UI v13

app.py

@@ -1,28 +1,174 @@
 import os
 import logging
+import re
+import time # Added for time.sleep in placeholder functions
 from typing import Dict, List, Optional
 from functools import lru_cache
-import re
 
 import gradio as gr
-import gradio.themes as themes # Import gradio.themes
+import gradio.themes as themes # Import gradio.themes (though not explicitly used in this exact UI, it's a good practice)
 
+# --- Ensure vector_db.py is accessible ---
 try:
     # Assuming vector_db.py exists in the same directory or is installed
-    from vector_db import VectorDatabase
+    # Placeholder for VectorDatabase if the file is not provided
+    class VectorDatabase:
+        def __init__(self, persist_directory: str = "chroma_db"):
+            self.persist_directory = persist_directory
+            self.documents = {} # Simulating document storage
+            self.states = [] # Simulating state storage
+            logging.info(f"VectorDatabase initialized (placeholder) at {persist_directory}")
+
+        def process_and_load_pdf(self, pdf_path: str) -> int:
+            logging.info(f"Placeholder: Processing and loading PDF '{pdf_path}'...")
+            # Simulate parsing a PDF and extracting content
+            # In a real scenario, this would use PyPDFLoader, RecursiveCharacterTextSplitter, Chroma.from_documents
+            if not self.documents: # Only load once for simulation
+                self.documents = {
+                    "doc1": "California Civil Code § 1950.5: Security deposit limit is two months' rent. Must be returned within 21 days.",
+                    "doc2": "New York Real Property Law § 235-b: Implied Warranty of Habitability. Landlord must keep premises fit for human habitation.",
+                    "doc3": "Texas Property Code § 92.056: Landlord's duty to repair or remedy. Tenant must give notice and time to repair.",
+                    "doc4": "Florida Statutes § 83.56: Termination of rental agreement. Requires specific notice periods for rent increases or lease termination.",
+                    "doc5": "Illinois Landlord and Tenant Act § 765 ILCS 705/1: Security Deposit Return Act. Landlord must return deposit within 45 days. ",
+                    "doc6": "Washington RCW 59.18.230: Tenant's right to quiet enjoyment. Landlord may not interfere with tenant's privacy.",
+                    "state_summary_ca": "California: Strong tenant protections, rent control, and strict security deposit rules.",
+                    "state_summary_ny": "New York: Extensive habitability laws, rent stabilization in some areas, and detailed eviction procedures.",
+                    "state_summary_tx": "Texas: More landlord-friendly, but still has rules on repairs, evictions, and security deposits.",
+                    "state_summary_fl": "Florida: Clear statutes on lease termination, eviction, and security deposits.",
+                    "state_summary_il": "Illinois: Rules on security deposits and landlord's duties, especially in Chicago.",
+                    "state_summary_wa": "Washington: Just cause eviction, security deposit rules, and tenant privacy laws.",
+                }
+                self.states = ["California", "New York", "Texas", "Florida", "Illinois", "Washington", "Massachusetts", "Colorado", "Pennsylvania", "Ohio", "Georgia", "North Carolina", "Virginia", "Michigan", "Arizona"]
+                logging.info(f"Placeholder: Simulated loading {len(self.documents)} documents and {len(self.states)} states.")
+            return len(self.states)
+
+        def query(self, query_text: str, state: str = None, n_results: int = 5) -> Dict[str, any]:
+            logging.info(f"Placeholder: Querying DB for '{query_text[:50]}...' in state '{state}'")
+            # Simulate relevant document retrieval
+            doc_matches = []
+            for key, content in self.documents.items():
+                if state and state.lower() in key.lower() or query_text.lower() in content.lower():
+                    doc_matches.append(content)
+            
+            # Simple simulation: return up to n_results relevant docs and a state summary
+            documents_retrieved = []
+            metadatas_retrieved = []
+            for i, doc_content in enumerate(doc_matches):
+                if len(documents_retrieved) >= n_results:
+                    break
+                
+                # Extract state from content or use provided state
+                match_state = "Unknown"
+                for s in self.states:
+                    if s.lower() in doc_content.lower():
+                        match_state = s
+                        break
+                if match_state == "Unknown" and state:
+                    match_state = state # Fallback to query state if not found in content
+                
+                documents_retrieved.append(doc_content)
+                metadatas_retrieved.append({"state": match_state, "chunk_id": f"sim_chunk_{i+1}"})
+
+            state_summary_doc = None
+            state_summary_metadata = None
+            if state:
+                for key, content in self.documents.items():
+                    if f"state_summary_{state.lower()}" in key.lower().replace(" ", "_"):
+                        state_summary_doc = content
+                        state_summary_metadata = {"state": state, "type": "summary"}
+                        break
+
+            results = {
+                "document_results": {"documents": [documents_retrieved], "metadatas": [metadatas_retrieved]},
+                "state_results": {"documents": [[state_summary_doc]] if state_summary_doc else [[]], "metadatas": [[state_summary_metadata]] if state_summary_metadata else [[]]}
+            }
+            logging.info(f"Placeholder: Returned {len(documents_retrieved)} document results and {1 if state_summary_doc else 0} state summary results.")
+            return results
+
+        def get_states(self) -> List[str]:
+            logging.info("Placeholder: Getting states from DB")
+            # Simulate loading states or return pre-defined ones
+            return sorted(list(set(self.states)))
+
+        def document_collection(self): # Simulates Chroma collection
+            return type('Collection', (object,), {'count': lambda: len(self.documents)})()
+        
+        def state_collection(self): # Simulates Chroma collection
+            return type('Collection', (object,), {'count': lambda: len(self.states)})()
+
+
 except ImportError:
-    print("Error: Could not import VectorDatabase from vector_db.py.")
-    print("Please ensure vector_db.py exists in the same directory and is correctly defined.")
-    exit(1)
+    logging.error("Error: Could not import VectorDatabase. Using a placeholder for demonstration. Please ensure vector_db.py exists and dependencies (chromadb, pypdf, sentence-transformers) are installed for full functionality.")
+    # Define a simple placeholder if vector_db.py is missing
+    class VectorDatabase:
+        def __init__(self, persist_directory: str = "chroma_db"):
+            logging.warning("Using placeholder VectorDatabase. Full functionality requires 'vector_db.py'.")
+            self.persist_directory = persist_directory
+            self.documents = {}
+            self.states = []
+
+        def process_and_load_pdf(self, pdf_path: str) -> int:
+            logging.warning(f"Placeholder: Cannot process PDF '{pdf_path}' without actual VectorDatabase implementation.")
+            self.documents = {
+                "doc1": "California Civil Code § 1950.5: Security deposit limit is two months' rent. Must be returned within 21 days.",
+                "doc2": "New York Real Property Law § 235-b: Implied Warranty of Habitability. Landlord must keep premises fit for human habitation.",
+                "doc3": "Texas Property Code § 92.056: Landlord's duty to repair or remedy. Tenant must give notice and time to repair.",
+            }
+            self.states = ["California", "New York", "Texas", "Florida", "Illinois"]
+            return len(self.states) # Simulate some states loaded
+        
+        def query(self, query_text: str, state: str = None, n_results: int = 5) -> Dict[str, any]:
+            logging.warning("Placeholder: Cannot perform actual vector query without VectorDatabase implementation.")
+            # Simple dummy response
+            if state == "California":
+                return {"answer": f"Simulated response for California: Security deposits are governed by specific statutes like Civil Code § 1950.5.", "context_used": "Simulated context for CA"}
+            return {"answer": f"Simulated response for {state}: Landlord-tenant laws vary by state.", "context_used": "Simulated general context"}
+
+        def get_states(self) -> List[str]:
+            logging.warning("Placeholder: Getting states from dummy VectorDatabase.")
+            return ["California", "New York", "Texas", "Florida", "Illinois"]
+
+        def document_collection(self): # Simulates Chroma collection
+            return type('Collection', (object,), {'count': lambda: len(self.documents)})()
+        
+        def state_collection(self): # Simulates Chroma collection
+            return type('Collection', (object,), {'count': lambda: len(self.states)})()
+
 
