Update learning_platform.py

learning_platform.py

@@ -9,10 +9,11 @@ from langchain_core.messages import BaseMessage, HumanMessage, AIMessage
 from langchain.embeddings import OpenAIEmbeddings
 from langchain_community.vectorstores import FAISS
 from langchain.tools import Tool
-from langgraph.graph import StateGraph,START,END
+from langgraph.graph import StateGraph, START, END
 from langgraph.graph.message import add_messages
 import streamlit as st
 
+
 @dataclass
 class Section:
     title: str
@@ -22,6 +23,7 @@ class Section:
     quiz_questions: List[Dict[str, Any]] = field(default_factory=list)
     is_complete: bool = False
 
+
 @dataclass
 class CourseModule:
     title: str
@@ -30,6 +32,7 @@ class CourseModule:
     sections: List[Section] = field(default_factory=list)
     is_complete: bool = False
 
+
 @dataclass
 class LearningPath:
     topic: str
@@ -39,6 +42,7 @@ class LearningPath:
     created_at: datetime
     is_generating: bool = True
 
+
 class CourseState(TypedDict):
     messages: Annotated[Sequence[BaseMessage], add_messages]
     topic: str
@@ -47,6 +51,7 @@ class CourseState(TypedDict):
     modules: List[Dict]
     status: str
 
+
 class CoursePrompts:
     @staticmethod
     def course_planning_prompt() -> str:
@@ -116,6 +121,7 @@ Return JSON:
     "feedback": ["improvement notes"]
 }"""
 
+
 class CourseBuilder:
     def __init__(self, api_key: str):
         self.api_key = api_key
@@ -135,63 +141,63 @@ class CourseBuilder:
         self.setup_graph()
 
     async def plan_course(self, state: CourseState) -> CourseState:
-    """Planner agent for course structure"""
-    st.session_state.agent_logs.append("📋 Planning course structure...")
+        """Planner agent for course structure"""
+        st.session_state.agent_logs.append("📋 Planning course structure...")
 
-    try:
-        # Use RAG to find similar course structures
-        similar_courses = self.vector_store.similarity_search(
-            f"{state['topic']} {state['difficulty']} course",
-            k=2
-        )
-        context = "\n".join([doc.page_content for doc in similar_courses])
+        try:
+            # Use RAG to find similar course structures
+            similar_courses = self.vector_store.similarity_search(
+                f"{state['topic']} {state['difficulty']} course",
+                k=2
+            )
+            context = "\n".join([doc.page_content for doc in similar_courses])
 
-        prompt = self.prompts.course_planning_prompt()
-        response = await self.llm.apredict(
-            prompt.format(
-                topic=state["topic"],
-                difficulty=state["difficulty"],
-                context=context
+            prompt = self.prompts.course_planning_prompt()
+            response = await self.llm.apredict(
+                prompt.format(
+                    topic=state["topic"],
+                    difficulty=state["difficulty"],
+                    context=context
+                )
             )
-        )
 
-        # Index the course plan for future reference
-        course_plan = json.loads(response)
-        self.vector_store.add_texts(
-            [json.dumps(course_plan)],
-            metadatas=[{"type": "course_plan", "topic": state["topic"]}]
-        )
+            # Index the course plan for future reference
+            course_plan = json.loads(response)
+            self.vector_store.add_texts(
+                [json.dumps(course_plan)],
+                metadatas=[{"type": "course_plan", "topic": state["topic"]}]
+            )
 
-        st.session_state.agent_logs.append("✅ Course structure planned")
-        return {
-            **state,
-            "messages": [AIMessage(content=response)],
-            "status": "planning_complete"
-        }
-    except Exception as e:
-        error_message = f"Course creation error: {str(e)}"
-        st.session_state.agent_logs.append(error_message)
-        return {
-            **state,
-            "messages": [AIMessage(content=error_message)],
-            "status": "planning_failed"
-        }
+            st.session_state.agent_logs.append("✅ Course structure planned")
+            return {
+                **state,
+                "messages": [AIMessage(content=response)],
+                "status": "planning_complete"
+            }
+        except Exception as e:
+            error_message = f"Course creation error: {str(e)}"
+            st.session_state.agent_logs.append(error_message)
+            return {
+                **state,
+                "messages": [AIMessage(content=error_message)],
+                "status": "planning_failed"
+            }
 
