mossi i database in db

app/document_handling.py

@@ -10,9 +10,10 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 from dataclasses import dataclass
 import json
 from datetime import datetime
+from app.functions.database_handling import BASE_DB_PATH  # Aggiungi questo import
 
 # Initialize the text splitter
-text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=2000, chunk_overlap=100)
 
 # -------------- UTILITY FUNCTIONS --------------
 @dataclass
@@ -33,9 +34,15 @@ class DocumentMetadata:
         }
 
 def save_metadata(metadata_list, db_name):
-    db_path = f"faiss_index_{db_name}"
+    """Salva i metadati nel percorso corretto."""
+    # Usa il percorso base corretto
+    db_path = os.path.join(BASE_DB_PATH, f"faiss_index_{db_name}")
     metadata_file = os.path.join(db_path, "metadata.json")
     
+    # Crea la directory se non esiste
+    if not os.path.exists(db_path):
+        os.makedirs(db_path)
+    
     existing_metadata = []
     if os.path.exists(metadata_file):
         with open(metadata_file, 'r') as f:
@@ -63,7 +70,7 @@ def extract_text_from_docx(file_path):
 
 # -------------- CHATBOT TAB FUNCTIONS --------------
 def answer_question(question, db_name="default_db"):
-    db_path = f"faiss_index_{db_name}"
+    db_path = os.path.join(BASE_DB_PATH, f"faiss_index_{db_name}")
     if not os.path.exists(db_path):
         logging.warning(f"L'indice FAISS per il database {db_name} non esiste.")
         return "Database non trovato."
@@ -132,7 +139,7 @@ def upload_and_index(files, title, author, db_name="default_db"):
 
     if documents:
         try:
-            db_path = f"faiss_index_{db_name}"
+            db_path = os.path.join(BASE_DB_PATH, f"faiss_index_{db_name}")  # Modifica qui
             os.makedirs(db_path, exist_ok=True)
             
             embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
@@ -154,7 +161,7 @@ def upload_and_index(files, title, author, db_name="default_db"):
     return "Nessun documento processato."
 
 def list_indexed_files(db_name="default_db"):
-    db_path = f"faiss_index_{db_name}"
+    db_path = os.path.join(BASE_DB_PATH, f"faiss_index_{db_name}")  # Modifica qui
     metadata_file = os.path.join(db_path, "metadata.json")
     
     if not os.path.exists(metadata_file):
@@ -188,7 +195,7 @@ def delete_file_from_database(file_name, db_name="default_db"):
     da FAISS. Attualmente, la funzione gestisce un 'file_list.txt',
     ma devi adattarla alle tue esigenze di rimozione dei chunk.
     """
-    db_path = f"faiss_index_{db_name}"
+    db_path = os.path.join(BASE_DB_PATH, f"faiss_index_{db_name}")  # Modifica qui
     file_list_path = os.path.join(db_path, "file_list.txt")
     
     if not os.path.exists(file_list_path):
@@ -213,7 +220,7 @@ def delete_file_from_database(file_name, db_name="default_db"):
 
 # -------------- DOCUMENT VISUALIZATION TAB FUNCTIONS --------------
 def list_indexed_documents(db_name="default_db"):
-    db_path = f"faiss_index_{db_name}"
+    db_path = os.path.join(BASE_DB_PATH, f"faiss_index_{db_name}")  # Modifica qui
     metadata_file = os.path.join(db_path, "metadata.json")
     
     if not os.path.exists(db_path):
@@ -250,7 +257,7 @@ def list_indexed_documents(db_name="default_db"):
 
 # -------------- NEW FEATURES TAB FUNCTIONS --------------
 def search_documents(query, db_name="default_db"):
-    db_path = f"faiss_index_{db_name}"
+    db_path = os.path.join(BASE_DB_PATH, f"faiss_index_{db_name}")  # Modifica qui
     if not os.path.exists(db_path):
         logging.warning(f"L'indice FAISS per il database '{db_name}' non esiste.")
         return "Database non trovato."

