import os import gradio as gr from langchain_groq import ChatGroq from langchain.text_splitter import RecursiveCharacterTextSplitter from langchain.chains.combine_documents import create_stuff_documents_chain from langchain_core.prompts import ChatPromptTemplate from langchain.chains import create_retrieval_chain from langchain_community.vectorstores import FAISS from langchain_community.document_loaders import PyPDFLoader from langchain_community.embeddings import HuggingFaceEmbeddings from langchain.prompts import PromptTemplate from dotenv import load_dotenv """ ### How to Use the App: 1. **Upload PDF:** Upload PDF and click 'Process PDF' to add them to the knowledge base. 2. **Ask a Question:** Switch to the 'Q&A System' tab, enter your question, and click 'Ask Question' to get an answer based on the uploaded PDF content. 3. **Clear Data:** Click 'Clear Knowledge Base' to reset and remove all uploaded documents. Ensure a PDF is uploaded before asking questions. """ # Load environment variables load_dotenv() # Load the GROQ API key GROQ_API_KEY = os.environ.get("GROQ_API_KEY") # Set up the language model llm = ChatGroq(temperature=0, model_name='llama-3.1-8b-instant', groq_api_key=GROQ_API_KEY) # Define the prompt template prompt = ChatPromptTemplate.from_template(""" Answer the questions based on the provided context only. Please provide the most accurate response based on the question. {context} Question: {input} """) # Set up embeddings model embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2") vectors = None # Function to process PDF files def process_pdf(file): global vectors if file is not None: loader = PyPDFLoader(file.name) docs = loader.load() text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200) final_documents = text_splitter.split_documents(docs) if vectors is None: vectors = FAISS.from_documents(final_documents, embeddings) else: vectors.add_documents(final_documents) return "PDF processed and added to the knowledge base." return "No file uploaded." # Function to clear the knowledge base def clear_knowledge_base(): global vectors vectors = None # Reset the vector store return "Knowledge base cleared." def process_question(question): global vectors if vectors is None: return "Please upload a PDF first.", "", 0 # Create document retrieval chain retriever = vectors.as_retriever(search_type="similarity", search_kwargs={"k": 5}) # Use the invoke method for retrieving relevant documents documents = retriever.invoke(question) if not documents: return "No relevant context found.", "", 0 # Create context from retrieved documents context = "\n\n".join([doc.page_content for doc in documents]) # Combine context and question into a single string (formatted input for LLM) prompt = f"Answer the question based on the provided context.\n\nContext: {context}\n\nQuestion: {question}" # Pass the string to llm.invoke response = llm.invoke(prompt) # Confidence score as average relevance confidence_score = sum([doc.metadata.get('score', 0) for doc in documents]) / len(documents) return response, context, round(confidence_score, 2) # CSS styling CSS = """ .duplicate-button { margin: auto !important; color: white !important; background: black !important; border-radius: 100vh !important;} h3, p, h1 { text-align: center; color: white;} footer { text-align: center; padding: 10px; width: 100%; background-color: rgba(240, 240, 240, 0.8); z-index: 1000; position: relative; margin-top: 10px; color: black;} """ # Footer text FOOTER_TEXT = """ """ # Title text TITLE = "

📚 RAG Document Q&A 📚

" # Gradio interface with gr.Blocks(css=CSS, theme="Nymbo/Nymbo_Theme") as demo: gr.HTML(TITLE) with gr.Tab("PDF Uploader"): pdf_file = gr.File(label="Upload PDF") upload_button = gr.Button("Process PDF") clear_button = gr.Button("Clear Knowledge Base") # New button to clear the knowledge base upload_output = gr.Textbox(label="Upload Status") with gr.Tab("Q&A System"): question_input = gr.Textbox(lines=2, placeholder="Enter your question here...") submit_button = gr.Button("Ask Question") answer_output = gr.Textbox(label="Answer") context_output = gr.Textbox(label="Relevant Context", lines=10) confidence_output = gr.Number(label="Confidence Score") # Button actions upload_button.click(process_pdf, inputs=[pdf_file], outputs=[upload_output]) submit_button.click(process_question, inputs=[question_input], outputs=[answer_output, context_output, confidence_output]) # Action to clear the knowledge base clear_button.click(clear_knowledge_base, outputs=[upload_output]) gr.HTML(FOOTER_TEXT) # Launch the Gradio app if __name__ == "__main__": demo.launch()