Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from langchain.prompts import PromptTemplate | |
| from langchain.chains.question_answering import load_qa_chain | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| from langchain_community.vectorstores.faiss import FAISS | |
| from langchain_google_genai import GoogleGenerativeAIEmbeddings, ChatGoogleGenerativeAI | |
| from dotenv import load_dotenv | |
| import PyPDF2 | |
| import os | |
| import io | |
| # Set page configuration | |
| st.set_page_config(layout="centered") | |
| st.markdown("<h1 style='font-size:24px;'>PDF ChatBot by Ali & Arooj</h1>", unsafe_allow_html=True) | |
| # Load environment variables from .env file | |
| load_dotenv() | |
| # Retrieve API key from environment variable | |
| google_api_key = os.getenv("GOOGLE_API_KEY") | |
| # Check if the API key is available | |
| if google_api_key is None: | |
| st.warning("API key not found. Please set the google_api_key environment variable.") | |
| st.stop() | |
| uploaded_file = st.file_uploader("Your PDF file here", type=["pdf", "docx"]) | |
| # Prompt template | |
| prompt_template = """ | |
| Answer the question as detailed as possible from the provided context, | |
| make sure to provide all the details, if the answer is not in | |
| provided context just say, "answer is not available in the context", | |
| don't provide the wrong answer\n\n | |
| Context:\n {context}?\n | |
| Question: \n{question}\n | |
| Answer: | |
| """ | |
| # Additional prompts | |
| prompt_template += """ | |
| -------------------------------------------------- | |
| Prompt Suggestions: | |
| 1. Summarize the primary theme of the context. | |
| 2. Elaborate on the crucial concepts highlighted in the context. | |
| ... | |
| 20. Cite case studies or examples that demonstrate the concepts discussed in the context. | |
| """ | |
| # Function to process PDF and DOCX files | |
| def process_files(uploaded_file): | |
| if uploaded_file is not None: | |
| st.text("File Uploaded Successfully!") | |
| # Check file type and process accordingly | |
| if uploaded_file.type == "application/pdf": | |
| # PDF Processing | |
| pdf_data = uploaded_file.read() | |
| pdf_reader = PyPDF2.PdfReader(io.BytesIO(pdf_data)) | |
| pdf_pages = pdf_reader.pages | |
| context = "\n\n".join(page.extract_text() for page in pdf_pages) | |
| text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=200) | |
| texts = text_splitter.split_text(context) | |
| embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001") | |
| vector_index = FAISS.from_texts(texts, embeddings).as_retriever() | |
| elif uploaded_file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document": | |
| # DOCX Processing (if needed) | |
| pass | |
| else: | |
| st.warning("Unsupported file format. Please upload PDF or DOCX.") | |
| st.stop() | |
| user_question = st.text_input("Ask Anything from PDF:", "") | |
| if st.button("Get Answer"): | |
| if user_question: | |
| with st.spinner("Processing..."): | |
| docs = vector_index.get_relevant_documents(user_question) | |
| prompt = PromptTemplate(template=prompt_template, input_variables=['context', 'question']) | |
| model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3, api_key=google_api_key) | |
| chain = load_qa_chain(model, chain_type="stuff", prompt=prompt) | |
| response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True) | |
| st.subheader("Answer:") | |
| st.write(response['output_text']) | |
| else: | |
| st.warning("Please Ask.") | |
| # Main function | |
| def main(): | |
| process_files(uploaded_file) | |
| if __name__ == "__main__": | |
| main() | |