets import load_dataset
>>> ds = load_dataset('community-datasets/crime_and_punish', split='train[:100]')
>>> ds_with_embeddings = ds.map(lambda example: {'embeddings': ctx_encoder(**ctx_tokenizer(example["line"], return_tensors="pt"))[0][0].numpy()})

>>> ds_with_embeddings.add_faiss_index(column='embeddings')

>>> from transformers import DPRQuestionEncoder, DPRQuestionEncoderTokenizer
>>> q_encoder = DPRQuestionEncoder.from_pretrained("facebook/dpr-question_encoder-single-nq-base")
>>> q_tokenizer = DPRQuestionEncoderTokenizer.from_pretrained("facebook/dpr-question_encoder-single-nq-base")

>>> question = "Is it serious ?"
>>> question_embedding = q_encoder(**q_tokenizer(question, return_tensors="pt"))[0][0].numpy()
>>> scores, retrieved_examples = ds_with_embeddings.get_nearest_examples('embeddings', question_embedding, k=10)
>>> retrieved_examples["line"][0]
'_that_ serious? It is not serious at all. It’s simply a fantasy to amuse\r\n'

>>> faiss_index = ds_with_embeddings.get_index('embeddings').faiss_index
>>> limits, distances, indices = faiss_index.range_search(x=question_embedding.reshape(1, -1), thresh=0.95)

>>> ds_with_embeddings.save_faiss_index('embeddings', 'my_index.faiss')

>>> ds = load_dataset('community-datasets/crime_and_punish', split='train[:100]')
>>> ds.load_faiss_index('embeddings', 'my_index.faiss')

>>> from datasets import load_dataset
>>> squad = load_dataset('rajpurkar/squad', split='validation')

>>> squad.add_elasticsearch_index("context", host="localhost", port="9200")

>>> query = "machine"
>>> scores, retrieved_examples = squad.get_nearest_examples("context", query, k=10)
>>> retrieved_examples["title"][0]
'Computational_complexity_theory'

>>> from datasets import load_dataset
>>> squad = load_dataset('rajpurkar/squad', split='validation')
>>> squad.add_elasticsearch_index("context", host="localhost", port="9200", es_index_name="hf_squad_val_context")
>>> squad.get_index("context").es_index_name
hf_squad_val_context

>>> from datasets import load_dataset
>>> squad = load_dataset('rajpurkar/squad', split='validation')
>>> squad.load_elasticsearch_index("context", host="localhost", port="9200", es_index_name="hf_squad_val_context")
>>> query = "machine"
>>> scores, retrieved_examples = squad.get_nearest_examples("context", query, k=10)

>>> import elasticsearch as es
>>> import elasticsearch.helpers
>>> from elasticsearch import Elasticsearch
>>> es_client = Elasticsearch([{"host": "localhost", "port": "9200"}])  # default client
>>> es_config = {
...     "settings": {
...         "number_of_shards": 1,
...         "analysis": {"analyzer": {"stop_standard": {"type": "standard", " stopwords": "_english_"}}},
...     },
...     "mappings": {"properties": {"text": {"type": "text", "analyzer": "standard", "similarity": "BM25"}}},
... }  # default config
>>> es_index_name = "hf_squad_context"  # name of the index in Elasticsearch
>>> squad.add_elasticsearch_index("context", es_client=es_client, es_config=es_config, es_index_name=es_index_name)