Chroma使用入门以及向量数据库查询入门_chromavectorstore

参考：
https://python.langchain.com/docs/integrations/vectorstores/chroma

import ChatGLM

from langchain_community.document_loaders import PyPDFLoader
import ChatGLM

from langchain_community.vectorstores import Chroma
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_community.embeddings import JinaEmbeddings
from langchain_core.runnables import RunnableParallel, RunnablePassthrough


llm = ChatGLM.ChatGLM_LLM()
# loader = PyPDFLoader("唐诗三百首.pdf")
loader = PyPDFLoader("西游记.pdf")
documents = loader.load_and_split()

embeddings = JinaEmbeddings(
    jina_api_key="jina_c5d02a61c97d4d79b88234362726e94aVLMTvF38wvrElYqpGYSxFtC5Ifhj", model_name="jina-embeddings-v2-base-zh"
)

# 第一次存入本地
# vectorstore = Chroma.from_documents(documents, embeddings,persist_directory="./chroma_db")

# 从本地加载
vectorstore = Chroma(persist_directory="./chroma_db", embedding_function=embeddings)

retriever = vectorstore.as_retriever()
template = """Answer the question based only on the following context:
{context}

Question: {question}
"""
prompt = ChatPromptTemplate.from_template(template)
llm = ChatGLM.ChatGLM_LLM()
output_parser = StrOutputParser()
setup_and_retrieval = RunnableParallel(
    {"context": retriever, "question": RunnablePassthrough()}
)
chain = setup_and_retrieval | prompt | llm | output_parser
print(chain.invoke("第二十二回讲了什么"))




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

1
2
3
4