Opensearch Neural Sparse Encoding Doc V3 Distill

🚀 opensearch-neural-sparse-encoding-doc-v3-distill

本項目是一個學習型稀疏檢索模型，可將文檔編碼為30522維的稀疏向量，支持使用Lucene倒排索引進行學習型稀疏檢索，在搜索相關性、效率和推理速度上表現出色。

🚀 快速開始

本模型旨在在OpenSearch集群內運行，但也可以使用HuggingFace模型API在集群外使用。以下是使用示例：

import json
import itertools
import torch

from transformers import AutoModelForMaskedLM, AutoTokenizer


# get sparse vector from dense vectors with shape batch_size * seq_len * vocab_size
def get_sparse_vector(feature, output):
    values, _ = torch.max(output*feature["attention_mask"].unsqueeze(-1), dim=1)
    # note we update the activation for v3 model
    values = torch.log(1 + torch.log(1 + torch.relu(values)))
    values[:,special_token_ids] = 0
    return values
    
# transform the sparse vector to a dict of (token, weight)
def transform_sparse_vector_to_dict(sparse_vector):
    sample_indices,token_indices=torch.nonzero(sparse_vector,as_tuple=True)
    non_zero_values = sparse_vector[(sample_indices,token_indices)].tolist()
    number_of_tokens_for_each_sample = torch.bincount(sample_indices).cpu().tolist()
    tokens = [transform_sparse_vector_to_dict.id_to_token[_id] for _id in token_indices.tolist()]

    output = []
    end_idxs = list(itertools.accumulate([0]+number_of_tokens_for_each_sample))
    for i in range(len(end_idxs)-1):
        token_strings = tokens[end_idxs[i]:end_idxs[i+1]]
        weights = non_zero_values[end_idxs[i]:end_idxs[i+1]]
        output.append(dict(zip(token_strings, weights)))
    return output
    
# download the idf file from model hub. idf is used to give weights for query tokens
def get_tokenizer_idf(tokenizer):
    from huggingface_hub import hf_hub_download
    local_cached_path = hf_hub_download(repo_id="opensearch-project/opensearch-neural-sparse-encoding-doc-v3-distill", filename="idf.json")
    with open(local_cached_path) as f:
        idf = json.load(f)
    idf_vector = [0]*tokenizer.vocab_size
    for token,weight in idf.items():
        _id = tokenizer._convert_token_to_id_with_added_voc(token)
        idf_vector[_id]=weight
    return torch.tensor(idf_vector)

# load the model
model = AutoModelForMaskedLM.from_pretrained("opensearch-project/opensearch-neural-sparse-encoding-doc-v3-distill")
tokenizer = AutoTokenizer.from_pretrained("opensearch-project/opensearch-neural-sparse-encoding-doc-v3-distill")
idf = get_tokenizer_idf(tokenizer)

# set the special tokens and id_to_token transform for post-process
special_token_ids = [tokenizer.vocab[token] for token in tokenizer.special_tokens_map.values()]
get_sparse_vector.special_token_ids = special_token_ids
id_to_token = ["" for i in range(tokenizer.vocab_size)]
for token, _id in tokenizer.vocab.items():
    id_to_token[_id] = token
transform_sparse_vector_to_dict.id_to_token = id_to_token



query = "What's the weather in ny now?"
document = "Currently New York is rainy."

# encode the query
feature_query = tokenizer([query], padding=True, truncation=True, return_tensors='pt', return_token_type_ids=False)
input_ids = feature_query["input_ids"]
batch_size = input_ids.shape[0]
query_vector = torch.zeros(batch_size, tokenizer.vocab_size)
query_vector[torch.arange(batch_size).unsqueeze(-1), input_ids] = 1
query_sparse_vector = query_vector*idf

# encode the document
feature_document = tokenizer([document], padding=True, truncation=True, return_tensors='pt', return_token_type_ids=False)
output = model(**feature_document)[0]
document_sparse_vector = get_sparse_vector(feature_document, output)


# get similarity score
sim_score = torch.matmul(query_sparse_vector[0],document_sparse_vector[0])
print(sim_score)   # tensor(11.1105, grad_fn=<DotBackward0>)


query_token_weight = transform_sparse_vector_to_dict(query_sparse_vector)[0]
document_query_token_weight = transform_sparse_vector_to_dict(document_sparse_vector)[0]
for token in sorted(query_token_weight, key=lambda x:query_token_weight[x], reverse=True):
    if token in document_query_token_weight:
        print("score in query: %.4f, score in document: %.4f, token: %s"%(query_token_weight[token],document_query_token_weight[token],token))
        

        
# result:
# score in query: 5.7729, score in document: 0.8049, token: ny
# score in query: 4.5684, score in document: 0.9710, token: weather
# score in query: 3.5895, score in document: 0.4720, token: now
# score in query: 3.3313, score in document: 0.0286, token: ?
# score in query: 2.7699, score in document: 0.0787, token: what
# score in query: 0.4989, score in document: 0.0417, token: in

上述代碼示例展示了神經稀疏搜索的一個示例。儘管原始查詢和文檔中沒有重疊的標記，但該模型仍能實現良好的匹配。

✨ 主要特性

• 搜索相關性高：v3系列模型在搜索相關性上優於v1和v2系列，在不同數據集上表現出色。
• 效率和推理速度快：在推理和檢索效率（FLOPS）上有較好的表現。
• 支持學習型稀疏檢索：OpenSearch神經稀疏特性支持使用Lucene倒排索引進行學習型稀疏檢索。

📚 詳細文檔

選擇模型

選擇模型時應考慮搜索相關性、模型推理和檢索效率（FLOPS）。我們在BEIR基準測試的一個子集上對模型性能進行了基準測試：TrecCovid、NFCorpus、NQ、HotpotQA、FiQA、ArguAna、Touche、DBPedia、SCIDOCS、FEVER、Climate FEVER、SciFact、Quora。

總體而言，v3系列模型在搜索相關性、效率和推理速度上優於v1和v2系列。具體優缺點可能因不同數據集而異。

模型概述

• 論文：Exploring $\ell_0$ Sparsification for Inference-free Sparse Retrievers
• 代碼：opensearch-sparse-model-tuning-sample

這是一個學習型稀疏檢索模型。它將文檔編碼為30522維的稀疏向量。對於查詢，它僅使用分詞器和權重查找表來生成稀疏向量。非零維度索引表示詞彙表中對應的標記，權重表示標記的重要性。相似度得分是查詢/文檔稀疏向量的內積。

訓練數據集包括MS MARCO、eli5_question_answer、squad_pairs、WikiAnswers、yahoo_answers_title_question、gooaq_pairs、stackexchange_duplicate_questions_body_body、wikihow、S2ORC_title_abstract、stackexchange_duplicate_questions_title-body_title-body、yahoo_answers_question_answer、searchQA_top5_snippets、stackexchange_duplicate_questions_title_title、yahoo_answers_title_answer、fever、fiqa、hotpotqa、nfcorpus、scifact。

OpenSearch神經稀疏特性支持使用Lucene倒排索引進行學習型稀疏檢索。鏈接：https://opensearch.org/docs/latest/query-dsl/specialized/neural-sparse/。可以使用OpenSearch高級API進行索引和搜索。

詳細搜索相關性

📄 許可證

本項目採用Apache v2.0許可證。

版權信息

版權歸OpenSearch貢獻者所有。詳情請見NOTICE。