| from langchain.vectorstores import Chroma |
| from langchain.embeddings import OpenAIEmbeddings |
| from langchain.text_splitter import RecursiveCharacterTextSplitter |
| from langchain.llms import OpenAI |
| from langchain.chains import VectorDBQA, RetrievalQA |
| from langchain.chat_models import ChatOpenAI |
| from langchain.document_loaders import TextLoader, PyPDFLoader |
| from langchain import PromptTemplate |
| from PyPDF2 import PdfFileMerger |
| import gradio as gr |
| from dotenv import load_dotenv |
| import openai |
| import glob |
| import os |
|
|
| load_dotenv() |
| os.environ["OPENAI_API_KEY"] = os.environ['OPENAI_API_KEY'] |
|
|
| merge_file = 'src/retrieval_qa/pdf/merge.pdf' |
| if not os.path.isfile(merge_file): |
| pdf_file_merger = PdfFileMerger() |
| for file_name in glob.glob('src/retrieval_qa/pdf/*.pdf'): |
| pdf_file_merger.append(file_name) |
| pdf_file_merger.write(merge_file) |
| pdf_file_merger.close() |
|
|
| loader = PyPDFLoader(merge_file) |
| documents = loader.load() |
|
|
| text_splitter = RecursiveCharacterTextSplitter( |
| chunk_size=1000, chunk_overlap=0) |
| texts = text_splitter.split_documents(documents) |
| embeddings = OpenAIEmbeddings() |
| vectordb = Chroma.from_documents(texts, embeddings) |
|
|
| qa = RetrievalQA.from_chain_type(llm=ChatOpenAI( |
| model_name="gpt-3.5-turbo"), chain_type="stuff", retriever=vectordb.as_retriever()) |
|
|
| |
| template = """ |
| あなたは再生医療・美容医学について学習したAIアシスタントです。下記の質問に具体的で医学的な回答をしてください。 |
| 質問：{question} |
| 回答： |
| """ |
|
|
| prompt = PromptTemplate( |
| input_variables=["question"], |
| template=template, |
| ) |
|
|
|
|
| def add_text(history, text): |
| history = history + [(text, None)] |
| return history, "" |
|
|
|
|
| def bot(history): |
| query = history[-1][0] |
| query = prompt.format(question=query) |
| answer = qa.run(query) |
| source = qa._get_docs(query)[0] |
| source_sentence = source.page_content |
| answer_source = source_sentence + "\n"+"source:" + \ |
| source.metadata["source"] + ", page:" + str(source.metadata["page"]) |
| history[-1][1] = answer |
| return history |
|
|
|
|
| with gr.Blocks() as demo: |
| chatbot = gr.Chatbot([], elem_id="chatbot").style(height=400) |
|
|
| with gr.Row(): |
| with gr.Column(scale=0.6): |
| txt = gr.Textbox( |
| show_label=False, |
| placeholder="Enter text and press enter", |
| ).style(container=False) |
|
|
| txt.submit(add_text, [chatbot, txt], [chatbot, txt]).then( |
| bot, chatbot, chatbot |
| ) |
|
|
| demo.launch() |
|
|
