app.py

# Code adapted from https://docs.llamaindex.ai/en/stable/examples/customization/prompts/chat_prompts/
import gradio as gr

from llama_index.core import ChatPromptTemplate

def define_custom_prompts(): 
  qa_prompt_str = (
      "Context information is below.\n"
      "---------------------\n"
      "{context_str}\n"
      "---------------------\n"
      "Given the context information and not prior knowledge, "
      "answer the question: {query_str}\n")

  refine_prompt_str = (
      "We have the opportunity to refine the original answer "
      "(only if needed) with some more context below.\n"
      "------------\n"
      "{context_msg}\n"
      "------------\n"
      "Given the new context, refine the original answer to better "
      "answer the question: {query_str}. "
      "If the context isn't useful, output the original answer again.\n"
      "Original Answer: {existing_answer}")
  
  # Text QA Prompt
  chat_text_qa_msgs = [
      (
          "system",
          "Always answer the question, even if the context isn't helpful.",
      ),
      ("user", qa_prompt_str),
  ]
  text_qa_template = ChatPromptTemplate.from_messages(chat_text_qa_msgs)

  # Refine Prompt
  chat_refine_msgs = [
      (
          "system",
          "Always answer the question, even if the context isn't helpful.",
      ),
      ("user", refine_prompt_str),
  ]
  refine_template = ChatPromptTemplate.from_messages(chat_refine_msgs)

  return text_qa_template, refine_template


def answer_questions(user_question):

  text_qa_template, refine_template = define_custom_prompts()

  import openai
  import os
  os.environ["OPENAI_API_KEY"]
  openai.api_key = os.environ["OPENAI_API_KEY"]
  from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
  from llama_index.llms.openai import OpenAI

  documents = SimpleDirectoryReader("./data/").load_data()

  # Create an index using a chat model, so that we can use the chat prompts!
  llm = OpenAI(model="gpt-3.5-turbo", temperature=0.1)

  index = VectorStoreIndex.from_documents(documents)

  response = index.as_query_engine(text_qa_template=text_qa_template, refine_template=refine_template, llm=llm).query(user_question)

  return str(response)


text_qa_template, refine_template = define_custom_prompts()

#question = "Which countries were affected?"
#question = "What are the number of injuries in Gaziantep?"

#answer = answer_questions(question, text_qa_template, refine_template)
#answer

demo = gr.Interface(fn=answer_questions, inputs="text", outputs="text")

demo.launch()