使用huggingface的text embedding models

from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_community.vectorstores import FAISS
from langchain_community.llms import Tongyi
from langchain_core.runnables import RunnableParallel, RunnablePassthrough
from langchain_community.embeddings import HuggingFaceEmbeddings
import os
import time
os.environ["DASHSCOPE_API_KEY"] = "sk-cc1c8314fdbd43ceaf26ec1824d5dd3b"
llm = Tongyi()

from langchain_community.document_loaders import UnstructuredURLLoader

embeddings = HuggingFaceEmbeddings()

# 记录开始时间
start_time = time.time()
text = "This is a test document."

query_result = embeddings.embed_query(text)

end_time = time.time()
# 计算并打印函数执行时间
execution_time = end_time - start_time
print(f"函数执行时间: {execution_time} 秒")
print(query_result[:3])


urls = [
    "https://en.wikipedia.org/wiki/Android_(operating_system)"
]

loader = UnstructuredURLLoader(urls=urls)
documents = loader.load_and_split()
# print(documents)


# # 第一次存入本地
# vectorstore = FAISS.from_documents(documents, embeddings)
# vectorstore.save_local("faiss_index2")


# 记录开始时间
start_time = time.time()

# # 从本地加载
vectorstore = FAISS.load_local("faiss_index2", embeddings)

retriever = vectorstore.as_retriever()
template = """Answer the question based on the context below. If the
question cannot be answered using the information provided answer
with "I don't know"     

Context: {context}

Question: {question}
"""
prompt = ChatPromptTemplate.from_template(template)

output_parser = StrOutputParser()
setup_and_retrieval = RunnableParallel(
    {"context": retriever, "question": RunnablePassthrough()}
)
chain = setup_and_retrieval | prompt | llm | output_parser
print(chain.invoke("what is android"))
# 计算并打印函数执行时间
end_time = time.time()
execution_time = end_time - start_time
print(f"函数执行时间: {execution_time} 秒")



1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72

上面是使用的默认的模型，以下指定使用 all-MiniLM-L6-v2：

from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_community.vectorstores import FAISS
from langchain_community.llms import Tongyi
from langchain_core.runnables import RunnableParallel, RunnablePassthrough
from langchain_community.embeddings import HuggingFaceEmbeddings
import os
import time
os.environ["DASHSCOPE_API_KEY"] = "sk-cc1c8314fdbd43ceaf26ec1824d5dd3b"
llm = Tongyi()

from langchain_community.document_loaders import UnstructuredURLLoader
model_name = "all-MiniLM-L6-v2"
embeddings = HuggingFaceEmbeddings(
         model_name=model_name,
)

# 记录开始时间
start_time = time.time()
text = "This is a test document."

query_result = embeddings.embed_query(text)

end_time = time.time()
# 计算并打印函数执行时间
execution_time = end_time - start_time
print(f"函数执行时间: {execution_time} 秒")
print(query_result[:3])


urls = [
    "https://en.wikipedia.org/wiki/Android_(operating_system)"
]

loader = UnstructuredURLLoader(urls=urls)
documents = loader.load_and_split()
# print(documents)


# 记录开始时间
start_time = time.time()

# 第一次存入本地
vectorstore = FAISS.from_documents(documents, embeddings)
vectorstore.save_local("faiss_index2")


# # 从本地加载
# vectorstore = FAISS.load_local("faiss_index2", embeddings)

retriever = vectorstore.as_retriever()
template = """Answer the question based on the context below. If the
question cannot be answered using the information provided answer
with "I don't know"     

Context: {context}

Question: {question}
"""
prompt = ChatPromptTemplate.from_template(template)

output_parser = StrOutputParser()
setup_and_retrieval = RunnableParallel(
    {"context": retriever, "question": RunnablePassthrough()}
)
chain = setup_and_retrieval | prompt | llm | output_parser
print(chain.invoke("what is android"))
# 计算并打印函数执行时间
end_time = time.time()
execution_time = end_time - start_time
print(f"函数执行时间: {execution_time} 秒")



1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74

关于可以使用的模型，可以看这里：