     async def create_content(self, state: CourseState) -> CourseState:
         """Content creator agent using RAG"""
         st.session_state.agent_logs.append(f"📝 Creating module {state['current_module'] + 1}...")
-        
+
         messages = state["messages"]
         current_plan = json.loads(messages[-1].content)
         current_module = current_plan["modules"][state["current_module"]]
-        
+
         # Use RAG for content enhancement
         similar_content = self.vector_store.similarity_search(
             current_module["title"],
             k=3
         )
         context = "\n".join([doc.page_content for doc in similar_content])
-        
+
         prompt = self.prompts.module_content_prompt()
         content = await self.llm.apredict(
             prompt.format(
@@ -200,7 +206,7 @@ class CourseBuilder:
                 objectives=", ".join(current_module["objectives"])
             )
         )
-        
+
         # Index new content
         try:
             content_json = json.loads(content)
@@ -214,7 +220,7 @@ class CourseBuilder:
                 )
         except Exception as e:
             st.session_state.agent_logs.append(f"⚠️ Warning: Couldn't index content: {str(e)}")
-        
+
         st.session_state.agent_logs.append("✅ Module content created")
         return {
             **state,
@@ -225,17 +231,17 @@ class CourseBuilder:
     async def review_content(self, state: CourseState) -> CourseState:
         """Content reviewer agent with RAG"""
         st.session_state.agent_logs.append("🔍 Reviewing content quality...")
-        
+
         messages = state["messages"]
         content = messages[-1].content
-        
+
         # Use RAG for content review
         similar_contents = self.vector_store.similarity_search(
             content,
             k=2
         )
         context = "\n".join([doc.page_content for doc in similar_contents])
-        
+
         prompt = self.prompts.review_prompt()
         review = await self.llm.apredict(
             prompt.format(
@@ -243,9 +249,9 @@ class CourseBuilder:
                 context=context
             )
         )
-        
+
         review_data = json.loads(review)
-        
+
         if review_data["approved"]:
             st.session_state.agent_logs.append("✅ Content approved")
             return {
@@ -270,12 +276,12 @@ class CourseBuilder:
     def setup_graph(self):
         """Set up the agent workflow graph"""
         workflow = StateGraph(CourseState)
-        
+
         # Add agent nodes
         workflow.add_node("planner", self.plan_course)
         workflow.add_node("creator", self.create_content)
         workflow.add_node("reviewer", self.review_content)
-        
+
         # Define workflow
         workflow.add_edge(START, "planner")  # Connect START to planner
         workflow.add_edge("planner", "creator")
@@ -288,9 +294,10 @@ class CourseBuilder:
             }
         )
         workflow.add_edge("reviewer", "creator")
-        
+
         self.graph = workflow.compile()
-        
+
+
 class LearningPlatform:
     def __init__(self, api_key: str = None):
         self.api_key = api_key or os.getenv("OPENAI_API_KEY")
@@ -306,13 +313,13 @@ class LearningPlatform:
                 "modules": [],
                 "status": "planning"
             }
-            
+
             final_state = None
             async for output in self.course_builder.graph.astream(initial_state):
                 final_state = output
-            
+
             course_content = json.loads(final_state["messages"][-1].content)
-            
+
             # Create first module
             first_module = CourseModule(
                 title=course_content["modules"][0]["title"],
@@ -320,7 +327,7 @@ class LearningPlatform:
                 prerequisites=course_content["modules"][0].get("prerequisites", [])
             )
             first_module.is_complete = True
-            
+
             return LearningPath(
                 topic=topic,
                 description=course_content["description"],
@@ -335,7 +342,7 @@ class LearningPlatform:
                 created_at=datetime.now(),
                 is_generating=True
             )
-            
+
         except Exception as e:
             raise Exception(f"Course creation error: {str(e)}")
 
@@ -357,11 +364,11 @@ class LearningPlatform:
                     "modules": [],
                     "status": "creating"
                 }
-                
+
                 final_state = None
                 async for output in self.course_builder.graph.astream(state):
                     final_state = output
-                
+
                 content = json.loads(final_state["messages"][-1].content)
                 module.sections = [Section(**s) for s in content["sections"]]
                 module.is_complete = True