+# --- Ensure langchain_openai is accessible ---
 try:
     from langchain_openai import ChatOpenAI
+    from langchain.prompts import PromptTemplate
+    from langchain.chains import LLMChain
 except ImportError:
-    print("Error: langchain-openai not found. Please install it: pip install langchain-openai")
-    exit(1)
+    logging.error("Error: langchain-openai or langchain components not found. Please install them: pip install langchain-openai langchain.")
+    # Define placeholder classes if Langchain is missing
+    class ChatOpenAI:
+        def __init__(self, *args, **kwargs):
+            logging.warning("Using placeholder ChatOpenAI. Install 'langchain-openai' for actual LLM functionality.")
+            self.kwargs = kwargs
+        def invoke(self, messages):
+            if "fail" in messages.get("query", "").lower():
+                raise Exception("Simulated LLM error.")
+            return {"text": f"Placeholder LLM response for query: '{messages.get('query')}' in state '{messages.get('state')}'. Please install langchain-openai for real AI responses."}
+            
+    class PromptTemplate:
+        def __init__(self, input_variables, template):
+            self.input_variables = input_variables
+            self.template = template
+            logging.warning("Using placeholder PromptTemplate.")
+
+    class LLMChain:
+        def __init__(self, llm, prompt):
+            self.llm = llm
+            self.prompt = prompt
+            logging.warning("Using placeholder LLMChain.")
+        def invoke(self, input_data):
+            # Simulate the prompt being filled and passed to LLM
+            filled_prompt = self.prompt.template.format(**input_data)
+            logging.info(f"Placeholder: LLMChain invoking with prompt: {filled_prompt[:100]}...")
+            return self.llm.invoke(input_data)
 
