File size: 5,527 Bytes
a1824bb de9afe2 a1824bb de9afe2 a1824bb de9afe2 a1824bb de9afe2 f1aa416 de9afe2 a1824bb de9afe2 a1824bb de9afe2 a1824bb de9afe2 a1824bb de9afe2 a1824bb de9afe2 a1824bb de9afe2 a1824bb de9afe2 a1824bb de9afe2 a1824bb de9afe2 a1824bb de9afe2 a1824bb de9afe2 a1824bb de9afe2 |
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 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 |
import streamlit as st
from dotenv import load_dotenv
from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.embeddings import HuggingFaceEmbeddings # General embeddings from HuggingFace models.
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from htmlTemplates import css, bot_template, user_template
from langchain.llms import LlamaCpp # For loading transformer models.
from langchain.document_loaders import PyPDFLoader, TextLoader, JSONLoader, CSVLoader
import tempfile
import os
from huggingface_hub import hf_hub_download
# PDF ๋ฌธ์๋ก๋ถํฐ ํ
์คํธ๋ฅผ ์ถ์ถํ๋ ํจ์
def get_pdf_text(pdf_docs):
temp_dir = tempfile.TemporaryDirectory()
temp_filepath = os.path.join(temp_dir.name, pdf_docs.name)
with open(temp_filepath, "wb") as f:
f.write(pdf_docs.getvalue())
pdf_loader = PyPDFLoader(temp_filepath)
pdf_doc = pdf_loader.load()
return pdf_doc
# ์ถ๊ฐ๋ ๋ถ๋ถ: python-dotenv ํจํค์ง ์ค์น
import subprocess
subprocess.run(["pip", "install", "python-dotenv"])
# .env ํ์ผ์์ ํ๊ฒฝ ๋ณ์ ๋ก๋
from dotenv import load_dotenv
load_dotenv()
# ๊ณผ์ ๋ถ๋ถ
def get_text_file(docs):
text_loader = TextLoader(docs.name)
return text_loader.load()
def get_csv_file(docs):
csv_loader = CSVLoader(docs.name)
return csv_loader.load()
def get_json_file(docs):
json_loader = JSONLoader(docs.name)
return json_loader.load()
# ๋ฌธ์๋ค์ ์ฒ๋ฆฌํ์ฌ ํ
์คํธ ์ฒญํฌ๋ก ๋๋๋ ํจ์
def get_text_chunks(documents):
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=1000,
chunk_overlap=200,
length_function=len
)
documents = text_splitter.split_documents(documents)
return documents
# ํ
์คํธ ์ฒญํฌ๋ค๋ก๋ถํฐ ๋ฒกํฐ ์คํ ์ด๋ฅผ ์์ฑํ๋ ํจ์
def get_vectorstore(text_chunks):
embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L12-v2',
model_kwargs={'device': 'cpu'})
vectorstore = FAISS.from_documents(text_chunks, embeddings)
return vectorstore
# ๋ํ ์ฒด์ธ ์ค์ ํจ์
def get_conversation_chain(vectorstore):
model_name_or_path = 'TheBloke/Llama-2-7B-chat-GGUF'
model_basename = 'llama-2-7b-chat.Q2_K.gguf'
model_path = hf_hub_download(repo_id=model_name_or_path, filename=model_basename)
llm = LlamaCpp(model_path=model_path,
n_ctx=4086,
input={"temperature": 0.75, "max_length": 2000, "top_p": 1},
verbose=True, )
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
# ์ฌ์ฉ์ ์
๋ ฅ ์ฒ๋ฆฌ ํจ์
def handle_userinput(user_question):
print('user_question => ', user_question)
response = st.session_state.conversation({'question': user_question})
st.session_state.chat_history = response['chat_history']
for i, message in enumerate(st.session_state.chat_history):
if i % 2 == 0:
st.write(user_template.replace(
"{{MSG}}", message.content), unsafe_allow_html=True)
else:
st.write(bot_template.replace(
"{{MSG}}", message.content), unsafe_allow_html=True)
def main():
load_dotenv()
st.set_page_config(page_title="Chat with multiple Files",
page_icon=":books:")
st.write(css, unsafe_allow_html=True)
if "conversation" not in st.session_state:
st.session_state.conversation = None
if "chat_history" not in st.session_state:
st.session_state.chat_history = None
st.header("Chat with multiple Files:")
user_question = st.text_input("Ask a question about your documents:")
if user_question:
handle_userinput(user_question)
with st.sidebar:
st.subheader("Your documents")
docs = st.file_uploader(
"Upload your PDFs here and click on 'Process'", accept_multiple_files=True)
if st.button("Process"):
with st.spinner("Processing"):
# get pdf text
doc_list = []
for file in docs:
print('file - type : ', file.type)
if file.type == 'text/plain':
# file is .txt
doc_list.extend(get_text_file(file))
elif file.type in ['application/octet-stream', 'application/pdf']:
# file is .pdf
doc_list.extend(get_pdf_text(file))
elif file.type == 'text/csv':
# file is .csv
doc_list.extend(get_csv_file(file))
elif file.type == 'application/json':
# file is .json
doc_list.extend(get_json_file(file))
# get the text chunks
text_chunks = get_text_chunks(doc_list)
# create vector store
vectorstore = get_vectorstore(text_chunks)
# create conversation chain
st.session_state.conversation = get_conversation_chain(
vectorstore)
if __name__ == '__main__':
main()
|