Update app/services/extraction.py

app/services/extraction.py

@@ -346,10 +346,11 @@ Output: {{
 ---
 Now process this input:
 Input: "{text}"
-Output: ONLY provide the JSON data with no additional formatting, markdowns, or annotations.
+Output:
 """}
     ]
 
+    # Send the prompt to OpenAI API
     prompt = ""
     for message in messages:
         if message["role"] == "system":
@@ -362,66 +363,24 @@ Output: ONLY provide the JSON data with no additional formatting, markdowns, or
     
     # Generate response
     response = model.generate_content(prompt, 
-                                   generation_config=genai.types.GenerationConfig(
-                                       temperature=0,
-                                       max_output_tokens=150,
-                                       top_p=1
-                                   ))
+                                     generation_config=genai.types.GenerationConfig(
+                                         temperature=0,
+                                         max_output_tokens=150,
+                                         top_p=1
+                                     ))
     
-    # Process the response - handle complex responses correctly
-    try:
-        # Try the simple accessor first
-        if hasattr(response, 'text'):
-            output_text = response.text.strip()
-        # If that fails, try accessing the parts
-        elif hasattr(response, 'parts') and response.parts:
-            output_text = ''.join([part.text for part in response.parts if hasattr(part, 'text')])
-        # If that fails, try the full path
-        elif hasattr(response, 'candidates') and response.candidates:
-            parts = response.candidates[0].content.parts
-            output_text = ''.join([part.text for part in parts if hasattr(part, 'text')])
-        else:
-            # Last resort: try to find any text in the response
-            output_text = str(response)
-            if not '{' in output_text:  # Check if it looks like JSON
-                # If we can't extract valid text, return a simple fallback
-                return {
-                    "category": "",
-                    "calories": "",
-                    "time": "",
-                    "ingredients": ["ingredient from " + text],
-                    "keywords": ["keyword from " + text],
-                    "keywords_name": []
-                }
-    except Exception as e:
-        print(f"Error processing Gemini response: {e}")
-        # Log additional information about the response for debugging
-        print(f"Response type: {type(response)}")
-        print(f"Response attributes: {dir(response)}")
-        return {
-            "error": f"Failed to process Gemini response: {str(e)}",
-            "ingredients": [text],  # Include the search text as an ingredient for fallback
-            "keywords": [text],
-            "keywords_name": []
-        }
+    # Process the response
+    output_text = response.text.strip()
+    
+    # Check if output is wrapped in markdown code blocks and extract the JSON if needed
+    if output_text.strip().startswith('```') and '```' in output_text:
+        import re
+        match = re.search(r'```(?:json)?\n(.*?)\n```', output_text, re.DOTALL)
+        if match:
+            output_text = match.group(1).strip()
     
     try:
-        # Extract JSON from markdown code blocks if needed
-        if output_text.strip().startswith('```') and '```' in output_text:
-            # Extract the content between the code block markers
-            import re
-            match = re.search(r'```(?:json)?\n(.*?)\n```', output_text, re.DOTALL)
-            if match:
-                output_text = match.group(1).strip()
-            else:
-                # Try another pattern without the language specification
-                match = re.search(r'```(.*?)```', output_text, re.DOTALL)
-                if match:
-                    output_text = match.group(1).strip()
-        
-        # Now parse the cleaned JSON
         result = json.loads(output_text)
-        
         # Update category with closest match from dataset
         original_category = result["category"]
         matched_category = find_closest_category(original_category)
@@ -438,11 +397,98 @@ Output: ONLY provide the JSON data with no additional formatting, markdowns, or
                 result["keywords_name"] = result.get("keywords_name", []) + ["beverages", "caffeinated", "coffee"]
                 result["ingredients"] = result.get("ingredients", []) + ["coffee beans", "water"]
                 
