import gradio as gr import PyPDF2 #rom langchain.embeddings.openai import OpenAIEmbeddings from langchain.embeddings import HuggingFaceEmbeddings from langchain.vectorstores.faiss import FAISS from langchain.text_splitter import RecursiveCharacterTextSplitter from langchain import HuggingFaceHub from langchain.document_loaders import UnstructuredPDFLoader from langchain.indexes import VectorstoreIndexCreator from langchain import OpenAI, VectorDBQA import os def pdf_to_text(pdf_file, query): # Open the PDF file in binary mode with open(pdf_file.name, 'rb') as pdf_file: # Create a PDF reader object pdf_reader = PyPDF2.PdfReader(pdf_file) # Create an empty string to store the text text = "" # Loop through each page of the PDF for page_num in range(len(pdf_reader.pages)): # Get the page object page = pdf_reader.pages[page_num] # Extract the texst from the page and add it to the text variable text += page.extract_text() #embedding step from langchain.text_splitter import CharacterTextSplitter text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0) texts = text_splitter.split_text(text) embeddings = HuggingFaceEmbeddings() #vector store vectorstore = FAISS.from_texts(texts, embeddings) llm = HuggingFaceHub(repo_id="google/flan-t5-xl", model_kwargs={"temperature":0, "max_length":512}) loaders = UnstructuredPDFLoader(pdf_file) index = vectorstore.as_retriever() #inference #qa = VectorDBQA.from_chain_type(llm=llm, chain_type="stuff", vectorstore=vectorstore) from langchain.chains import RetrievalQA chain = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=index, input_key="question") return chain.run(query) # Define the Gradio interface pdf_input = gr.inputs.File(label="PDF File") query_input = gr.inputs.Textbox(label="Query") outputs = gr.outputs.Textbox(label="Chatbot Response") interface = gr.Interface(fn=pdf_to_text, inputs=[pdf_input, query_input], outputs=outputs) # Run the interface interface.launch(debug = True)