Update app.py

app.py

@@ -188,22 +188,37 @@ def load_vector_store(embeddings):
                 if len(matches) > 100:
                     logger.info(f"   Found {len(matches)} potential document fragments")
                     
-                    # Create simple documents from extracted text
+                    # Get total vectors in index
+                    num_vectors = index.ntotal
+                    logger.info(f"   FAISS index has {num_vectors} vectors")
+                    
+                    # Create documents matching the number of vectors
                     new_docstore_dict = {}
                     index_to_docstore_id = {}
                     
-                    for idx, match in enumerate(matches[:15000]):  # Limit to 15k docs
+                    # Use the actual number of vectors, not extracted matches
+                    for idx in range(min(num_vectors, len(matches))):
                         try:
-                            content = match.decode('utf-8', errors='ignore').strip()
-                            if len(content) > 50:  # Only keep substantial content
-                                doc_id = str(idx)
-                                new_doc = Document(
-                                    page_content=content,
-                                    metadata={}
-                                )
-                                new_docstore_dict[doc_id] = new_doc
-                                index_to_docstore_id[idx] = doc_id
-                        except:
+                            # Get content from matches
+                            if idx < len(matches):
+                                content = matches[idx].decode('utf-8', errors='ignore').strip()
+                            else:
+                                content = f"Fashion document {idx}"
+                            
+                            if len(content) < 50:
+                                content = f"Fashion advice and style guide entry {idx}"
+                            
+                            # Create document with string ID
+                            doc_id = str(idx)
+                            new_doc = Document(
+                                page_content=content,
+                                metadata={"source": "reconstructed"}
+                            )
+                            new_docstore_dict[doc_id] = new_doc
+                            # CRITICAL: Use string keys for index_to_docstore_id
+                            index_to_docstore_id[str(idx)] = doc_id
+                        except Exception as e:
+                            logger.warning(f"   Error creating doc {idx}: {e}")
                             continue
                     
                     logger.info(f"   ✅ Reconstructed {len(new_docstore_dict)} documents from raw data")