Update utils.py

utils.py

@@ -277,38 +277,85 @@ def classify_mood(input_string):
             return word, True
     return None, False
 
+# def generate_llm_output(
+#     prompt, history, temperature=0.1, max_new_tokens=2048, top_p=0.8, repetition_penalty=1.0,
+# ):
+#     temperature = temperature
+#     top_p = float(top_p)
+
+#     generate_kwargs = dict(
+#         temperature=temperature,
+#         max_new_tokens=max_new_tokens,
+#         top_p=top_p,
+#         repetition_penalty=repetition_penalty,
+#         do_sample=True,
+#         seed=42,
+#     )
+
+#     formatted_prompt = format_prompt(prompt, history)
+
+#     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+#     output = ""
+
+#     for response in stream:
+#         output += response.token.text
+#         mood, is_classified = classify_mood(output)
+#         # Print the chatbot's response
+#         if is_classified:
+#             print("Chatbot:", mood.capitalize())
+#             playlist_message = f"Playing {mood.capitalize()} playlist for you!"
+#             output=playlist_message
+#             return output               
+#         # yield output
+#     return output
+
 def generate_llm_output(
-    prompt, history, temperature=0.1, max_new_tokens=2048, top_p=0.8, repetition_penalty=1.0,
-):
-    temperature = temperature
-    top_p = float(top_p)
-
-    generate_kwargs = dict(
-        temperature=temperature,
-        max_new_tokens=max_new_tokens,
-        top_p=top_p,
-        repetition_penalty=repetition_penalty,
-        do_sample=True,
-        seed=42,
-    )
-
-    formatted_prompt = format_prompt(prompt, history)
-
-    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-    output = ""
-
-    for response in stream:
-        output += response.token.text
-        mood, is_classified = classify_mood(output)
-        # Print the chatbot's response
-        if is_classified:
-            print("Chatbot:", mood.capitalize())
-            playlist_message = f"Playing {mood.capitalize()} playlist for you!"
-            output=playlist_message
-            return output               
-        # yield output
-    return output
-    
+        prompt,    
+        history,
+        llm,
+        temperature=0.8,
+        max_tokens=256,
+        top_p=0.95,
+        stop_words=["<s>","[/INST]", "</s>"]
+    ):
+        temperature = temperature
+        
+        top_p = float(top_p)
+
+        generate_kwargs = dict(
+            temperature=temperature,
+            max_tokens=max_tokens,
+            top_p=top_p,
+            stop=stop_words
+        )
+        formatted_prompt = format_prompt(prompt, history)
+        try:
+            print("LLM Input:", formatted_prompt)
+            # Local GGUF
+            stream = llm(
+                formatted_prompt,
+                **generate_kwargs,
+                stream=True,
+            )
+            output = ""
+            for response in stream:
+                output += response.token.text
+                mood, is_classified = classify_mood(output)
+                # Print the chatbot's response
+                if is_classified:
+                    print("Chatbot:", mood.capitalize())
+                    playlist_message = f"Playing {mood.capitalize()} playlist for you!"
+                    output=playlist_message
+                    return output               
+                # yield output
+            return output
+
+        except Exception as e:
+            print("Unhandled Exception: ", str(e))
+            gr.Warning("Generating error")
+            output = "I do not know what happened but I could not understand you ."
+        return output
+
 def get_sentence(history, llm):
     history = [["", None]] if history is None else history 
     history[-1][1] = ""