-            # ... (rest of your conditional processing)
+            elif "smoothie bowl" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["beverages", "healthy", "smoothie bowl"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["beverages", "smoothie bowl"]
+                result["ingredients"] = result.get("ingredients", []) + ["fruits", "yogurt", "granola"]
+                
+            elif "kombucha" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["beverage", "fermented", "kombucha"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["beverages", "kombucha"]
+                result["ingredients"] = result.get("ingredients", []) + ["tea", "sugar", "SCOBY"]
+
+            elif "herbal tea" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["beverages", "caffeine-free", "herbal tea"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["beverages", "herbal tea"]
+                result["ingredients"] = result.get("ingredients", []) + ["herbs", "water"]
+
+            elif "seaweed" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["ingredient", "seafood", "seaweed"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["seaweed"]
+                result["ingredients"] = result.get("ingredients", []) + ["seaweed"]
+
+            elif "vegan cheese" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["dairy-free", "vegan", "cheese"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["vegan cheese"]
+                result["ingredients"] = result.get("ingredients", []) + ["cashews", "nutritional yeast", "coconut oil"]
+
+            elif "air fryer" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["cooking method", "air fryer", "healthy"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["air fryer"]
+                result["ingredients"] = result.get("ingredients", [])  # Ingredients vary with recipe, left blank
+
+            elif "instant pot" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["cooking method", "instant pot", "pressure cooker"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["instant pot"]
+                result["ingredients"] = result.get("ingredients", [])  # Ingredients vary with recipe, left blank
+
+            elif "sous vide" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["cooking method", "sous vide", "precision cooking"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["sous vide"]
+                result["ingredients"] = result.get("ingredients", [])  # Ingredients vary with recipe, left blank
+
+            elif "paleo" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["diet", "paleo", "low-carb"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["paleo"]
+                result["ingredients"] = result.get("ingredients", [])  # Ingredients vary with recipe, left blank
+
+            elif "fodmap" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["diet", "fodmap", "digestive health"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["fodmap"]
+                result["ingredients"] = result.get("ingredients", [])  # Ingredients vary with recipe, left blank
+
+            elif "cold brew" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["beverages", "caffeinated", "cold coffee"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["beverages", "cold brew"]
+                result["ingredients"] = result.get("ingredients", []) + ["coffee grounds", "water"]
+
+            elif "matcha" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["beverages", "green tea", "matcha"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["beverages", "matcha"]
+                result["ingredients"] = result.get("ingredients", []) + ["matcha powder", "water", "milk"]
+
+            elif "smoothie" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["beverages", "healthy", "smoothie"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["beverages", "smoothie"]
+                result["ingredients"] = result.get("ingredients", []) + ["fruits", "milk", "yogurt"]
+
+            elif "protein shake" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["beverages", "high protein", "shake"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["beverages", "protein shake"]
+                result["ingredients"] = result.get("ingredients", []) + ["protein powder", "milk", "banana"]
+
+            elif "oat milk" in text.lower() or "almond milk" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["dairy-free", "vegan", "plant-based milk"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["oat milk" if "oat" in text.lower() else "almond milk"]
+                result["ingredients"] = result.get("ingredients", []) + ["oats" if "oat" in text.lower() else "almonds", "water"]
+
+            elif "zoodles" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["low carb", "gluten-free", "vegetable noodles", "noodles"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["zoodles", "noodles"]
+                result["ingredients"] = result.get("ingredients", []) + ["zucchini"]
+
+            elif "avocado toast" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["breakfast", "healthy", "avocado"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["avocado toast"]
+                result["ingredients"] = result.get("ingredients", []) + ["avocado", "bread"]
+
+            elif "golden milk" in text.lower():
+                result["keywords"] = result.get("keywords", []) + ["beverage", "turmeric", "anti-inflammatory"]
+                result["keywords_name"] = result.get("keywords_name", []) + ["golden milk"]
+                result["ingredients"] = result.get("ingredients", []) + ["turmeric", "milk", "honey", "spices"]
+            # other cases...
             
-    except json.JSONDecodeError as e:
-        print(f"JSON parse error: {e}")
-        print(f"Failed to parse: {output_text}")
+    except json.JSONDecodeError:
         result = {"error": "Failed to parse JSON", "output": output_text}
     
     return result