Update app.py

app.py

@@ -1,10 +1,19 @@
 import gradio as gr
+import json
 from transformers import pipeline
 
-# Load models
+# Load AI models
 code_analyzer = pipeline("text-classification", model="microsoft/codebert-base")
 nlp_model = pipeline("text2text-generation", model="google/flan-t5-large")
 
+# Load FAQ fallback from JSON file
+try:
+    with open("faq.json", "r") as f:
+        faq_fallbacks = json.load(f)
+except FileNotFoundError:
+    faq_fallbacks = {}
+    print("⚠️ Warning: faq.json not found. Only AI model will be used.")
+
 # Code Review Function
 def analyze_code(code):
     if not code.strip():
@@ -12,7 +21,7 @@ def analyze_code(code):
     result = code_analyzer(code)
     return result[0]["label"], "Consider refactoring for better performance", "Medium"
 
-# Metadata Validator (Mock)
+# Metadata Validator
 def validate_metadata(metadata):
     if not metadata.strip():
         return "No metadata provided.", "", ""
@@ -23,15 +32,16 @@ def process_nlp_query(query):
     if not query.strip():
         return "No query provided."
 
-    # Enhanced prompt
-    prompt = f"""
-    You are a Salesforce and Apex expert. Provide a clear and technically accurate answer to the following question:
+    normalized = query.lower().strip()
 
-    {query}
+    # Check fallback JSON for exact match
+    if normalized in faq_fallbacks:
+        return faq_fallbacks[normalized]
 
-    Answer:
+    # Fallback to AI model if not in faq.json
+    prompt = f"""
+    You are a Salesforce and Apex expert. Provide a clear and accurate answer to the following question:\n\n{query}\n\nAnswer:
     """
-
     result = nlp_model(
         prompt,
         max_length=256,
@@ -44,18 +54,13 @@ def process_nlp_query(query):
 
     output = result[0]["generated_text"]
 
-    # Extract answer after "Answer:"
+    # Clean output
     if "Answer:" in output:
         output = output.split("Answer:")[-1]
 
-    # Remove duplicate lines
     lines = output.strip().splitlines()
-    unique_lines = []
     seen = set()
-    for line in lines:
-        if line.strip() not in seen:
-            seen.add(line.strip())
-            unique_lines.append(line.strip())
+    unique_lines = [line.strip() for line in lines if line.strip() not in seen and not seen.add(line.strip())]
 
     return "\n".join(unique_lines).strip()