Update app.py

Key Functionality and Components
The application is a combined mechanical calculator and a Hugging Face LLM inference engine deployed via Gradio.

1. Gear Dimension Calculator (gear_calc)
Purpose: Takes standard gear inputs—Number of Teeth (N), Diametral Pitch (Pd in teeth/inch), and Pressure Angle (ϕ in degrees)—and applies common mechanical engineering formulas (e.g., for Pitch Diameter, Base Diameter, Addendum, Dedendum, etc.).

Output: Returns a comprehensive dictionary of over 18 key gear dimensions, calculated and provided in both millimeters (mm) and inches (in).

2. Large Language Model (LLM) Integration
Model: Uses the HuggingFaceTB/SmolLM2-135M-Instruct model, a small, fast, instruction-following model suitable for low-latency tasks.

Inference: The transformers pipeline is initialized with deterministic settings (do_sample=False, temperature=0.0) to ensure the LLM provides the most compliant, non-creative, and factual response possible.

Recommendation (llm_explain): This function extracts key size parameters (Pitch Diameter and Circular Pitch) from the calculation results and uses a highly restrictive system prompt to force the LLM to output EXACTLY ONE CONCISE SENTENCE suggesting a general machinery category (e.g., "precision instrumentation," "heavy-duty power transmission").

3. Gradio Interface
Inputs: Three numerical input fields for the required gear parameters.

Process: The run_once function acts as the main entry point, handling input validation, running the calculation, formatting the numerical results into a Pandas DataFrame for a clean tabular display, and generating the LLM-based narrative.

Outputs: Displays the complete table of calculated dimensions and the LLM-generated single-sentence use case recommendation below it. The interface also includes pre-set examples for testing.

This tool demonstrates a multi-purpose application where traditional engineering computation is augmented by the interpretive and summarization capabilities of a small LLM.

app.py

@@ -132,37 +132,70 @@ def _llm_generate(prompt: str, max_tokens: int) -> str:
 
 def llm_explain(results: dict, inputs: list) -> str:
     """
-    Generates a concise, single-sentence use case recommendation for the gear.
-    This function prepares the data and applies strict prompting to the LLM
-    to prevent rambling or lists.
+    Generates a clear, customized explanation for a non-technical user
+    based on the calculated gear dimensions.
     """
-    # Unpack relevant calculated values for the LLM context
-    circular_pitch_in = results['circular_pitch_in']
+
     pitch_diameter_in = results['pitch_diameter_in']
+    tooth_thickness_in = results['tooth_thickness_in']
+    circular_pitch_in = results['circular_pitch_in']
 
-    # Define the system prompt - Enforcing strict single-sentence output and content rules
+    # Estimate scale
+    if pitch_diameter_in < 2:
+        scale = "small"
+        examples = "clocks, cameras, or precision instruments"
+    elif pitch_diameter_in < 10:
+        scale = "medium"
+        examples = "bicycles, sewing machines, or automotive gearboxes"
+    else:
+        scale = "large"
+        examples = "wind turbines, cranes, or heavy mining machinery"
+
+    # Interpret tooth strength
+    if tooth_thickness_in < 0.05:
+        strength = "delicate and precise, best for very light loads"
+    elif tooth_thickness_in < 0.3:
+        strength = "balanced between precision and strength"
+    else:
+        strength = "very strong, made for heavy-duty work"
+
+    # Interpret circular pitch (spacing)
+    if circular_pitch_in < 0.2:
+        spacing = "fine and closely spaced for smooth, quiet motion"
+    elif circular_pitch_in < 1:
+        spacing = "moderate spacing for reliable general use"
+    else:
+        spacing = "wide spacing, rugged enough to handle shocks and dirt"
+
+    # System prompt
     system_prompt = (
-        "You are a mechanical engineer providing a design recommendation. "
-        "Your response MUST be **EXACTLY ONE CONCISE SENTENCE**. "
-        "Suggest ONE general category of machinery or application scale (e.g., 'precision instrumentation', 'heavy-duty mixer') for a gear "
-        "with these dimensions. **DO NOT** use bullet points, lists, or repeat input numbers."
+        "You are a mechanical engineer explaining gears to a non-technical user. "
+        "Write in 2–4 friendly sentences. "
+        "Explain what the size suggests, what the tooth shape/spacing means in practice, "
+        "and give unique example applications that fit the gear’s scale. "
+        "Do not simply restate the numbers given. "
+        "Be specific and avoid repeating the same examples across different gear sizes."
     )
 
-    # Define the user prompt - Providing the key size parameters
+    # User prompt (gear context)
     user_prompt = (
-        f"The gear has a Pitch Diameter of {pitch_diameter_in:.3f} inches and "
-        f"a Circular Pitch of {circular_pitch_in:.3f} inches. "
-        "Based only on these size parameters, provide its appropriate use case."
+        f"This is a {scale} gear. "
+        f"Its teeth are {strength}, and the spacing is {spacing}. "
+        f"Suggest everyday uses where a gear like this would make sense, such as {examples}. "
+        "Explain it in a way that feels useful and practical for someone who is not an engineer."
     )
 
-    # Apply the chat template and generate text with a low token limit for brevity
     formatted = _format_chat(system_prompt, user_prompt)
-    explanation = _llm_generate(formatted, max_tokens=80)
-    
-    # Check if the LLM returned an empty string and provide a helpful fallback.
+
+    explanation = _llm_generate(formatted, max_tokens=200)
+
+    # Fallback if the LLM fails
     if not explanation:
-        explanation = "The language model did not return a use case. Please ensure your inputs are reasonable and try again."
-        
+        explanation = (
+            f"This is a {scale} gear with {strength} and {spacing}. "
+            f"You’d expect to find gears like this in {examples}."
+        )
+
     return explanation