llama-index-question-gen-openai

import os from llama_index.question_gen.openai import OpenAIQuestionGenerator from llama_index.core.tools import ToolMetadata, QueryEngineTool from llama_index.core import QueryBundle, VectorStoreIndex, SimpleDirectoryReader from llama_index.llms.openai import OpenAI # Set your OpenAI API key (replace with your actual key or load from .env) os.environ["OPENAI_API_KEY"] = os.environ.get("OPENAI_API_KEY", "YOUR_OPENAI_API_KEY") # Create a dummy data file for demonstration with open("data.txt", "w") as f: f.write("The capital of France is Paris. Paris is known for its Eiffel Tower.") f.write("The capital of Germany is Berlin. Berlin has a rich history.") # Load data and create a simple index for a tool reader = SimpleDirectoryReader("./") documents = reader.load_data() index = VectorStoreIndex.from_documents(documents) query_engine = index.as_query_engine() # Define a tool for the question generator to use tool = QueryEngineTool( query_engine=query_engine, metadata=ToolMetadata( name="city_info", description="Provides information about cities and their landmarks." ), ) # Initialize OpenAIQuestionGenerator # It uses OpenAI's function calling API by default. question_gen = OpenAIQuestionGenerator.from_defaults(llm=OpenAI(model="gpt-3.5-turbo-0613")) # Generate sub-questions based on a complex query and available tools query_bundle = QueryBundle("Tell me about the capitals of European countries and their famous landmarks.") sub_questions = question_gen.generate( tools=[tool], query=query_bundle ) print(f"Generated {len(sub_questions)} sub-questions:") for sq in sub_questions: print(f"- Question: {sq.sub_question}, Tool: {sq.tool_name}")