import gradio as gr from langchain.document_loaders import OnlinePDFLoader from langchain.text_splitter import CharacterTextSplitter text_splitter = CharacterTextSplitter(chunk_size=350, chunk_overlap=0) from langchain.llms import OpenAI from langchain.embeddings import OpenAIEmbeddings embeddings = OpenAIEmbeddings() from langchain.vectorstores import Chroma from langchain.chains import RetrievalQA def loading_pdf(): return "Loading..." def pdf_changes(pdf_doc): loader = OnlinePDFLoader(pdf_doc.name) documents = loader.load() texts = text_splitter.split_documents(documents) db = Chroma.from_documents(texts, embeddings) retriever = db.as_retriever() global qa qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="stuff", retriever=retriever, return_source_documents=True) return "Ready" def add_text(history, text): history = history + [(text, None)] return history, "" def bot(history): response = infer(history[-1][0]) history[-1][1] = response['result'] return history def infer(question): query = question result = qa({"query": query}) return result css=""" #col-container {max-width: 700px; margin-left: auto; margin-right: auto;} """ title = """
Upload a .PDF from your computer, click the "Load PDF to LangChain" button,
when everything is ready, you can start asking questions about the pdf ;)