Llama Index中GPTSimpleVectorIndex初始化报'unexpected keyword argument'错误求助

这个错误源于你使用的Llama Index版本（v0.8及以上）重构了索引构造API，GPTSimpleVectorIndex不再支持直接传入llm_predictor和prompt_helper参数，需要通过ServiceContext封装这些组件。

修改步骤 #

• 从llama_index导入ServiceContext类
• 将llm_predictor和prompt_helper封装到ServiceContext实例中
• 构造索引时传入service_context参数，替代原来的两个独立参数

修改后的完整代码 #

from llama_index import SimpleDirectoryReader, GPTListIndex, GPTSimpleVectorIndex, LLMPredictor, PromptHelper, ServiceContext
from langchain import OpenAI
import gradio as gr
import sys
import os

os.environ["OPENAI_API_KEY"] = 'MYKEY'

def construct_index(directory_path):
    max_input_size = 4096
    num_outputs = 512
    max_chunk_overlap = 20
    chunk_size_limit = 600

    prompt_helper = PromptHelper(max_input_size, num_outputs, max_chunk_overlap, chunk_size_limit=chunk_size_limit)

    llm_predictor_gpt = LLMPredictor(llm=OpenAI(temperature=0.7, model_name="text-davinci-003", max_tokens=num_outputs))

    # 封装ServiceContext
    service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor_gpt, prompt_helper=prompt_helper)

    documents = SimpleDirectoryReader(directory_path).load_data()

    # 用新版本推荐的from_documents方法构造索引
    index = GPTSimpleVectorIndex.from_documents(documents, service_context=service_context)

    index.save_to_disk('index.json')

    return index

def chatbot(input_text):
    index = GPTSimpleVectorIndex.load_from_disk('index.json')
    response = index.query(input_text, response_mode="compact")
    return response.response

# Gradio新版本中gr.inputs.Textbox已弃用，改用gr.Textbox
iface = gr.Interface(fn=chatbot,
                     inputs=gr.Textbox(lines=7, label="Enter your text"),
                     outputs="text",
                     title="Custom-trained AI Chatbot")

index = construct_index("salesdocs")
iface.launch(share=False)

额外说明 #

• 新版本Llama Index推荐使用from_documents方法构造索引，替代直接实例化的方式
• 若你的Gradio版本较新，gr.inputs.Textbox会触发警告，替换为gr.Textbox即可消除

内容的提问来源于stack exchange，提问作者t25