| | import csv |
| | import json |
| | import streamlit as st |
| | from dotenv import load_dotenv |
| | from PyPDF2 import PdfReader |
| | from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter |
| | from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings |
| | from langchain.vectorstores import FAISS, Chroma |
| | from langchain.embeddings import HuggingFaceEmbeddings |
| | from langchain.chat_models import ChatOpenAI |
| | from langchain.memory import ConversationBufferMemory |
| | from langchain.chains import ConversationalRetrievalChain |
| | from htmlTemplates import css, bot_template, user_template |
| | from langchain.llms import HuggingFaceHub, LlamaCpp, CTransformers |
| | from langchain.document_loaders import PyPDFLoader, TextLoader, JSONLoader, CSVLoader |
| | import tempfile |
| | import os |
| |
|
| |
|
| | |
| | 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 |
| |
|
| | |
| | |
| | def get_text_file(docs): |
| | temp_dir2 = tempfile.TemporaryDirectory() |
| | temp_filepath2 = os.path.join(temp_dir2.name, docs.name) |
| | with open(temp_filepath2, "wb") as f: |
| | f.write(docs.getvalue()) |
| | txt_loader = TextLoader( |
| | file_path=temp_filepath2, |
| | txt_args={ |
| | "delimiter": " ", |
| | |
| | |
| | } |
| | ) |
| | txt_data = txt_loader.load() |
| | return txt_data |
| |
|
| | def get_csv_file(docs): |
| | temp_dir3 = tempfile.TemporaryDirectory() |
| | temp_filepath3 = os.path.join(temp_dir3.name, docs.name) |
| | with open(temp_filepath3, "wb") as f: |
| | f.write(docs.getvalue()) |
| | csv_loader = CSVLoader( |
| | file_path=temp_filepath3, |
| | csv_args={ |
| | "delimiter": ",", |
| | "quotechar": '"', |
| | "fieldnames": ["name", "school", "address", "phone"], |
| | }, |
| | ) |
| | csv_data = csv_loader.load() |
| | return csv_data |
| |
|
| | def get_json_file(docs): |
| | temp_dir4 = tempfile.TemporaryDirectory() |
| | temp_filepath4 = os.path.join(temp_dir4.name, docs.name) |
| | with open(temp_filepath4, "wb") as f: |
| | f.write(docs.getvalue()) |
| | json_loader = JSONLoader( |
| | file_path=temp_filepath4, |
| | jq_schema='.messages[].content', |
| | text_content=False |
| | ) |
| | json_data = json_loader.load() |
| | return json_data |
| |
|
| | |
| | |
| | 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 |
| |
|
| |
|
| | |
| | def get_vectorstore(text_chunks): |
| | |
| |
|
| | embeddings = OpenAIEmbeddings() |
| | vectorstore = FAISS.from_documents(text_chunks, embeddings) |
| |
|
| | return vectorstore |
| |
|
| |
|
| | def get_conversation_chain(vectorstore): |
| | gpt_model_name = 'gpt-3.5-turbo' |
| | llm = ChatOpenAI(model_name = gpt_model_name) |
| | |
| | |
| | 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 |
| |
|
| | |
| | def handle_userinput(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: |
| | openai_key = st.text_input("Paste your OpenAI API key (sk-...)") |
| | if openai_key: |
| | os.environ["OPENAI_API_KEY"] = openai_key |
| |
|
| | 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"): |
| | |
| | doc_list = [] |
| |
|
| | for file in docs: |
| | print('file - type : ', file.type) |
| | if file.type == 'text/plain': |
| | |
| | doc_list.extend(get_text_file(file)) |
| | elif file.type in ['application/octet-stream', 'application/pdf']: |
| | |
| | doc_list.extend(get_pdf_text(file)) |
| | elif file.type == 'text/csv': |
| | |
| | doc_list.extend(get_csv_file(file)) |
| | elif file.type == 'application/json': |
| | |
| | doc_list.extend(get_json_file(file)) |
| |
|
| | |
| | text_chunks = get_text_chunks(doc_list) |
| |
|
| | |
| | vectorstore = get_vectorstore(text_chunks) |
| |
|
| | |
| | st.session_state.conversation = get_conversation_chain( |
| | vectorstore) |
| |
|
| |
|
| | if __name__ == '__main__': |
| | main() |
| |
|