import sys

sys.path.append('..')
from text2vec import SentenceModel
from text2vec import Word2Vec


def compute_emb(model):
    # Embed a list of sentences
    sentences = [
        '卡',
        '银行卡',
        '如何更换花呗绑定银行卡',
        '花呗更改绑定银行卡',
        'This framework generates embeddings for each input sentence',
        'Sentences are passed as a list of string.',
        'The quick brown fox jumps over the lazy dog.'
    ]
    sentence_embeddings = model.encode(sentences)
    print(type(sentence_embeddings), sentence_embeddings.shape)

    # The result is a list of sentence embeddings as numpy arrays
    for sentence, embedding in zip(sentences, sentence_embeddings):
        print("Sentence:", sentence)
        print("Embedding shape:", embedding.shape)
        print("Embedding head:", embedding[:10])
        print()


if __name__ == "__main__":
    # 中文句向量模型(CoSENT)，中文语义匹配任务推荐，支持fine-tune继续训练
    t2v_model = SentenceModel("shibing624/text2vec-base-chinese")
    compute_emb(t2v_model)

    # 支持多语言的句向量模型（Sentence-BERT），英文语义匹配任务推荐，支持fine-tune继续训练
    sbert_model = SentenceModel("sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2")
    compute_emb(sbert_model)

    # 中文词向量模型(word2vec)，中文字面匹配任务和冷启动适用
    w2v_model = Word2Vec("w2v-light-tencent-chinese")
    compute_emb(w2v_model)

import os
import torch
from transformers import AutoTokenizer, AutoModel

os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"


# Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0]  # First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('shibing624/text2vec-base-chinese')
model = AutoModel.from_pretrained('shibing624/text2vec-base-chinese')
sentences = ['如何更换花呗绑定银行卡', '花呗更改绑定银行卡']
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)

from sentence_transformers import SentenceTransformer

m = SentenceTransformer("shibing624/text2vec-base-chinese")
sentences = ['如何更换花呗绑定银行卡', '花呗更改绑定银行卡']

sentence_embeddings = m.encode(sentences)
print("Sentence embeddings:")
print(sentence_embeddings)

import sys

sys.path.append('..')
from text2vec import Similarity

# Two lists of sentences
sentences1 = ['如何更换花呗绑定银行卡',
              'The cat sits outside',
              'A man is playing guitar',
              'The new movie is awesome']

sentences2 = ['花呗更改绑定银行卡',
              'The dog plays in the garden',
              'A woman watches TV',
              'The new movie is so great']

sim_model = Similarity()
for i in range(len(sentences1)):
    for j in range(len(sentences2)):
        score = sim_model.get_score(sentences1[i], sentences2[j])
        print("{} \t\t {} \t\t Score: {:.4f}".format(sentences1[i], sentences2[j], score))

import sys

sys.path.append('..')
from text2vec import SentenceModel, cos_sim, semantic_search

embedder = SentenceModel()

# Corpus with example sentences
corpus = [
    '花呗更改绑定银行卡',
    '我什么时候开通了花呗',
    'A man is eating food.',
    'A man is eating a piece of bread.',
    'The girl is carrying a baby.',
    'A man is riding a horse.',
    'A woman is playing violin.',
    'Two men pushed carts through the woods.',
    'A man is riding a white horse on an enclosed ground.',
    'A monkey is playing drums.',
    'A cheetah is running behind its prey.'
]
corpus_embeddings = embedder.encode(corpus)

# Query sentences:
queries = [
    '如何更换花呗绑定银行卡',
    'A man is eating pasta.',
    'Someone in a gorilla costume is playing a set of drums.',
    'A cheetah chases prey on across a field.']

for query in queries:
    query_embedding = embedder.encode(query)
    hits = semantic_search(query_embedding, corpus_embeddings, top_k=5)
    print("\n\n======================\n\n")
    print("Query:", query)
    print("\nTop 5 most similar sentences in corpus:")
    hits = hits[0]  # Get the hits for the first query
    for hit in hits:
        print(corpus[hit['corpus_id']], "(Score: {:.4f})".format(hit['score']))

from similarities import Similarity

m = Similarity()
r = m.similarity('如何更换花呗绑定银行卡', '花呗更改绑定银行卡')
print(f"similarity score: {float(r)}")  # similarity score: 0.855146050453186

from jina import Flow

port = 50001
f = Flow(port=port).add(
    uses='jinahub://Text2vecEncoder',
    uses_with={'model_name': 'shibing624/text2vec-base-chinese'}
)

with f:
    # backend server forever
    f.block()

from jina import Client
from docarray import Document, DocumentArray

port = 50001

c = Client(port=port)

data = ['如何更换花呗绑定银行卡',
        '花呗更改绑定银行卡']
print("data:", data)
print('data embs:')
r = c.post('/', inputs=DocumentArray([Document(text='如何更换花呗绑定银行卡'), Document(text='花呗更改绑定银行卡')]))
print(r.embeddings)

from datasets import load_dataset

dataset = load_dataset("shibing624/nli_zh", "STS-B") # ATEC or BQ or LCQMC or PAWSX or STS-B
print(dataset)
print(dataset['test'][0])