Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from dotenv import load_dotenv | |
| import os | |
| from htmlTemplate import css, bot_template, user_template | |
| import PyPDF2 | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| from langchain_community.embeddings.spacy_embeddings import SpacyEmbeddings | |
| from langchain_community.llms import LlamaCpp | |
| from langchain.embeddings import HuggingFaceEmbeddings | |
| from langchain.vectorstores import FAISS | |
| from langchain.memory import ConversationBufferMemory | |
| from langchain.chains import ConversationalRetrievalChain | |
| from langchain.prompts import PromptTemplate | |
| from sentence_transformers import SentenceTransformer, util | |
| from langchain_openai import AzureOpenAIEmbeddings | |
| from langchain_openai import OpenAIEmbeddings | |
| from langchain_community.embeddings.fastembed import FastEmbedEmbeddings | |
| from langchain_openai import ChatOpenAI | |
| def main(): | |
| load_dotenv() | |
| st.set_page_config( | |
| page_title="PDF Insights AI", | |
| page_icon=":books:", | |
| layout="wide" | |
| ) | |
| st.write(css, unsafe_allow_html=True) | |
| # Welcome section | |
| st.title("📚 PDF Insights AI") | |
| st.markdown(""" | |
| ### Unlock the Knowledge in Your PDFs | |
| - 🤖 AI-powered document analysis | |
| - 💬 Ask questions about your uploaded documents | |
| - 📄 Support for multiple PDF files | |
| """) | |
| 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 = [] | |
| # File upload section | |
| with st.sidebar: | |
| st.header("📤 Upload Documents") | |
| pdf_docs = st.file_uploader( | |
| "Upload your PDFs here", | |
| type=['pdf'], | |
| accept_multiple_files=True, | |
| help="Upload PDF files to analyze. Max file size: 200MB" | |
| ) | |
| # File validation | |
| if pdf_docs: | |
| for doc in pdf_docs: | |
| if doc.size > 200 * 1024 * 1024: # 200 MB | |
| st.error(f"File {doc.name} is too large. Maximum file size is 200MB.") | |
| pdf_docs.remove(doc) | |
| if st.button("Process Documents", type="primary"): | |
| if not pdf_docs: | |
| st.warning("Please upload at least one PDF file.") | |
| else: | |
| with st.spinner("Processing your documents..."): | |
| try: | |
| # get pdf text | |
| content, metadata = prepare_docs(pdf_docs) | |
| # get the text chunks | |
| split_docs = get_text_chunks(content, metadata) | |
| # create vector store | |
| vectorstore = ingest_into_vectordb(split_docs) | |
| # create conversation chain | |
| st.session_state.conversation = get_conversation_chain(vectorstore) | |
| st.success("Documents processed successfully! You can now ask questions.") | |
| except Exception as e: | |
| st.error(f"An error occurred while processing documents: {str(e)}") | |
| # Question input section | |
| user_question = st.text_input( | |
| "📝 Ask a question about your documents", | |
| placeholder="What insights can you provide from these documents?" | |
| ) | |
| if user_question: | |
| if st.session_state.conversation is None: | |
| st.warning("Please upload and process documents first.") | |
| else: | |
| handle_userinput(user_question) |