add Moonshot, debug my_llm (#126)

rag/llm/chat_model.py

@@ -54,6 +54,21 @@ class MoonshotChat(GptTurbo):
         self.client = OpenAI(api_key=key, base_url="https://api.moonshot.cn/v1",)
         self.model_name = model_name
 
+    def chat(self, system, history, gen_conf):
+        if system: history.insert(0, {"role": "system", "content": system})
+        try:
+            response = self.client.chat.completions.create(
+                model=self.model_name,
+                messages=history,
+                **gen_conf)
+            ans = response.choices[0].message.content.strip()
+            if response.choices[0].finish_reason == "length":
+                ans += "...\nFor the content length reason, it stopped, continue?" if is_english(
+                    [ans]) else "······\n由于长度的原因，回答被截断了，要继续吗？"
+            return ans, response.usage.completion_tokens
+        except openai.APIError as e:
+            return "**ERROR**: "+str(e), 0
+
 
 from dashscope import Generation
 class QWenChat(Base):