LangChain学习：Chat with Your Data

from config import api_type, api_key, api_base, api_version, model_name
from langchain.chat_models import AzureChatOpenAI

llm = AzureChatOpenAI(
    openai_api_base=api_base,
    openai_api_version=api_version,
    deployment_name=model_name,
    openai_api_key=api_key,
    openai_api_type=api_type,
    temperature=0.5,
)

## pdf
from langchain.document_loaders import PyPDFLoader
loader = PyPDFLoader("CVPR2015-Appearance-Based-Gaze-Estimation-in-the-Wild.pdf")

pages = loader.load()
print(len(pages))
page = pages[0]
print(page.page_content[0:500])
print(page.metadata)

Appearance-Based Gaze Estimation in the Wild
Xucong Zhang1Yusuke Sugano1Mario Fritz2Andreas Bulling1
1Perceptual User Interfaces Group,2Scalable Learning and Perception Group
Max Planck Institute for Informatics, Saarbr ¨ucken, Germany
{xczhang,sugano,mfritz,bulling }@mpi-inf.mpg.de
Abstract
Appearance-based gaze estimation is believed to work
well in real-world settings, but existing datasets have been
collected under controlled laboratory conditions and meth-
ods have been not evaluated across

{'source': 'CVPR2015-Appearance-Based-Gaze-Estimation-in-the-Wild.pdf', 'page': 0}

from langchain.document_loaders.generic import GenericLoader
from langchain.document_loaders.parsers import OpenAIWhisperParser
from langchain.document_loaders.blob_loaders.youtube_audio import YoutubeAudioLoader

url="https://www.youtube.com/watch?v=jGwO_UgTS7I"
save_dir="youtube/"
loader = GenericLoader(
    YoutubeAudioLoader([url],save_dir),
    OpenAIWhisperParser()
)
docs = loader.load()
docs[0].page_content[0:500]

from langchain.document_loaders import WebBaseLoader

loader = WebBaseLoader("https://michael.blog.csdn.net/article/details/131733577")
docs = loader.load()
print(docs[0].page_content[:500])

from langchain.document_loaders import NotionDirectoryLoader
loader = NotionDirectoryLoader("docs/Notion_DB")
docs = loader.load()

from langchain.text_splitter import RecursiveCharacterTextSplitter, CharacterTextSplitter

chunk_size = 26
chunk_overlap = 4
r_splitter = RecursiveCharacterTextSplitter(
    chunk_size=chunk_size,
    chunk_overlap=chunk_overlap
)
c_splitter = CharacterTextSplitter(
    chunk_size=chunk_size,
    chunk_overlap=chunk_overlap
)
text1 = 'abcdefghijklmnopqrstuvwxyz'
print(r_splitter.split_text(text1))

text2 = 'abcdefghijklmnopqrstuvwxyzabcdefg'
print(r_splitter.split_text(text2))

['abcdefghijklmnopqrstuvwxyz']
['abcdefghijklmnopqrstuvwxyz', 'wxyzabcdefg']

text3 = "a b c d e f g h i j k l m n o p q r s t u v w x y z"
print(r_splitter.split_text(text3))

['a b c d e f g h i j k l m', 'l m n o p q r s t u v w x', 'w x y z']

print(c_splitter.split_text(text3))

['a b c d e f g h i j k l m n o p q r s t u v w x y z']

When writing documents, writers will use document structure to group content. This can convey to the reader, which idea's are related. For example, closely related ideas are in sentances. Similar ideas are in paragraphs. Paragraphs form a document. 

  Paragraphs are often delimited with a carriage return or two carriage returns. Carriage returns are the "backslash n" you see embedded in this string. Sentences have a period at the end, but also, have a space.and words are separated by space.

print(c_splitter.split_text(some_text))

'When writing documents, writers will use document structure to group content. This can convey to the reader, which idea\'s are related. For example, closely related ideas are in sentances. Similar ideas are in paragraphs. Paragraphs form a document. \n\n Paragraphs are often delimited with a carriage return or two carriage returns. Carriage returns are the "backslash n" you see embedded in this string. Sentences have a period at the end, but also,'

'have a space.and words are separated by space.'

print(r_splitter.split_text(some_text))

"When writing documents, writers will use document structure to group content. This can convey to the reader, which idea's are related. For example, closely related ideas are in sentances. Similar ideas are in paragraphs. Paragraphs form a document."