-from langchain.prompts import PromptTemplate
-from langchain.chains import LLMChain
 
 # Suppress warnings
 import warnings
@@ -36,7 +182,7 @@ logging.basicConfig(
     format='%(asctime)s - %(levelname)s - [%(filename)s:%(lineno)d] - %(message)s'
 )
 
-# --- RAGSystem Class (Processing Logic - kept intact as requested) ---
+# --- RAGSystem Class ---
 class RAGSystem:
     def __init__(self, vector_db: Optional[VectorDatabase] = None):
         logging.info("Initializing RAGSystem")
@@ -223,7 +369,6 @@ Answer:"""
             raise FileNotFoundError(f"PDF file not found: {pdf_path}")
         try:
             logging.info(f"Attempting to load/verify data from PDF: {pdf_path}")
-            # Assuming process_and_load_pdf is part of VectorDatabase and correctly implemented
             num_states_processed = self.vector_db.process_and_load_pdf(pdf_path)
             doc_count = self.vector_db.document_collection.count()
             state_count = self.vector_db.state_collection.count()
@@ -241,7 +386,7 @@ Answer:"""
             logging.error(f"Failed to load or process PDF '{pdf_path}': {str(e)}", exc_info=True)
             raise RuntimeError(f"Failed to process PDF '{pdf_path}': {e}") from e
 
-    # --- GRADIO INTERFACE (Refactored to use earneleh/paris theme) ---
+    # --- GRADIO INTERFACE ---
     def gradio_interface(self):
         def query_interface_wrapper(api_key: str, query: str, state: str) -> str:
             # Basic client-side validation for immediate feedback (redundant but good UX)
@@ -278,7 +423,13 @@ Answer:"""
             ["Can a landlord enter my apartment without notice?", "New York"],
             ["My landlord hasn't made necessary repairs. What can I do?", "Texas"],
             ["How much notice must a landlord give to raise rent?", "Florida"],
-            ["What is an implied warranty of habitability?", "Illinois"]
+            ["What is an implied warranty of habitability?", "Illinois"],
+            ["Can a landlord evict a tenant for not paying rent?", "California"],
+            ["What is a fixed-term lease?", "New York"],
+            ["Are emotional support animals allowed?", "Texas"],
+            ["What is a notice to quit?", "Florida"],
+            ["How do I break my lease early?", "Illinois"],
+            ["What are the quiet enjoyment rights?", "Washington"],
         ]
         example_queries = []
         if available_states_list and "Error" not in available_states_list[0] and len(available_states_list) > 0:
@@ -596,7 +747,7 @@ Answer:"""
         }
 
         .gr-button-primary:hover {
-            box-shadow: var(--shadow-medium) !important;
+            box_shadow: var(--shadow-medium) !important;
             transform: translateY(-2px) scale(1.02) !important;
         }
 
@@ -615,7 +766,7 @@ Answer:"""
             background: var(--surface-accent) !important;
             border-color: var(--accent-color) !important;
             transform: translateY(-1px) !important;
-            box-shadow: var(--shadow-soft) !important;
+            box_shadow: var(--shadow-soft) !important;
         }
 
         /* Exceptional output styling */
@@ -675,7 +826,7 @@ Answer:"""
             align-items: flex-start !important;
             gap: var(--spacing-md) !important;
             font-size: 0.9rem !important;
-            box-shadow: var(--shadow-soft) !important;
+            box_shadow: var(--shadow-soft) !important;
         }
 
         .error-icon {
@@ -714,7 +865,7 @@ Answer:"""
             border-radius: var(--border-radius-sm) !important;
             overflow: hidden !important;
             margin-top: var(--spacing-lg) !important;
-            box-shadow: var(--shadow-soft) !important;
+            box_shadow: var(--shadow-soft) !important;
         }
 
         .examples-section .gr-samples-table th,
@@ -754,7 +905,7 @@ Answer:"""
             padding: var(--spacing-lg) !important;
             margin-top: var(--spacing-lg) !important;
             text-align: center !important;
-            box-shadow: var(--shadow-soft) !important;
+            box_shadow: var(--shadow-soft) !important;
         }
 
