adding department specifics

app.py

@@ -14,6 +14,7 @@ from llama_index.embeddings import MistralAIEmbedding
 from llama_index.vector_stores import ChromaVectorStore
 from llama_index.storage.storage_context import StorageContext
 from llama_index import ServiceContext
+from utils import departments_list, region_list
 
 title = "Team LFD rotation finder app"
 description = "Propose a rotation for a farmer"
@@ -51,7 +52,7 @@ query_engine = index.as_query_engine(similarity_top_k=10)
 
 def create_prompt(farmSize, cultures):
     prompt = f"""
-    You are a French agronomical advisor, answering in French. Your task is to provide an concise advice as a table of rotation crops (with a prioritary suggestion and an alternative one) to the farmer what to seed in the next year and in which proportion. You will be given the historical information about the farmer, and context data given previously gives you average performances in yield per acre by region and by culture, as well as production costs and selling prices. Consider agronomical limitation and provide advice to the farmer to maximize his profit (maximum yield and revenue -- the difference between the selling price and the cost of production). There are three possible scenarii, pessimistic (lowest revenue), optimistic (highest revenue) and mean.
+    You are a French agronomical advisor, answering in French. Your task is to provide an concise advice as a table of rotation crops (with a prioritary suggestion and an alternative one) to the farmer what to seed in the next year and in which proportion. You will be given the historical information about the farmer, and context data given previously gives you average performances in yield per acre by region and by culture, as well as production costs and selling prices. Consider agronomical limitation and provide advice to the farmer to maximize his profit (maximum yield and revenue -- (the difference between the selling price and the cost of production) times the yield). There are three possible scenarii, pessimistic (lowest revenue), optimistic (highest revenue) and mean.
     #facts
     The farm area is {farmSize} ha. 
     """
@@ -74,8 +75,13 @@ InputForm = typing_extensions.TypedDict('InputForm', {
 
 # This function is the API endpoint the web app will use 
 def find_my_rotation(department: str, farmSize: float, benefitsFromCommonAgriculturalPolicy: bool, cultures: list[str], yields: dict[str, float]):
-    
+    department_name = departments_list.get(department)
+    dpt_yield = pd.read_csv(f'data/departments/{department_name}.csv')
+    yield_text = ''
+    for i, _ in dpt_yield:
+        yield_text += f"Dans le département de {department_name}, la production de {dpt_yield['Culture'][i].split('-')[1]} est de {dpt_yield['mean'][i]} en moyenne, de {dpt_yield['pessimistic'][i]} avec un scenario pessimiste et de {dpt_yield['optimistic'][i]} avec un scenario optimiste"
     # Create the prompt
+    index.insert(Document(text=yield_text))
     prompt = create_prompt(farmSize, cultures)
     # Question the model
     response = query_engine.query(prompt)