'Paragraphs are often delimited with a carriage return or two carriage returns. Carriage returns are the "backslash n" you see embedded in this string. Sentences have a period at the end, but also, have a space.and words are separated by space.'

r_splitter = RecursiveCharacterTextSplitter(
    chunk_size=150,
    chunk_overlap=0,
    separators=["\n\n", "\n", "\. ", " ", ""]
)
r_splitter.split_text(some_text)

When writing documents, writers will use document structure to group content. This can convey to the reader, which idea's are related
. For example, closely related ideas are in sentances. Similar ideas are in paragraphs. Paragraphs form a document.
Paragraphs are often delimited with a carriage return or two carriage returns
. Carriage returns are the "backslash n" you see embedded in this string
. Sentences have a period at the end, but also, have a space.and words are separated by space.

r_splitter = RecursiveCharacterTextSplitter(
    chunk_size=150,
    chunk_overlap=0,
    separators=["\n\n", "\n", "(?<=\. )", " ", ""]
)

When writing documents, writers will use document structure to group content. This can convey to the reader, which idea's are related.
For example, closely related ideas are in sentances. Similar ideas are in paragraphs. Paragraphs form a document.
Paragraphs are often delimited with a carriage return or two carriage returns.
Carriage returns are the "backslash n" you see embedded in this string.
Sentences have a period at the end, but also, have a space.and words are separated by space.

from langchain.text_splitter import TokenTextSplitter
text_splitter = TokenTextSplitter(chunk_size=1, chunk_overlap=0)
text1 = "foo bar bazzyfoo"
print(text_splitter.split_text(text1))
# ['foo', ' bar', ' b', 'az', 'zy', 'foo']

text1 = "我喜欢学习深度学习的知识"
print(text_splitter.split_text(text1))
# ['我喜欢学', '习深度学�', '�的知识']

from langchain.text_splitter import MarkdownHeaderTextSplitter

markdown_document = """# Title\n\n \
## Chapter 1\n\n \
Hi this is Jim\n\n Hi this is Joe\n\n \
### Section \n\n \
Hi this is Lance \n\n 
## Chapter 2\n\n \
Hi this is Molly"""
print(markdown_document)

headers_to_split_on = [
    ("#", "Header 1"),
    ("##", "Header 2"),
    ("###", "Header 3"),
]

markdown_splitter = MarkdownHeaderTextSplitter(
    headers_to_split_on=headers_to_split_on
)
md_header_splits = markdown_splitter.split_text(markdown_document)
for x in md_header_splits:
    print(x)

page_content='Hi this is Jim  \nHi this is Joe' metadata={'Header 1': 'Title', 'Header 2': 'Chapter 1'}
page_content='Hi this is Lance' metadata={'Header 1': 'Title', 'Header 2': 'Chapter 1', 'Header 3': 'Section'}
page_content='Hi this is Molly' metadata={'Header 1': 'Title', 'Header 2': 'Chapter 2'}

loader = NotionDirectoryLoader("./md/")
docs = loader.load()
txt = ' '.join([d.page_content for d in docs])

headers_to_split_on = [
    ("#", "Header 1"),
    ("##", "Header 2"),
]
markdown_splitter = MarkdownHeaderTextSplitter(
    headers_to_split_on=headers_to_split_on
)
md_header_splits = markdown_splitter.split_text(txt)

for x in md_header_splits:
    print(x)

page_content='概要。。  \n### 1. 深度学习的发展史  \n深度学习。。。' metadata={'Header 1': 'blog', 'Header 2': '第一章'}
page_content='概要2。。' metadata={'Header 1': 'blog', 'Header 2': '第二章'}

from langchain.document_loaders import PyPDFLoader

# Load PDF
loaders = [
    # Duplicate documents on purpose - messy data
    PyPDFLoader("docs/cs229_lectures/MachineLearning-Lecture01.pdf"),
    PyPDFLoader("docs/cs229_lectures/MachineLearning-Lecture01.pdf"),
    PyPDFLoader("docs/cs229_lectures/MachineLearning-Lecture02.pdf"),
    PyPDFLoader("docs/cs229_lectures/MachineLearning-Lecture03.pdf")
]
docs = []
for loader in loaders:
    docs.extend(loader.load())

# Split
from langchain.text_splitter import RecursiveCharacterTextSplitter
text_splitter = RecursiveCharacterTextSplitter(
    chunk_size = 1500,
    chunk_overlap = 150
)
splits = text_splitter.split_documents(docs)

