|
import os
|
|
from langchain_community.vectorstores import FAISS
|
|
from langchain_openai import OpenAIEmbeddings
|
|
from langchain.chains.conversational_retrieval.base import ConversationalRetrievalChain
|
|
from PyPDF2 import PdfReader
|
|
|
|
|
|
from langchain.text_splitter import CharacterTextSplitter
|
|
from langchain_openai import ChatOpenAI
|
|
from langchain.memory import ConversationBufferMemory
|
|
from langchain.chains import ConversationalRetrievalChain
|
|
|
|
OPENAI_API_KEY = "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"
|
|
os.environ['OPENAI_API_KEY'] = OPENAI_API_KEY
|
|
|
|
|
|
def get_pdf_text(pdf_docs):
|
|
text = ""
|
|
for pdf in pdf_docs:
|
|
pdf_reader = PdfReader(pdf)
|
|
for page in pdf_reader.pages:
|
|
text += page.extract_text()
|
|
return text
|
|
|
|
def get_text_chunks(text):
|
|
text_splitter = CharacterTextSplitter(
|
|
separator="\n",
|
|
chunk_size=1000,
|
|
chunk_overlap=200,
|
|
length_function=len
|
|
)
|
|
chunks = text_splitter.split_text(text)
|
|
return chunks
|
|
|
|
def get_vectorstore(text_chunks):
|
|
embeddings = OpenAIEmbeddings()
|
|
vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
|
|
return vectorstore
|
|
|
|
|
|
def get_conversation_chain(vectorstore):
|
|
llm = ChatOpenAI()
|
|
memory = ConversationBufferMemory(
|
|
memory_key='chat_history', return_messages=True)
|
|
conversation_chain = ConversationalRetrievalChain.from_llm(
|
|
llm=llm,
|
|
retriever=vectorstore.as_retriever(),
|
|
memory=memory
|
|
)
|
|
return conversation_chain
|
|
|
|
pdf_docs = [open("train.pdf","rb")]
|
|
raw_text = get_pdf_text(pdf_docs)
|
|
text_chunks = get_text_chunks(raw_text)
|
|
vectorstore = get_vectorstore(text_chunks)
|
|
conversation_chain = get_conversation_chain(vectorstore)
|
|
while True:
|
|
user_question = input("You: ")
|
|
response = conversation_chain.invoke({'question': user_question})
|
|
print(f"GPT: {response.get('answer')}") |
