Refactor: Move backend files to backend/ directory and split .gitignore

backend/src/ea_chatbot/graph/nodes/query_analyzer.py

@@ -0,0 +1,73 @@
+from typing import List, Literal
+from pydantic import BaseModel, Field
+from ea_chatbot.graph.state import AgentState
+from ea_chatbot.config import Settings
+from ea_chatbot.utils.llm_factory import get_llm_model
+from ea_chatbot.utils.logging import get_logger, LangChainLoggingHandler
+from ea_chatbot.graph.prompts.query_analyzer import QUERY_ANALYZER_PROMPT
+
+class QueryAnalysis(BaseModel):
+    """Analysis of the user's query."""
+    data_required: List[str] = Field(description="List of data points or entities mentioned (e.g., ['2024 results', 'Florida']).")
+    unknowns: List[str] = Field(description="List of target information the user wants to know or needed for final answer (e.g., 'who won', 'total votes').")
+    ambiguities: List[str] = Field(description="List of CRITICAL missing details that prevent ANY analysis. Do NOT include database names or plot types if defaults can be used.")
+    conditions: List[str] = Field(description="List of any filters or constraints (e.g., ['year=2024', 'state=Florida']). Include context resolved from history.")
+    next_action: Literal["plan", "clarify", "research"] = Field(description="The next action to take. 'plan' for data analysis (even with defaults), 'research' for general knowledge, or 'clarify' ONLY for critical ambiguities.")
+
+def query_analyzer_node(state: AgentState) -> dict:
+    """Analyze the user's question and determine the next course of action."""
+    question = state["question"]
+    history = state.get("messages", [])
+    summary = state.get("summary", "")
+    
+    # Keep last 3 turns (6 messages)
+    history = history[-6:]
+    
+    settings = Settings()
+    logger = get_logger("query_analyzer")
+    
+    logger.info(f"Analyzing question: [italic]\"{question}\"[/italic]")
+    
+    # Initialize the LLM with structured output using the factory
+    # Pass logging callback to track LLM usage
+    llm = get_llm_model(
+        settings.query_analyzer_llm, 
+        callbacks=[LangChainLoggingHandler(logger=logger)]
+    )
+    structured_llm = llm.with_structured_output(QueryAnalysis)
+    
+    # Prepare messages using the prompt template
+    messages = QUERY_ANALYZER_PROMPT.format_messages(
+        question=question,
+        history=history,
+        summary=summary
+    )
+    
+    try:
+        # Invoke the structured LLM directly with the list of messages
+        analysis_result = structured_llm.invoke(messages)
+        analysis_result = QueryAnalysis.model_validate(analysis_result)
+        
+        analysis_dict = analysis_result.model_dump()
+        analysis_dict.pop("next_action")
+        next_action = analysis_result.next_action
+        
+        logger.info(f"Analysis complete. Next action: [bold magenta]{next_action}[/bold magenta]")
+        
+    except Exception as e:
+        logger.error(f"Error during query analysis: {str(e)}")
+        analysis_dict = {
+            "data_required": [],
+            "unknowns": [],
+            "ambiguities": [f"Error during analysis: {str(e)}"],
+            "conditions": []
+        }
+        next_action = "clarify"
+    
+    return {
+        "analysis": analysis_dict,
+        "next_action": next_action,
+        "iterations": 0
+    }
+        
+