update

src/legisqa_local/app.py

@@ -2,7 +2,7 @@
 
 import logging
 import streamlit as st
-from legisqa_local.config.settings import STREAMLIT_CONFIG, setup_environment, setup_chromadb
+from legisqa_local.config.settings import STREAMLIT_CONFIG, setup_environment, inspect_chromadb
 from legisqa_local.core.vectorstore import initialize_vectorstore
 from legisqa_local.components.sidebar import render_sidebar
 from legisqa_local.tabs.rag_tab import RAGTab
@@ -32,9 +32,9 @@ def main():
     logger.info("✅ Environment setup complete")
     
     # Setup ChromaDB (download if needed)
-    logger.info("💾 Setting up ChromaDB...")
-    setup_chromadb()
-    logger.info("✅ ChromaDB setup complete")
+    logger.info("💾 Inspecting ChromaDB...")
+    inspect_chromadb()
+    logger.info("✅ ChromaDB inspection complete")
     
     # Initialize vectorstore (load once and cache in session state)
     initialize_vectorstore()

src/legisqa_local/config/settings.py

@@ -58,73 +58,55 @@ def create_chroma_client():
     return client
 
 
-def inspect_chromadb(client: chromadb.HttpClient):
+def inspect_chromadb():
     """Inspect ChromaDB collection to verify it's working correctly"""
     logger.info("🔍 === ChromaDB Collection Inspection ===")
+    client = create_chroma_client()
+
+    # Get collection name from config
+    chroma_config = get_chroma_config()
+    collection_name = chroma_config["collection_name"]
     
-    try:
-        from chromadb import PersistentClient
+    logger.info(f"📋 Collection name: {collection_name}")
+    
+    # List all collections
+    collections = client.list_collections()
+    logger.info(f"📚 Available collections: {[c.name for c in collections]}")
+    
+    # Get the specific collection
+    if collection_name in [c.name for c in collections]:
+        collection = client.get_collection(name=collection_name)
+        logger.info(f"✅ Collection '{collection_name}' found")
         
-        # Get collection name from config
-        chroma_config = get_chroma_config()
-        collection_name = chroma_config["collection_name"]
+        # Get collection count
+        count = collection.count()
+        logger.info(f"📊 Collection count: {count} items")
+    else:
+        logger.error(f"❌ Collection '{collection_name}' not found!")
+        logger.error(f"Available collections: {[c.name for c in collections]}")
+        return
         
-        logger.info(f"📋 Collection name: {collection_name}")
+    # Process the collection (either the requested one or the fallback)
+    if count > 0:
+        # Get a sample item
+        logger.info("🔍 Fetching sample items...")
+        sample = collection.get(limit=3, include=["documents", "metadatas"])
         
-        # List all collections
-        collections = client.list_collections()
-        logger.info(f"📚 Available collections: {[c.name for c in collections]}")
+        if sample.get('ids'):
+            logger.info(f"📝 Sample IDs: {sample['ids']}")
         
-        # Get the specific collection
-        if collection_name in [c.name for c in collections]:
-            collection = client.get_collection(name=collection_name)
-            logger.info(f"✅ Collection '{collection_name}' found")
-            
-            # Get collection count
-            count = collection.count()
-            logger.info(f"📊 Collection count: {count} items")
-        elif collections:
-            # Try the first available collection if the requested one doesn't exist
-            logger.warning(f"⚠️  Collection '{collection_name}' not found, trying first available collection")
-            first_collection = collections[0]
-            logger.info(f"🔄 Using collection '{first_collection.name}' instead")
-            collection = first_collection
-            count = collection.count()
-            logger.info(f"📊 Collection count: {count} items")
-            
-            # Update environment variable for future use
-            os.environ["CHROMA_COLLECTION_NAME"] = first_collection.name
-            logger.info(f"🔧 Updated CHROMA_COLLECTION_NAME to: {first_collection.name}")
-        else:
-            logger.error(f"❌ Collection '{collection_name}' not found!")
-            logger.error(f"Available collections: {[c.name for c in collections]}")
-            return
-            
-        # Process the collection (either the requested one or the fallback)
-        if count > 0:
-            # Get a sample item
-            logger.info("🔍 Fetching sample items...")
-            sample = collection.get(limit=3, include=["documents", "metadatas"])
-            
-            if sample.get('ids'):
-                logger.info(f"📝 Sample IDs: {sample['ids']}")
-            
-            if sample.get('documents'):
-                logger.info(f"📄 Sample document (first 200 chars):")
-                logger.info(f"   {sample['documents'][0][:200]}...")
-            
-            if sample.get('metadatas'):
-                logger.info(f"🏷️  Sample metadata:")
-                for i, metadata in enumerate(sample['metadatas'][:2]):
-                    logger.info(f"   Item {i}: {metadata}")
-        else:
-            logger.warning("⚠️  Collection is empty!")
+        if sample.get('documents'):
+            logger.info(f"📄 Sample document (first 200 chars):")
+            logger.info(f"   {sample['documents'][0][:200]}...")
+        
+        if sample.get('metadatas'):
+            logger.info(f"🏷️  Sample metadata:")
+            for i, metadata in enumerate(sample['metadatas'][:2]):
+                logger.info(f"   Item {i}: {metadata}")
+    else:
+        logger.warning("⚠️  Collection is empty!")
             
-    except ImportError as e:
-        logger.error(f"❌ Import error during ChromaDB inspection: {e}")
-    except Exception as e:
-        logger.error(f"❌ Error inspecting ChromaDB: {e}")
-        logger.error(f"Exception type: {type(e).__name__}")
+
     
     logger.info("🔍 === ChromaDB Inspection Complete ===")