fix

app/rag.py

@@ -30,25 +30,25 @@ class ChatPDF:
     # model_url = "https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat-GGUF/resolve/main/qwen1_5-1_8b-chat-q8_0.gguf"
     model_url = "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf/resolve/main/Phi-3-mini-4k-instruct-q4.gguf"
 
-    def messages_to_prompt(messages):
-        prompt = ""
-        for message in messages:
-            if message.role == 'system':
-                prompt += f"<|system|>\n{message.content}</s>\n"
-            elif message.role == 'user':
-                prompt += f"<|user|>\n{message.content}</s>\n"
-            elif message.role == 'assistant':
-                prompt += f"<|assistant|>\n{message.content}</s>\n"
+    # def messages_to_prompt(messages):
+    #     prompt = ""
+    #     for message in messages:
+    #         if message.role == 'system':
+    #             prompt += f"<|system|>\n{message.content}</s>\n"
+    #         elif message.role == 'user':
+    #             prompt += f"<|user|>\n{message.content}</s>\n"
+    #         elif message.role == 'assistant':
+    #             prompt += f"<|assistant|>\n{message.content}</s>\n"
 
-        if not prompt.startswith("<|system|>\n"):
-            prompt = "<|system|>\n</s>\n" + prompt
+    #     if not prompt.startswith("<|system|>\n"):
+    #         prompt = "<|system|>\n</s>\n" + prompt
 
-        prompt = prompt + "<|assistant|>\n"
+    #     prompt = prompt + "<|assistant|>\n"
 
-        return prompt
+    #     return prompt
 
-    def completion_to_prompt(completion):
-        return f"<|system|>\n</s>\n<|user|>\n{completion}</s>\n<|assistant|>\n"
+    # def completion_to_prompt(completion):
+    #     return f"<|system|>\n</s>\n<|user|>\n{completion}</s>\n<|assistant|>\n"
 
 
     def __init__(self):
@@ -68,7 +68,7 @@ class ChatPDF:
             max_new_tokens=256,
             context_window=3900,
             # generate_kwargs={},
-            model_kwargs={"n_gpu_layers": -1},
+            # model_kwargs={"n_gpu_layers": -1},
             messages_to_prompt=self.messages_to_prompt,
             completion_to_prompt=self.completion_to_prompt,
             verbose=True,