Update app.py

app.py

@@ -6,10 +6,16 @@ from pydantic import BaseModel, Field
 from typing import Optional, Literal, Dict
 from huggingface_hub.errors import HfHubHTTPError
 
+from pydantic import BaseModel, Field
+from typing import Optional, Literal
+from huggingface_hub.errors import HfHubHTTPError
+
+# Input model
 class PromptInput(BaseModel):
     text: str = Field(..., description="The initial prompt text")
     meta_prompt_choice: Literal["star", "done", "physics", "morphosis", "verse", "phor", "bolism", "math", "arpe"] = Field(..., description="Choice of meta prompt strategy")
 
+# Output model for LLM responses
 class LLMResponse(BaseModel):
     initial_prompt_evaluation: str = Field(default="")
     refined_prompt: str = Field(default="")
@@ -18,7 +24,7 @@ class LLMResponse(BaseModel):
 class PromptRefiner:
     def __init__(self, api_token: str):
         self.client = InferenceClient(token=api_token, timeout=300)
-        self.meta_prompts: Dict[str, str] = {
+        self.meta_prompts = {
             "morphosis": original_meta_prompt,
             "verse": new_meta_prompt,
             "physics": metaprompt1,
@@ -41,9 +47,9 @@ class PromptRefiner:
                     "role": "system",
                     "content": '''You are an expert at refining prompts. Respond in JSON format with exactly these fields:
                     {
-                        "initial_prompt_evaluation": "your evaluation of the initial prompt",
-                        "refined_prompt": "your refined version of the prompt",
-                        "explanation_of_refinements": "your explanation of the changes made"
+                        "initial_prompt_evaluation": "your evaluation",
+                        "refined_prompt": "your refined prompt",
+                        "explanation_of_refinements": "your explanation"
                     }'''
                 },
                 {
@@ -65,12 +71,12 @@ class PromptRefiner:
             try:
                 parsed_response = LLMResponse.model_validate_json(response_content)
                 result = parsed_response.model_dump()
-            except Exception as e:
+            except Exception:
                 # Fallback to basic dict if JSON parsing fails
                 result = {
-                    "initial_prompt_evaluation": "Error parsing model response",
-                    "refined_prompt": response_content,
-                    "explanation_of_refinements": str(e)
+                    "initial_prompt_evaluation": response_content,
+                    "refined_prompt": prompt_input.text,
+                    "explanation_of_refinements": "Failed to parse model response"
                 }
 
             return (
@@ -82,27 +88,27 @@ class PromptRefiner:
 
         except HfHubHTTPError as e:
             error_response = LLMResponse(
-                initial_prompt_evaluation="Error: Model timeout",
-                refined_prompt="The model is currently experiencing high traffic",
-                explanation_of_refinements="Please try again later"
-            )
+                initial_prompt_evaluation="Error: Model timeout or connection issue",
+                refined_prompt=prompt_input.text,
+                explanation_of_refinements="Please try again in a few moments"
+            ).model_dump()
             return (
-                error_response.initial_prompt_evaluation,
-                error_response.refined_prompt,
-                error_response.explanation_of_refinements,
-                error_response.model_dump()
+                error_response["initial_prompt_evaluation"],
+                error_response["refined_prompt"],
+                error_response["explanation_of_refinements"],
+                error_response
             )
         except Exception as e:
             error_response = LLMResponse(
                 initial_prompt_evaluation=f"Error: {str(e)}",
-                refined_prompt="",
+                refined_prompt=prompt_input.text,
                 explanation_of_refinements="An unexpected error occurred"
-            )
+            ).model_dump()
             return (
-                error_response.initial_prompt_evaluation,
-                error_response.refined_prompt,
-                error_response.explanation_of_refinements,
-                error_response.model_dump()
+                error_response["initial_prompt_evaluation"],
+                error_response["refined_prompt"],
+                error_response["explanation_of_refinements"],
+                error_response
             )
 
     def apply_prompt(self, prompt: str, model: str) -> str: