Update rag_agent.py

rag_agent.py

@@ -19,29 +19,31 @@ load_dotenv()
 
 # Define paths
 BNI_CSV_FILE = "bni_pearl_chapter.csv"
-# BNI_JSON_FILE = "bni_pearl_chapter.json"
+BNI_JSON_FILE = "bni_pearl_chapter.json"
 
-# Define the path to the structured BNI dataset (JSON file)
-BNI_DATA_PATH = "bni_pearl_chapter.json"
+# 1️⃣ **Ensure JSON file exists by converting CSV to JSON**
+def convert_csv_to_json():
+    """
+    Converts the BNI CSV file into a structured JSON format.
+    """
+    if not os.path.exists(BNI_CSV_FILE):
+        raise FileNotFoundError(f"❌ Error: The BNI CSV file {BNI_CSV_FILE} is missing.")
 
-# Ensure the JSON file exists
-if not os.path.exists(BNI_DATA_PATH):
-    raise FileNotFoundError(f"❌ Error: The BNI data file {BNI_DATA_PATH} is missing.")
+    df = pd.read_csv(BNI_CSV_FILE)
 
-# 1️⃣ **Convert CSV to JSON for structured retrieval**
-# def convert_csv_to_json():
-#     df = pd.read_csv(BNI_CSV_FILE)
-#     json_data = df.to_dict(orient="records")
-    
-#     with open(BNI_JSON_FILE, "w") as file:
-#         json.dump(json_data, file, indent=4)
+    if df.empty:
+        raise ValueError(f"❌ Error: {BNI_CSV_FILE} is empty!")
 
-#     print(f"✅ Converted {BNI_CSV_FILE} to JSON format.")
+    json_data = df.to_dict(orient="records")
 
-# # Run the conversion **only if JSON does not exist**
-# if not os.path.exists(BNI_JSON_FILE):
-#     convert_csv_to_json()
+    with open(BNI_JSON_FILE, "w") as file:
+        json.dump(json_data, file, indent=4)
 
+    print(f"✅ Converted {BNI_CSV_FILE} to JSON format.")
+
+# Run the conversion **only if JSON does not exist**
+if not os.path.exists(BNI_JSON_FILE):
+    convert_csv_to_json()
 
 # 2️⃣ **Create a Vector Database for RAG**
 vector_db = LanceDb(
@@ -53,8 +55,8 @@ vector_db = LanceDb(
 
 # 3️⃣ **Create Knowledge Base from JSON**
 knowledge_base = JSONKnowledgeBase(
-    file_path=BNI_DATA_PATH,  
-    vector_db=vector_db,  # Use vector DB for faster search
+    file_path=BNI_JSON_FILE,  # Ensure the correct JSON file is used
+    vector_db=vector_db,  # Use vector DB for efficient search
 )
 
 # **Load Knowledge Base** (Run this once)
@@ -75,14 +77,12 @@ def recommend_bni_connections(company_data: str) -> str:
     
     Args:
         company_data (str): The user's company information.
-
     Returns:
         str: A list of relevant BNI members and how they can help.
     """
     query = f"""
     Given the following business details:
     - **Company Information:** {company_data}
-
     Search the BNI Pearl Chapter database and recommend **3-5 members** who can 
     help this business **through referrals, networking, or industry connections.** 
     Provide:
@@ -91,4 +91,4 @@ def recommend_bni_connections(company_data: str) -> str:
     3. **How They Can Help**
     """
     response = rag_agent.run(query)
-    return response.content  # Return recommended BNI connections
+    return response.content  # Return recommended BNI connections