removed jd agent

app/graph.py

@@ -5,35 +5,28 @@ from langgraph.graph import StateGraph,END,START
 from langgraph.types import RetryPolicy
 
 
-node_retry = RetryPolicy(
-    max_attempts=3,
-    initial_interval=1.5,
-    retry_on=[ConnectionError]
-)
+# node_retry = RetryPolicy(
+#     max_attempts=3,
+#     initial_interval=1.5,
+#     retry_on=[ConnectionError]
+# )
 
 builder = StateGraph(OnboardingState)
 
 # Define Nodes
 builder.add_node("input_node", input_node)
 builder.add_node("resume_data_extraction", extractResumeDataNode)
-builder.add_node("jd_data_extraction", extractJDDataNode ,retry_policy=node_retry)
 builder.add_node("skill_gap_analysis", skill_gap_node)
 
 # The ReAct Agent Node
 builder.add_node("roadmap_planning_agent", roadmap_planning_node)
-
 # The Tool Execution Node (Required for the loop)
 builder.add_node("tools", ToolNode(roadmap_planner_agent_tools))
-
 # 5. Define Edges and Workflow
 builder.add_edge(START, "input_node")
 builder.add_edge("input_node", "resume_data_extraction")
-builder.add_edge("input_node", "jd_data_extraction")
-
 # Join Parallel Extractions
 builder.add_edge("resume_data_extraction", "skill_gap_analysis")
-builder.add_edge("jd_data_extraction", "skill_gap_analysis")
-
 # Start the Planning Phase
 builder.add_edge("skill_gap_analysis", "roadmap_planning_agent")
 
@@ -51,4 +44,15 @@ builder.add_conditional_edges(
 builder.add_edge("tools", "roadmap_planning_agent")
 
 # 6. Compile
-graph = builder.compile()
+graph = builder.compile()
+
+
+try:
+    # This creates a PNG and saves it to your project folder
+    graph_png = graph.get_graph().draw_mermaid_png()
+    with open("graph.png", "wb") as f:
+        f.write(graph_png)
+    print("--- Graph image saved as 'graph.png' ---")
+except Exception as e:
+    # This happens if you don't have the 'pypydot' or 'graphviz' dependencies
+    print(f"Could not generate graph image: {e}")

app/nodes/graphnodes.py

@@ -55,50 +55,46 @@ def extractResumeDataNode(state: OnboardingState):
     return {"resume_data": result["parsed"]}
 
 
-def extractJDDataNode(state: OnboardingState):
-    """Extract structured job description data using JD agent."""
-    jd_text = state.get("job_description", "")
+# def extractJDDataNode(state: OnboardingState):
+#     """Extract structured job description data using JD agent."""
+#     jd_text = state.get("job_description", "")
 
-    if not jd_text or len(jd_text.strip()) < 5:
-        logger.warning("job_description text is missing from state")
-        return {"JobDescriptionExtract_data": JobDescriptionExtract()}
+#     if not jd_text or len(jd_text.strip()) < 5:
+#         logger.warning("job_description text is missing from state")
+#         return {"JobDescriptionExtract_data": JobDescriptionExtract()}
 
-    logger.info(f"Extracting JD from {len(jd_text)} characters")
+#     logger.info(f"Extracting JD from {len(jd_text)} characters")
 
-    messages = [
-        SystemMessage(content=jd_agent_prompt),
-        HumanMessage(content=f"<job_description>{jd_text}</job_description>")
-    ]
+#     messages = [
+#         SystemMessage(content=jd_agent_prompt),
+#         HumanMessage(content=f"<job_description>{jd_text}</job_description>")
+#     ]
 
-    try:
-        result = jd_agent.invoke(messages)
-        parsed_data = result.get("parsed") if isinstance(result, dict) else result
+#     try:
+#         result = jd_agent.invoke(messages)
+#         parsed_data = result.get("parsed") if isinstance(result, dict) else result
 
-        if parsed_data.job_title is None and parsed_data.tools_technologies is None:
-            logger.warning("JD extraction returned empty schema")
-        else:
-            logger.info(f"Successfully extracted job title: {parsed_data.job_title}")
+#         if parsed_data.job_title is None and parsed_data.tools_technologies is None:
+#             logger.warning("JD extraction returned empty schema")
+#         else:
+#             logger.info(f"Successfully extracted job title: {parsed_data.job_title}")
 
-        return {"JobDescriptionExtract_data": parsed_data}
+#         return {"JobDescriptionExtract_data": parsed_data}
 
-    except Exception as e:
-        logger.error(f"JD extraction failed: {str(e)}")
-        return {"JobDescriptionExtract_data": JobDescriptionExtract()}
+#     except Exception as e:
+#         logger.error(f"JD extraction failed: {str(e)}")
+#         return {"JobDescriptionExtract_data": JobDescriptionExtract()}
 
 
 def skill_gap_node(state: OnboardingState):
     """Analyze skill gaps between resume and job description."""
     resume_data = state["resume_data"]
     candidate_name = state.get("candidate_name", "Candidate")
-
     # Convert Pydantic models to lean dicts (exclude None values)
     lean_resume_dict = resume_data.model_dump(exclude_none=True)
-    lean_jd_dict = state["JobDescriptionExtract_data"].model_dump(exclude_none=True)
-
+    jd_text = state.get("job_description", "")
     # Serialize to JSON
     lean_resume_json = json.dumps(lean_resume_dict, indent=2)
-    lean_jd_json = json.dumps(lean_jd_dict, indent=2)
-
     # Clean prompt with proper formatting
     prompt_text = f"""Analyze the skill gaps for the following candidate:
 
@@ -108,7 +104,7 @@ Resume:
 {lean_resume_json}
 
 Job Description:
-{lean_jd_json}
+{jd_text}
 
 Please provide a detailed skill gap analysis."""
 

app/test.py

@@ -47,9 +47,7 @@ config = {"configurable": {"thread_id": THREAD_ID}}
 
 # print(final_result['resume_data'])
 
-# print()
 
-# print(final_result['JobDescriptionExtract_data'])
 
 # print()