python - 为什么我在 Azure Open AI 中遇到 "gpt-35-turbo-16k"模型无效模型错误，但在 "gpt-35-turbo"中却没有？

Question

我使用 Azure Open AI、Langchain 和 Streamlit 构建了一个非常简单的应用程序。以下是我的代码:

from dotenv import load_dotenv,find_dotenv
load_dotenv(find_dotenv())

import streamlit as st
from langchain.llms import AzureOpenAI

from langchain.prompts import PromptTemplate


LLM = AzureOpenAI(max_tokens=1500, deployment_name="gpt-35-turbo-16k", model="gpt-35-turbo-16k")


prompt_template = """
If you don't know the answer, just say that you don't know, don't try to make up an answer.

Question: {question}
"""
PROMPT = PromptTemplate(template=prompt_template, input_variables=["question"])
st.title('Experiment AzureOpenAI :)')
user_question = st.text_input('Your query here please')

if user_question:
    prompt = prompt_template.format(question = user_question)
    response = LLM(prompt)
    st.write(response)
    st.write('done')

当我运行上面的代码时，我收到以下错误:

InvalidRequestError: The completion operation does not work with thespecified model, gpt-35-turbo-16k. Please choose different model andtry again. You can learn more about which models can be used with eachoperation here: https://go.microsoft.com/fwlink/?linkid=2197993.

但是，如果我将模型从 gpt-35-turbo-16k 更改为 gpt-35-turbo，我的代码运行得非常好。所以下面的代码可以工作:

LLM = AzureOpenAI(max_tokens=1500, deployment_name="gpt-35-turbo", model="gpt-35-turbo")

我想知道为什么会发生这个错误？

从此link ，我看到的唯一区别是 gpt-35-turbo-16k 支持最多 16k 输入 token ，而 gpt-35-turbo 支持最多 4k 输入 token 。

Answer 1

根据文档，合理的原因是:版本 (0613) 仅支持 Chat Completions API。

https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-35-models

GPT-3.5 Turbo is used with the Chat Completion API. GPT-3.5 Turbo (0301) can also be used with the Completions API. GPT3.5 Turbo (0613) only supports the Chat Completions API.