Spaces:
Running
Running
| import streamlit as st | |
| from dotenv import load_dotenv | |
| import sys | |
| from PyPDF2 import PdfReader | |
| from langchain_community.llms import OpenAI | |
| from langchain_community.chat_models import ChatOpenAI | |
| from langchain_text_splitters import CharacterTextSplitter | |
| from langchain_openai.embeddings import OpenAIEmbeddings | |
| from langchain_community.embeddings import HuggingFaceInstructEmbeddings | |
| from langchain_community.vectorstores import FAISS | |
| from langchain.memory import ConversationBufferMemory | |
| from langchain.chains import ConversationalRetrievalChain | |
| from langchain.retrievers import ContextualCompressionRetriever | |
| from langchain.retrievers.document_compressors import LLMChainExtractor | |
| from langchain.retrievers import MultiQueryRetriever | |
| from langchain.chains import RetrievalQA | |
| from langchain.llms import OpenAI , Cohere | |
| from langchain_deepseek import ChatDeepSeek | |
| def get_pdf_text(pdf_docs): | |
| text = "" | |
| pdf_reader = PdfReader(pdf_docs) | |
| 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, | |
| is_separator_regex=False,) | |
| chunks = text_splitter.split_text(text) | |
| return chunks | |
| def get_vectorstore(text_chunks): | |
| embeddings = OpenAIEmbeddings() | |
| # embeddings = HuggingFaceInstructEmbeddings(model_name = "hkunlp/instructor-large") | |
| vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings) | |
| return vectorstore | |
| def ll_retriver(vectorstore): | |
| llm = OpenAI(temperature=0) | |
| llm_based_retriver=MultiQueryRetriever.from_llm( | |
| retriever=vectorstore.as_retriever(), | |
| llm=llm | |
| ) | |
| return llm_based_retriver | |
| def chain(llm_based_retriever): | |
| llm = OpenAI(temperature=0) | |
| QA_Chain = RetrievalQA.from_chain_type( | |
| llm=llm, | |
| chain_type="stuff", | |
| retriever=llm_based_retriever | |
| ) | |
| return QA_Chain | |
| def main(): | |
| load_dotenv() | |
| st.set_page_config(page_title = "Chat with a PDFs",page_icon=":books:") | |
| if "conversation" not in st.session_state: | |
| st.session_state.conversation = None | |
| if "Q_A_Chain" not in st.session_state: | |
| st.session_state.Q_A_Chain = None | |
| st.header("Chat with PDF :books:") | |
| # question = st.text_input("Ask a Question about your document:") | |
| with st.sidebar: | |
| st.subheader("Upload your PDF") | |
| pdf_docs = st.file_uploader("Upload your PDF here then Process") | |
| if st.button("Process"): | |
| with st.spinner("Processing"): | |
| # get the raw PDF context | |
| raw_text = get_pdf_text(pdf_docs) | |
| # st.write(raw_text) | |
| # get the chunks | |
| text_chunks = get_text_chunks(raw_text) | |
| # st.write(text_chunks) | |
| #Create Vector Store | |
| vectorstore = get_vectorstore(text_chunks) | |
| # Conversation chain | |
| llm_based_retriver = ll_retriver(vectorstore) | |
| st.session_state.Q_A_Chain = chain(llm_based_retriver) | |
| st.success("PDF processed successfully, you can now ask Questions.") | |
| if st.session_state.Q_A_Chain: | |
| question = st.text_input("Ask a Question about your document:") | |
| if st.button("Submit Question"): | |
| if question: | |
| with st.spinner("Getting answer..."): | |
| docs = st.session_state.Q_A_Chain({"query":question}) | |
| st.write(docs['result']) | |
| if __name__ == "__main__": | |
| main() |