2023年3月1日，openai官方发布了新的chatGPT的api接口。老接口的模型是text-davinci-003，新接口的模型是gpt-3.5-turbo。新接口的相应速度比原来快了很多，并且支持上下文。下面我来详解一下这个上下文是怎么做的。

下面这个代码是官方给出的调取api的示例。需要用户下载openai，并且保证版本是0.27。

import openai

openai.api_key = “这里放入你的API Key，注意要保留双引号”

completion = openai.ChatCompletion.create( model=“gpt-3.5-turbo”, messages=[{“role”: “user”, “content”: “知乎是什么？”}] )

print(completion)

按上面代码的写法，只能回答单个问题，并且无法形成上下文，原因在于messages这个参数只有一个字典。要想形成上下文，就必须按上下文对话的顺序把对话封装成字典，而且这个字典中，key为role时，对应的取值必须是system、user和assistant！

另外，字典中每一个role的取值，对应的功能都不太一样，其中system用于在会话开始之初给定chatGPT一个指示或声明，使得后续的回答更具有个性化和专业化。user是用于给用户提问的或者说是用来给用户输入prompt的。assistant是用于输入chatGPT的回答内容。

至于content这key，就是用于输入基于role的文本。如果role是user，content就是prompt，如果role是assitant，content就是chatGPT回答的内容。

详解完毕，下面上一个我自己写的一个python代码，可以实现多轮对话，仅供参考：

讯享网class Chat:

<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span><span class="n">conversation_list</span><span class="o">=</span><span class="p">[])</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span> <span class="c1"># 初始化对话列表，可以加入一个key为system的字典，有助于形成更加个性化的回答</span> <span class="c1"># self.conversation_list = [{&#39;role&#39;:&#39;system&#39;,&#39;content&#39;:&#39;你是一个非常友善的助手&#39;}]</span> <span class="bp">self</span><span class="o">.</span><span class="n">conversation_list</span> <span class="o">=</span> <span class="p">[]</span> <span class="c1"># 打印对话</span> <span class="k">def</span> <span class="nf">show_conversation</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span><span class="n">msg_list</span><span class="p">):</span> <span class="k">for</span> <span class="n">msg</span> <span class="ow">in</span> <span class="n">msg_list</span><span class="p">:</span> <span class="k">if</span> <span class="n">msg</span><span class="p">[</span><span class="s1">&#39;role&#39;</span><span class="p">]</span> <span class="o">==</span> <span class="s1">&#39;user&#39;</span><span class="p">:</span> <span class="nb">print</span><span class="p">(</span><span class="n">f</span><span class="s2">&#34;</span><span class="se">\U0001f47b</span><span class="s2">: </span><span class="si">{msg[&#39;content&#39;]}</span><span class="se">\n</span><span class="s2">&#34;</span><span class="p">)</span> <span class="k">else</span><span class="p">:</span> <span class="nb">print</span><span class="p">(</span><span class="n">f</span><span class="s2">&#34;</span><span class="se">\U0001f47D</span><span class="s2">: </span><span class="si">{msg[&#39;content&#39;]}</span><span class="se">\n</span><span class="s2">&#34;</span><span class="p">)</span> <span class="c1"># 提示chatgpt</span> <span class="k">def</span> <span class="nf">ask</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span><span class="n">prompt</span><span class="p">):</span> <span class="bp">self</span><span class="o">.</span><span class="n">conversation_list</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s2">&#34;role&#34;</span><span class="p">:</span><span class="s2">&#34;user&#34;</span><span class="p">,</span><span class="s2">&#34;content&#34;</span><span class="p">:</span><span class="n">prompt</span><span class="p">})</span> <span class="n">response</span> <span class="o">=</span> <span class="n">openai</span><span class="o">.</span><span class="n">ChatCompletion</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="n">model</span><span class="o">=</span><span class="s2">&#34;gpt-3.5-turbo&#34;</span><span class="p">,</span><span class="n">messages</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">conversation_list</span><span class="p">)</span> <span class="n">answer</span> <span class="o">=</span> <span class="n">response</span><span class="o">.</span><span class="n">choices</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">message</span><span class="p">[</span><span class="s1">&#39;content&#39;</span><span class="p">]</span> <span class="c1"># 下面这一步是把chatGPT的回答也添加到对话列表中，这样下一次问问题的时候就能形成上下文了</span> <span class="bp">self</span><span class="o">.</span><span class="n">conversation_list</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s2">&#34;role&#34;</span><span class="p">:</span><span class="s2">&#34;assistant&#34;</span><span class="p">,</span><span class="s2">&#34;content&#34;</span><span class="p">:</span><span class="n">answer</span><span class="p">})</span> <span class="bp">self</span><span class="o">.</span><span class="n">show_conversation</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conversation_list</span><span class="p">)</span></code></pre></div><p data-pid="jaMqzbyA">下面来看看成果</p><figure data-size="normal"><img src="https://pica.zhimg.com/v2-133f405a3b353eb4ecbe0274a144bc6a_r.jpg" data-size="normal" data-rawwidth="1792" data-rawheight="338" data-original-token="v2-a8bdaeba323a4acc556f6262f2caa20f" class="origin_image zh-lightbox-thumb" width="1792" data-original="https://pica.zhimg.com/v2-133f405a3b353eb4ecbe0274a144bc6a_r.jpg"/><figcaption>第一次问答</figcaption></figure><figure data-size="normal"><img src="https://pic4.zhimg.com/v2-34ce22f7e1da33435d6edced_r.jpg" data-size="normal" data-rawwidth="1791" data-rawheight="680" data-original-token="v2-8c9c5bd2a6984a42e025de12c443a490" class="origin_image zh-lightbox-thumb" width="1791" data-original="https://pic4.zhimg.com/v2-34ce22f7e1da33435d6edced_r.jpg"/><figcaption>第二次问答</figcaption></figure><p data-pid="qUKkQIIr">可以在第二次问答的图片中看到，chatGPT明显捕捉到了第一次对话的关键词“火锅”。</p><p></p><p></p>