# pip install chromadb
from langchain.embeddings.openai import OpenAIEmbeddings
embedding = OpenAIEmbeddings()

from langchain.vectorstores import Chroma
persist_directory = 'docs/chroma/'
vectordb = Chroma.from_documents(
    documents=splits,
    embedding=embedding,
    persist_directory=persist_directory
)

print(vectordb._collection.count())
 # 显示存储了多少个文档切片 splits

question = "is there an email i can ask for help"
docs = vectordb.similarity_search(question,k=3)
print(docs[0].page_content)

vectordb.persist() # 保存

docs_mmr = vectordb.max_marginal_relevance_search(question,k=3)

docs = vectordb.similarity_search(
    question,
    k=3,
    filter={"source":"docs/cs229_lectures/MachineLearning-Lecture03.pdf"}
)

from langchain.llms import OpenAI
from langchain.retrievers.self_query.base import SelfQueryRetriever
from langchain.chains.query_constructor.base import AttributeInfo

metadata_field_info = [
    AttributeInfo(
        name="source",
        description="The lecture the chunk is from, should be one of `docs/cs229_lectures/MachineLearning-Lecture01.pdf`, `docs/cs229_lectures/MachineLearning-Lecture02.pdf`, or `docs/cs229_lectures/MachineLearning-Lecture03.pdf`",
        type="string",
    ),
    AttributeInfo(
        name="page",
        description="The page from the lecture",
        type="integer",
    ),
]

document_content_description = "Lecture notes"
llm = OpenAI(temperature=0)
retriever = SelfQueryRetriever.from_llm(
    llm,
    vectordb,
    document_content_description,
    metadata_field_info,
    verbose=True
)

question = "what did they say about regression in the third lecture?"
docs = retriever.get_relevant_documents(question)

from langchain.retrievers import ContextualCompressionRetriever
from langchain.retrievers.document_compressors import LLMChainExtractor

compressor = LLMChainExtractor.from_llm(llm)
compression_retriever = ContextualCompressionRetriever(
    base_compressor=compressor,
    base_retriever=vectordb.as_retriever()
)

compressed_docs = compression_retriever.get_relevant_documents(question)

base_retriever=vectordb.as_retriever(search_type = "mmr")

from langchain.retrievers import SVMRetriever
from langchain.retrievers import TFIDFRetriever
from langchain.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter

svm_retriever = SVMRetriever.from_texts(splits,embedding)
tfidf_retriever = TFIDFRetriever.from_texts(splits)

docs_svm=svm_retriever.get_relevant_documents(question)
docs_tfidf=tfidf_retriever.get_relevant_documents(question)

from langchain.chains import RetrievalQA

qa_chain = RetrievalQA.from_chain_type(
    llm,
    retriever=vectordb.as_retriever()
)
result = qa_chain({"query": question})

from langchain.prompts import PromptTemplate

template = """使用以下context来回答问题。
如果你不知道答案，就说你不知道，不要试图编造答案。
最多使用三句话。尽量使答案简明扼要。
总是在回答的最后说“谢谢你的提问！”。
{context}
问题：{question}
有用的答案："""
QA_CHAIN_PROMPT = PromptTemplate.from_template(template)

qa_chain = RetrievalQA.from_chain_type(
    llm,
    retriever=vectordb.as_retriever(),
    return_source_documents=True,
    chain_type_kwargs={"prompt": QA_CHAIN_PROMPT}
)

question = "概率论是课程的主题吗？"
result = qa_chain({"query": question})
print(result["result"])
# '是的，概率论是这门课程的主题之一，但不是唯一的主题。'
print(result["source_documents"][0])
# 打印相关来源

from langchain.memory import ConversationBufferMemory
memory = ConversationBufferMemory(
    memory_key="chat_history",
    return_messages=True
)

from langchain.chains import ConversationalRetrievalChain
retriever=vectordb.as_retriever()
qa = ConversationalRetrievalChain.from_llm(
    llm,
    retriever=retriever,
    memory=memory
)

question = "我没有学过概率论，可以上这个课程吗？"
result = qa({"question": question})
print(result['answer'])

from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter
from langchain.vectorstores import DocArrayInMemorySearch
from langchain.document_loaders import TextLoader
from langchain.chains import RetrievalQA,  ConversationalRetrievalChain
from langchain.memory import ConversationBufferMemory
from langchain.chat_models import ChatOpenAI
from langchain.document_loaders import TextLoader
from langchain.document_loaders import PyPDFLoader

def load_db(file, chain_type, k):
    # load documents
    loader = PyPDFLoader(file)
    documents = loader.load()
    # split documents
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=150)
    docs = text_splitter.split_documents(documents)
    # define embedding
    embeddings = OpenAIEmbeddings()
    # create vector database from data
    db = DocArrayInMemorySearch.from_documents(docs, embeddings)
    # define retriever
    retriever = db.as_retriever(search_type="similarity", search_kwargs={"k": k})
    # create a chatbot chain. Memory is managed externally.
    qa = ConversationalRetrievalChain.from_llm(
        llm=ChatOpenAI(model_name=llm_name, temperature=0), 
        chain_type=chain_type, 
        retriever=retriever, 
        return_source_documents=True,
        return_generated_question=True,
    )
    return qa 

