working ingredient analysis with allergic and diet type

db/models.py

@@ -15,6 +15,8 @@ class Ingredient(Base):
     safety_rating = Column(Integer, nullable=True)
     description = Column(Text, nullable=True)
     health_effects = Column(JSON, nullable=True)
+    allergic_info = Column(JSON, nullable=True)
+    diet_type = Column(String, nullable=True)  
     created_at = Column(DateTime(timezone=True), server_default=func.now())
     updated_at = Column(DateTime(timezone=True), onupdate=func.now())
     

db/repositories.py

@@ -37,7 +37,9 @@ class IngredientRepository:
             alternate_names=ingredient_data.alternate_names,
             safety_rating=ingredient_data.safety_rating,
             description=ingredient_data.description,
-            health_effects=ingredient_data.health_effects
+            health_effects=ingredient_data.health_effects,
+            allergic_info=ingredient_data.allergic_info,
+            diet_type=ingredient_data.diet_type
         )
         self.db.add(db_ingredient)
         self.db.commit()

interfaces/ingredientModels.py

@@ -10,7 +10,9 @@ class IngredientAnalysisResult(BaseModel):
     safety_rating: int = 5
     description: str = "No information found."
     health_effects: List[str] = Field(default_factory=lambda: ["Unknown"])
-    details_with_source: List[Dict[str, Any]] = [Field(default_factory=list)]
+    allergic_info: Optional[List[str]] = None  # New field
+    diet_type: Optional[str] = None  # New field
+    details_with_source: List[Dict[str, Any]] = Field(default_factory=list)
     
     class Config:
         from_attributes = True  # Enable ORM mode

migrations/versions/1c28462c052a_added_allergic_and_diet_type_in_.py

@@ -0,0 +1,34 @@
+"""added allergic and diet type in ingredient
+
+Revision ID: 1c28462c052a
+Revises: aaceebfe9545
+Create Date: 2025-04-12 21:40:50.748853
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = '1c28462c052a'
+down_revision: Union[str, None] = 'aaceebfe9545'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column('ingredients', sa.Column('allergic_info', sa.JSON(), nullable=True))
+    op.add_column('ingredients', sa.Column('diet_type', sa.String(), nullable=True))
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column('ingredients', 'diet_type')
+    op.drop_column('ingredients', 'allergic_info')
+    # ### end Alembic commands ###

services/ingredientFinderAgent.py

@@ -208,7 +208,7 @@ def search_web(ingredient: str) -> Dict[str, Any]:
     
     try:
         duckduckgo = DuckDuckGoSearchRun()
-        search_queries = [f"{ingredient} food ingredient safety", f"{ingredient} E-number food additive"]
+        search_queries = [f"{ingredient} food ingredient safety", f"{ingredient} E-number food additive",f"{ingredient}'s allergic information",f"is {ingredient} vegan,vegetarian or Non-vegetarian"]
         all_results = []
         for query in search_queries:
             result = duckduckgo.run(query)
@@ -318,7 +318,7 @@ def analyze_ingredient(state: IngredientState) -> IngredientState:
             google_api_key=api_key,
             model=model_name,
             temperature=0.3,  # Lower temperature for more factual responses
-            convert_system_message_to_human=True
+            # convert_system_message_to_human=True
         )
     except Exception as e:
         logger.error(f"Error initializing LLM: {e}")
@@ -399,6 +399,8 @@ def analyze_ingredient(state: IngredientState) -> IngredientState:
         2. List of potential health effects (both positive & negative, maximum 5 points)
         3. Brief description of what this ingredient is, how it's used, and its properties
         4. Alternative names for this ingredient
+        5. Allergic information of the ingredient like which type of allergies we can got, etc.
+        6. Diet Type of that ingredient like Vegan, Vegetarian, Non-Vegetarian
         
         Available data:
         {combined_data}
@@ -408,9 +410,11 @@ def analyze_ingredient(state: IngredientState) -> IngredientState:
         - "health_effects": (array of strings)
         - "description": (string)
         - "alternate_names": (array of strings)
+        - "allergic_info": (array of strings)
+        - "diet_type" : (string from vegan,vegetarian,non-vegetarian,unknown)
         
         Only include factual information supported by the provided data. If information is 
-        unavailable for any field, use appropriate default values.
+        unavailable for any field, use appropriate default values. But if information is "too obvious" you can fill appropriate information.
         """
         
         # Process with LLM
@@ -437,7 +441,9 @@ def analyze_ingredient(state: IngredientState) -> IngredientState:
                         "safety_rating": analysis.get("safety_rating", 5),
                         "description": analysis.get("description", "No description available."),
                         "health_effects": analysis.get("health_effects", []),
-                        "alternate_names": analysis.get("alternate_names", [])
+                        "alternate_names": analysis.get("alternate_names", []),
+                        "allergic_info": analysis.get("allergic_info", []),
+                        "diet_type": analysis.get("diet_type", "unknown"),
                     })
                     logger.info(f"Analysis complete - Safety Rating: {result['safety_rating']}")
                 else:
@@ -551,38 +557,38 @@ class IngredientInfoAgentLangGraph:
         
         # Run each tool directly in sequence and collect results
         logger.info(f"Searching local database for {ingredient}")
-        result = search_local_db(ingredient)
+        result = search_local_db.invoke(ingredient)
         if result.get("found", False):
             sources_data.append(result)
             logger.info(f"Local DB found data for {ingredient}")
         
         logger.info(f"Searching web for {ingredient}")
-        result = search_web(ingredient)
+        result = search_web.invoke(ingredient)
         if result.get("found", False):
             sources_data.append(result)
             logger.info(f"Web search found data for {ingredient}")
         
         logger.info(f"Searching Wikipedia for {ingredient}")
-        result = search_wikipedia(ingredient)
+        result = search_wikipedia.invoke(ingredient)
         if result.get("found", False):
             sources_data.append(result)
             logger.info(f"Wikipedia found data for {ingredient}")
         
         logger.info(f"Searching Open Food Facts for {ingredient}")
-        result = search_open_food_facts(ingredient)
+        result = search_open_food_facts.invoke(ingredient)
         if result.get("found", False):
             sources_data.append(result)
             logger.info(f"Open Food Facts found data for {ingredient}")
         
         # Optional - Add these if needed:
         logger.info(f"Searching USDA for {ingredient}")
-        result = search_usda(ingredient)
+        result = search_usda.invoke(ingredient)
         if result.get("found", False):
             sources_data.append(result)
             logger.info(f"USDA found data for {ingredient}")
         
         logger.info(f"Searching PubChem for {ingredient}")
-        result = search_pubchem(ingredient)
+        result = search_pubchem.invoke(ingredient)
         if result.get("found", False):
             sources_data.append(result)
             logger.info(f"PubChem found data for {ingredient}")