Update app.py

app.py

@@ -6,15 +6,6 @@ import gradio as gr
 from pydantic import BaseModel, Field
 from typing import Optional, Literal
 
-
-import json
-import re
-import json
-import re
-from huggingface_hub import InferenceClient
-from pydantic import BaseModel, Field
-from typing import Optional, Literal
-
 class PromptInput(BaseModel):
     text: str = Field(..., description="The initial prompt text")
     meta_prompt_choice: Literal["star","done","physics","morphosis", "verse", "phor","bolism"] = Field(..., description="Choice of meta prompt strategy")
@@ -58,19 +49,14 @@ class PromptRefiner:
         )
         response_content = response.choices[0].message.content.strip()
         try:
-            # Extract JSON from between <json> tags
             json_match = re.search(r'<json>\s*(.*?)\s*</json>', response_content, re.DOTALL)
             if json_match:
                 json_str = json_match.group(1)
-                # Remove newlines and escape quotes within the JSON string
                 json_str = re.sub(r'\n\s*', ' ', json_str)
                 json_str = json_str.replace('"', '\\"')
-                # Wrap the entire string in quotes and parse it
                 json_output = json.loads(f'"{json_str}"')
-                # Ensure json_output is a dictionary
                 if isinstance(json_output, str):
                     json_output = json.loads(json_output)
-                # Unescape the parsed JSON
                 for key, value in json_output.items():
                     if isinstance(value, str):
                         json_output[key] = value.replace('\\"', '"')
@@ -80,7 +66,6 @@ class PromptRefiner:
         except (json.JSONDecodeError, ValueError) as e:
             print(f"Error parsing JSON: {e}")
             print(f"Raw content: {response_content}")
-            # If JSON parsing fails, attempt to extract the content manually
             output = {}
             for key in ["initial_prompt_evaluation", "refined_prompt", "explanation_of_refinements"]:
                 pattern = rf'"{key}":\s*"(.*?)"(?:,|\}})'
@@ -88,10 +73,10 @@ class PromptRefiner:
                 if match:
                     output[key] = match.group(1).replace('\\n', '\n').replace('\\"', '"')
                 else:
-                    output[key] = "" # Set empty string if content not found
+                    output[key] = ""
             return RefinementOutput(**output, raw_content=response_content)
                 
-    def apply_prompt(self, prompt: str) -> str:
+    def apply_prompt(self, prompt: str, model: str) -> str:
         try:
             messages = [
                 {"role": "system", "content": "You are a helpful assistant. Answer in stylized version with latex format or markdown if relevant. Separate your answer into logical sections using level 2 headers (##) for sections and bolding (**) for subsections.Incorporate a variety of lists, headers, and text to make the answer visually appealing"},
@@ -99,14 +84,13 @@ class PromptRefiner:
             ]
 
             response = self.client.chat_completion(
-                model="meta-llama/Meta-Llama-3-70B-Instruct",
+                model=model,
                 messages=messages,
-                max_tokens=4000, # Increased token limit
+                max_tokens=4000,
                 temperature=0.8
             )
 
             output = response.choices[0].message.content.strip()
-            # Basic post-processing
             output = output.replace('\n\n', '\n').strip()
             return output
         except Exception as e:
@@ -144,7 +128,22 @@ class GradioInterface:
                 outputs=[analysis_evaluation, refined_prompt, explanation_of_refinements, full_response_json]
             )
             with gr.Row():
-            #    apply_model=gr.Dropdown(["meta-llama/Llama-3.1-70B-Instruct",'Qwen/Qwen2.5-72B-Instruct'], value="meta-llama/Llama-3.1-70B-Instruct", label="Model"),
+                apply_model = gr.Dropdown(
+                    [
+                        "meta-llama/Llama-2-70b-chat-hf",
+                        "tiiuae/falcon-180B",
+                        "bigscience/bloom",
+                        "EleutherAI/gpt-neox-20b",
+                        "google/flan-t5-xxl",
+                        "facebook/opt-66b",
+                        "Qwen/Qwen-72B",
+                        "mistralai/Mistral-7B-Instruct-v0.1",
+                        "microsoft/phi-2",
+                        "THUDM/chatglm3-6b"
+                    ],
+                    value="meta-llama/Llama-2-70b-chat-hf",
+                    label="Choose Model"
+                )
                 apply_button = gr.Button("Apply Prompts")
 
             with gr.Row():
@@ -157,7 +156,7 @@ class GradioInterface:
 
             apply_button.click(
                 fn=self.apply_prompts,
-                inputs=[prompt_text, refined_prompt],
+                inputs=[prompt_text, refined_prompt, apply_model],
                 outputs=[original_output, refined_output]
             )
 
@@ -177,7 +176,6 @@ class GradioInterface:
                 inputs=[prompt_text, meta_prompt_choice]
             )
 
-                
     def refine_prompt(self, prompt: str, meta_prompt_choice: str) -> tuple:
         input_data = PromptInput(text=prompt, meta_prompt_choice=meta_prompt_choice)
         result = self.prompt_refiner.refine_prompt(input_data)
@@ -189,27 +187,25 @@ class GradioInterface:
             result.dict()
         )
 
-    def apply_prompts(self,original_prompt: str, refined_prompt: str):
-        original_output = self.prompt_refiner.apply_prompt(original_prompt)
-        refined_output = self.prompt_refiner.apply_prompt(refined_prompt)
+    def apply_prompts(self, original_prompt: str, refined_prompt: str, model: str):
+        original_output = self.prompt_refiner.apply_prompt(original_prompt, model)
+        refined_output = self.prompt_refiner.apply_prompt(refined_prompt, model)
         return original_output, refined_output
 
-
     def launch(self, share=False):
-        self.interface.launch()
-    
+        self.interface.launch(share=share)
+
 # Main code to run the application
 if __name__ == '__main__':
     api_token = os.getenv('HF_API_TOKEN')
     if not api_token:
         raise ValueError("HF_API_TOKEN not found in environment variables")
 
-    
-    metadone=os.getenv('metadone')
+    metadone = os.getenv('metadone')
     echo_prompt_refiner = os.getenv('echo_prompt_refiner')
     metaprompt1 = os.getenv('metaprompt1')   
     loic_metaprompt = os.getenv('loic_metaprompt')    
-    openai_metaprompt=os.getenv('openai_metaprompt')
+    openai_metaprompt = os.getenv('openai_metaprompt')
     original_meta_prompt = os.getenv('original_meta_prompt')    
     new_meta_prompt = os.getenv('new_meta_prompt')   
     advanced_meta_prompt = os.getenv('advanced_meta_prompt')