import panel as pn
import param

class cbfs(param.Parameterized):
    chat_history = param.List([])
    answer = param.String("")
    db_query  = param.String("")
    db_response = param.List([])
    
    def __init__(self,  **params):
        super(cbfs, self).__init__( **params)
        self.panels = []
        self.loaded_file = "docs/cs229_lectures/MachineLearning-Lecture01.pdf"
        self.qa = load_db(self.loaded_file,"stuff", 4)
    
    def call_load_db(self, count):
        if count == 0 or file_input.value is None:  # init or no file specified :
            return pn.pane.Markdown(f"Loaded File: {self.loaded_file}")
        else:
            file_input.save("temp.pdf")  # local copy
            self.loaded_file = file_input.filename
            button_load.button_style="outline"
            self.qa = load_db("temp.pdf", "stuff", 4)
            button_load.button_style="solid"
        self.clr_history()
        return pn.pane.Markdown(f"Loaded File: {self.loaded_file}")

    def convchain(self, query):
        if not query:
            return pn.WidgetBox(pn.Row('User:', pn.pane.Markdown("", width=600)), scroll=True)
        result = self.qa({"question": query, "chat_history": self.chat_history})
        self.chat_history.extend([(query, result["answer"])])
        self.db_query = result["generated_question"]
        self.db_response = result["source_documents"]
        self.answer = result['answer'] 
        self.panels.extend([
            pn.Row('User:', pn.pane.Markdown(query, width=600)),
            pn.Row('ChatBot:', pn.pane.Markdown(self.answer, width=600, style={'background-color': '#F6F6F6'}))
        ])
        inp.value = ''  #clears loading indicator when cleared
        return pn.WidgetBox(*self.panels,scroll=True)

    @param.depends('db_query ', )
    def get_lquest(self):
        if not self.db_query :
            return pn.Column(
                pn.Row(pn.pane.Markdown(f"Last question to DB:", styles={'background-color': '#F6F6F6'})),
                pn.Row(pn.pane.Str("no DB accesses so far"))
            )
        return pn.Column(
            pn.Row(pn.pane.Markdown(f"DB query:", styles={'background-color': '#F6F6F6'})),
            pn.pane.Str(self.db_query )
        )

    @param.depends('db_response', )
    def get_sources(self):
        if not self.db_response:
            return 
        rlist=[pn.Row(pn.pane.Markdown(f"Result of DB lookup:", styles={'background-color': '#F6F6F6'}))]
        for doc in self.db_response:
            rlist.append(pn.Row(pn.pane.Str(doc)))
        return pn.WidgetBox(*rlist, width=600, scroll=True)

    @param.depends('convchain', 'clr_history') 
    def get_chats(self):
        if not self.chat_history:
            return pn.WidgetBox(pn.Row(pn.pane.Str("No History Yet")), width=600, scroll=True)
        rlist=[pn.Row(pn.pane.Markdown(f"Current Chat History variable", styles={'background-color': '#F6F6F6'}))]
        for exchange in self.chat_history:
            rlist.append(pn.Row(pn.pane.Str(exchange)))
        return pn.WidgetBox(*rlist, width=600, scroll=True)

    def clr_history(self,count=0):
        self.chat_history = []
        return 

cb = cbfs()

file_input = pn.widgets.FileInput(accept='.pdf')
button_load = pn.widgets.Button(name="加载数据库", button_type='primary')
button_clearhistory = pn.widgets.Button(name="清空记录", button_type='warning')
button_clearhistory.on_click(cb.clr_history)
inp = pn.widgets.TextInput( placeholder='输入文本')

bound_button_load = pn.bind(cb.call_load_db, button_load.param.clicks)
conversation = pn.bind(cb.convchain, inp)

jpg_pane = pn.pane.Image( './img/convchain.jpg')

tab1 = pn.Column(
    pn.Row(inp),
    pn.layout.Divider(),
    pn.panel(conversation,  loading_indicator=True, height=300),
    pn.layout.Divider(),
)
tab2= pn.Column(
    pn.panel(cb.get_lquest),
    pn.layout.Divider(),
    pn.panel(cb.get_sources ),
)
tab3= pn.Column(
    pn.panel(cb.get_chats),
    pn.layout.Divider(),
)
tab4=pn.Column(
    pn.Row( file_input, button_load, bound_button_load),
    pn.Row( button_clearhistory, pn.pane.Markdown("清空对话记录，开始新的对话" )),
    pn.layout.Divider(),
    pn.Row(jpg_pane.clone(width=400))
)
dashboard = pn.Column(
    pn.Row(pn.pane.Markdown('# 跟你的文件聊天')),
    pn.Tabs(('聊天', tab1), ('数据库', tab2), ('对话历史', tab3),('配置', tab4))
)
pn.extension()
dashboard