Update agent.py

agent.py

@@ -137,15 +137,36 @@ with open("system_prompt.txt", "r", encoding="utf-8") as f:
 sys_msg = SystemMessage(content=system_prompt)
 
 
-    
+
+# -------------------------------
+# Step 2: Load the JSON file or tasks (Replace this part if you're loading tasks dynamically)
+# -------------------------------
+# Here we assume the tasks are already fetched from a URL or file.
+# For now, using an example JSON array directly. Replace this with the actual loading logic.
+
+tasks = [
+    {
+        "task_id": "8e867cd7-cff9-4e6c-867a-ff5ddc2550be",
+        "question": "How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)? You can use the latest 2022 version of English Wikipedia.",
+        "Level": "1",
+        "file_name": ""
+    },
+    {
+        "task_id": "a1e91b78-d3d8-4675-bb8d-62741b4b68a6",
+        "question": "In the video https://www.youtube.com/watch?v=L1vXCYZAYYM, what is the highest number of bird species to be on camera simultaneously?",
+        "Level": "1",
+        "file_name": ""
+    }
+]
+
 # -------------------------------
-# Step 2: Create Documents from Each JSON Object
+# Step 3: Create Documents from Each JSON Object
 # -------------------------------
 docs = []
 for task in tasks:
     # Debugging: Print the keys of each task to ensure 'question' exists
     print(f"Keys in task: {task.keys()}")
-    
+
     # Ensure the required field 'question' exists
     if 'question' not in task:
         print(f"Skipping task with missing 'question' field: {task}")
@@ -163,8 +184,9 @@ for task in tasks:
     docs.append(Document(page_content=content, metadata=task))
 
 
+
 # -------------------------------
-# Step 3: Set up HuggingFace Embeddings and FAISS VectorStore
+# Step 4: Set up HuggingFace Embeddings and FAISS VectorStore
 # -------------------------------
 # Initialize HuggingFace Embedding model
 embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
@@ -177,8 +199,10 @@ vector_store.save_local("faiss_index")
 
 #print("✅ FAISS index created and saved locally.")
 
+
+
 # -------------------------------
-# Step 4: Create Retriever Tool (for use in LangChain)
+# Step 5: Create Retriever Tool (for use in LangChain)
 # -------------------------------
 retriever = vector_store.as_retriever()