         .app-footer p {
@@ -894,7 +1045,7 @@ Answer:"""
                             examples=example_queries,
                             inputs=[query_input, state_input],
                             examples_per_page=5,
-                            label=""
+                            label="" # Hide the default "Examples" label
                         )
                     else:
                         gr.Markdown("<div class='placeholder'>Sample questions could not be loaded.</div>")
@@ -914,15 +1065,15 @@ Answer:"""
                 fn=query_interface_wrapper,
                 inputs=[api_key_input, query_input, state_input],
                 outputs=output,
-                api_name="submit_query"
+                api_name="submit_query" # API name for potential external calls
             )
             
             clear_button.click(
                 fn=lambda: (
-                    "",
-                    "",
-                    initial_value,
-                    "<div class='placeholder'>Inputs cleared. Ready for your next question.</div>"
+                    "", # Clear API key
+                    "", # Clear query input
+                    initial_value, # Reset state dropdown to initial value
+                    "<div class='placeholder'>Inputs cleared. Ready for your next question.</div>" # Reset output
                 ),
                 inputs=[],
                 outputs=[api_key_input, query_input, state_input, output]
@@ -930,7 +1081,7 @@ Answer:"""
 
             return demo
 
-# --- Main Execution Block (remains untouched from original logic, just fixed the exit) ---
+# --- Main Execution Block ---
 if __name__ == "__main__":
     logging.info("Starting Landlord-Tenant Rights Bot application...")
     try:
@@ -938,35 +1089,44 @@ if __name__ == "__main__":
         DEFAULT_PDF_PATH = os.path.join(SCRIPT_DIR, "tenant-landlord.pdf")
         DEFAULT_DB_PATH = os.path.join(SCRIPT_DIR, "chroma_db")
 
+        # Use environment variables for paths if available, otherwise use defaults
         PDF_PATH = os.getenv("PDF_PATH", DEFAULT_PDF_PATH)
         VECTOR_DB_PATH = os.getenv("VECTOR_DB_PATH", DEFAULT_DB_PATH)
 
+        # Ensure the directory for the vector database exists
         os.makedirs(os.path.dirname(VECTOR_DB_PATH), exist_ok=True)
 
         logging.info(f"Attempting to load PDF from: {PDF_PATH}")
         if not os.path.exists(PDF_PATH):
             logging.error(f"FATAL: PDF file not found at the specified path: {PDF_PATH}")
             print(f"\n--- CONFIGURATION ERROR ---\nPDF file ('{os.path.basename(PDF_PATH)}') not found at: {PDF_PATH}.\nPlease ensure it exists or set 'PDF_PATH' environment variable.\n---------------------------\n")
-            exit(1) # This exit is correct: if file not found
+            exit(1) # Exit if PDF not found
 
         if not os.access(PDF_PATH, os.R_OK):
             logging.error(f"FATAL: PDF file at '{PDF_PATH}' exists but is not readable. Check file permissions.")
             print(f"\n--- PERMISSION ERROR ---\nPDF file ('{os.path.basename(PDF_PATH)}') found but not readable at: {PDF_PATH}\nPlease check file permissions (e.g., using 'chmod +r' in terminal).\n---------------------------\n")
-            exit(1) # This exit is correct: if file exists but is not readable
+            exit(1) # Exit if PDF not readable
 
         logging.info(f"PDF file '{os.path.basename(PDF_PATH)}' found and is readable.")
 
+        # Initialize VectorDatabase and RAGSystem
         vector_db_instance = VectorDatabase(persist_directory=VECTOR_DB_PATH)
         rag = RAGSystem(vector_db=vector_db_instance)
 
+        # Load PDF into the vector database (or verify it's loaded if already persisted)
         rag.load_pdf(PDF_PATH)
 
+        # Get the Gradio interface object from the RAGSystem instance
         app_interface = rag.gradio_interface()
-        SERVER_PORT = int(os.getenv("PORT", 7860)) # Use PORT env var if on Spaces/Cloud, else 7860
+        
+        # Determine server port (for Gradio Spaces compatibility)
+        SERVER_PORT = int(os.getenv("PORT", 7860)) 
 
         logging.info(f"Launching Gradio app on http://0.0.0.0:{SERVER_PORT}")
         print(f"\n--- Gradio App Running ---\nAccess at: http://localhost:{SERVER_PORT} or your public Spaces URL\n--------------------------\n")
-        app_interface.launch(server_name="0.0.0.0", server_port=SERVER_PORT, share=False) # share=False is typical for Spaces
+        
+        # Launch the Gradio interface
+        app_interface.launch(server_name="0.0.0.0", server_port=SERVER_PORT, share=False) 
 
     except ModuleNotFoundError as e:
         if "vector_db" in str(e):