Spaces:
Build error
Build error
| import os | |
| from dotenv import load_dotenv | |
| import streamlit as st | |
| import os | |
| from langchain_openai import AzureChatOpenAI | |
| from langchain_openai import AzureOpenAIEmbeddings | |
| from langchain.chains import RetrievalQA | |
| from langchain_community.document_loaders import PyPDFLoader | |
| import streamlit as st | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| import os | |
| import tempfile | |
| from langchain_community.vectorstores import Chroma | |
| load_dotenv() | |
| azure_config = { | |
| "AZURE_OPENAI_ENDPOINT": os.getenv("AZURE_OPENAI_ENDPOINT"), | |
| "AZURE_OPENAI_MODEL_DEPLOYMENT_NAME": os.getenv("AZURE_OPENAI_MODEL_DEPLOYMENT_NAME"), | |
| "AZURE_OPENAI_MODEL_NAME": os.getenv("AZURE_OPENAI_MODEL_NAME"), | |
| "AZURE_OPENAI_API_KEY": os.getenv("AZURE_OPENAI_API_KEY"), | |
| "AZURE_OPENAI_API_VERSION": os.getenv("AZURE_OPENAI_API_VERSION"), | |
| "AZURE_OPENAI_EMBEDDING_ENDPOINT": os.getenv("AZURE_OPENAI_API_VERSION"), | |
| "AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME" : os.getenv("AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME"), | |
| "AZURE_OPENAI_EMBEDDING_NAME": os.getenv("AZURE_OPENAI_EMBEDDING_NAME"), | |
| "AZURE_OPENAI_EMBEDDING_API_KEY": os.getenv("AZURE_OPENAI_EMBEDDING_API_KEY"), | |
| "AZURE_OPENAI_EMBEDDING_API_VERSION" : os.getenv("AZURE_OPENAI_EMBEDDING_API_VERSION") | |
| } | |
| CHROMA_PATH = os.path.join(os.getcwd(), "chroma_db") | |
| st.set_page_config(page_title="PDF chatbot", layout="wide") | |
| st.title("RAG Demo - PDF Q&A") | |
| st.markdown(""" | |
| 1. **Upload Your Documents**: The system accepts multiple PDF files at once, analyzing the content to provide comprehensive insights. | |
| 2. **Ask a Question**: After processing the documents, ask any question related to the content of your uploaded documents for a precise answer. | |
| """) | |
| def main(): | |
| st.header("Ask a question") | |
| # Initialize vector store | |
| embeddings = AzureOpenAIEmbeddings( | |
| model="text-embedding-ada-002", | |
| api_key=azure_config["AZURE_OPENAI_API_KEY"], | |
| api_version="2024-02-01", | |
| azure_endpoint="https://ey-openai.openai.azure.com/openai/deployments/text-embedding-ada-002/embeddings?api-version=2023-05-15" | |
| ) | |
| vectorstore = Chroma( | |
| persist_directory=CHROMA_PATH, | |
| embedding_function=embeddings | |
| ) | |
| with st.sidebar: | |
| st.title("Menu:") | |
| uploaded_files = st.file_uploader( | |
| "Upload your PDF Files and Click on the Submit & Process Button", | |
| accept_multiple_files=True, | |
| key="pdf_uploader") | |
| if st.button("Submit & Process", key="process_button") and uploaded_files: # Check if API key is provided before processing | |
| with st.spinner("Processing..."): | |
| for uploaded_file in uploaded_files: | |
| try: | |
| # Create a temporary file to store the uploaded PDF | |
| with tempfile.NamedTemporaryFile(delete=False, suffix='.pdf') as tmp_file: | |
| tmp_file.write(uploaded_file.getvalue()) | |
| tmp_file_path = tmp_file.name | |
| # Load PDF using PyPDFLoader | |
| loader = PyPDFLoader(tmp_file_path) | |
| pages = loader.load() | |
| # Add metadata to each page | |
| for page in pages: | |
| page.metadata["page_number"] = pages.index(page) + 1 | |
| # Split into chunks | |
| text_splitter = RecursiveCharacterTextSplitter( | |
| chunk_size=1000, | |
| chunk_overlap=200, | |
| length_function=len, | |
| separators=["\n\n", "\n", " ", ""] | |
| ) | |
| chunks = text_splitter.split_documents(pages) | |
| # Clean up temporary file | |
| os.unlink(tmp_file_path) | |
| vectorstore.add_documents(chunks) | |
| vectorstore.persist() | |
| except Exception as e: | |
| st.error(f"Error processing {uploaded_file.name}: {str(e)}") | |
| continue | |
| print("vector store created") | |
| st.success("Vector store created") | |
| user_question = st.text_input("Ask a Question from the PDF Files", key="user_question") | |
| if user_question: | |
| print("Question: ", user_question) | |
| retriever = vectorstore.as_retriever(search_type='similarity', search_kwargs={'k': 5}) | |
| llm = AzureChatOpenAI(temperature=0, | |
| api_key=azure_config["AZURE_OPENAI_API_KEY"], | |
| openai_api_version=azure_config["AZURE_OPENAI_API_VERSION"], | |
| azure_endpoint=azure_config["AZURE_OPENAI_ENDPOINT"], | |
| model=azure_config["AZURE_OPENAI_MODEL_DEPLOYMENT_NAME"], | |
| validate_base_url=False) | |
| chain = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever) | |
| answer = chain.invoke(user_question) | |
| print(answer) | |
| st.write("Reply: ", answer['result']) | |
| if __name__ == "__main__": | |
| main() | |