app/functions/database_handling.py

@@ -2,10 +2,17 @@ import logging
 import os
 import shutil
 
+# Definisci il percorso base per i database
+BASE_DB_PATH = "db"
+
+# Crea la cartella db se non esiste
+if not os.path.exists(BASE_DB_PATH):
+    os.makedirs(BASE_DB_PATH)
+
 # -------------- DATABASE MANAGEMENT TAB FUNCTIONS --------------
 def create_database(db_name):
     logging.info(f"Creating database: {db_name}")
-    db_path = f"faiss_index_{db_name}"
+    db_path = os.path.join(BASE_DB_PATH, f"faiss_index_{db_name}")
 
     if os.path.exists(db_path):
         return f"Il database '{db_name}' esiste già."
@@ -19,7 +26,7 @@ def create_database(db_name):
         return f"Errore nella creazione del database: {e}"
 
 def delete_database(db_name):
-    db_path = f"faiss_index_{db_name}"
+    db_path = os.path.join(BASE_DB_PATH, f"faiss_index_{db_name}")
     if not os.path.exists(db_path):
         return f"Il database '{db_name}' non esiste."
     try:
@@ -31,8 +38,8 @@ def delete_database(db_name):
         return f"Impossibile eliminare il database '{db_name}': {e}"
 
 def modify_database(old_db_name, new_db_name):
-    old_db_path = f"faiss_index_{old_db_name}"
-    new_db_path = f"faiss_index_{new_db_name}"
+    old_db_path = os.path.join(BASE_DB_PATH, f"faiss_index_{old_db_name}")
+    new_db_path = os.path.join(BASE_DB_PATH, f"faiss_index_{new_db_name}")
     if not os.path.exists(old_db_path):
         return f"Il database '{old_db_name}' non esiste."
     if os.path.exists(new_db_path):
@@ -46,8 +53,8 @@ def modify_database(old_db_name, new_db_name):
 def list_databases():
     try:
         databases = []
-        for item in os.listdir():
-            if os.path.isdir(item) and item.startswith("faiss_index_"):
+        for item in os.listdir(BASE_DB_PATH):
+            if os.path.isdir(os.path.join(BASE_DB_PATH, item)) and item.startswith("faiss_index_"):
                 db_name = item.replace("faiss_index_", "")
                 databases.append(db_name)
         # Ensure "default_db" is in the list

app/llm_handling.py

@@ -8,9 +8,7 @@ from langchain_community.embeddings import HuggingFaceEmbeddings
 import gradio as gr
 
 from app.config import OPENAI_API_KEY
-# Se hai funzioni per gestire i database (list_databases, ensure_default_db, ecc.),
-# importale dal modulo corretto:
-# from app.document_handling import list_databases, ensure_default_db
+from app.functions.database_handling import BASE_DB_PATH  # Aggiungi questo import
 
 logging.basicConfig(level=logging.INFO)
 
@@ -33,13 +31,14 @@ def answer_question(question, db_name, chat_history=None):
     
     try:
         embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-        db_path = f"faiss_index_{db_name}"
+        db_path = os.path.join(BASE_DB_PATH, f"faiss_index_{db_name}")  # Percorso corretto
         
+        logging.info(f"Verifico esistenza database in: {db_path}")
         if not os.path.exists(db_path):
-            logging.warning(f"Database {db_name} non trovato.")
+            logging.warning(f"Database {db_name} non trovato in {db_path}")
             return [
                 {"role": "user", "content": question},
-                {"role": "assistant", "content": "Database non trovato"}
+                {"role": "assistant", "content": f"Database non trovato in {db_path}"}
             ]
         
         # Carica l'indice FAISS
@@ -92,7 +91,7 @@ def delete_database(db_name):
     Cancella il database FAISS corrispondente a 'db_name'.
     Restituisce un messaggio di stato e l'aggiornamento del dropdown in Gradio.
     """
-    db_path = f"faiss_index_{db_name}"
+    db_path = os.path.join(BASE_DB_PATH, f"faiss_index_{db_name}")  # Percorso corretto
     if not os.path.exists(db_path):
         return f"Il database {db_name} non esiste.", gr.Dropdown.update(choices=[])
     try:

{faiss_index_E-learning → db/faiss_index_Daniele2}/index.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0ec4d3c22f17861b941c079acdf82d250fdafd351e9b05ab3877110a3bbdade
-size 25352
+oid sha256:e79bcca55b5153ea71218a3d2204c01ec1eccf59162fd4547d19956a4750d04e
+size 2958

db/faiss_index_Daniele2/metadata.json

@@ -0,0 +1,9 @@
+[
+  {
+    "filename": "istruzioni obiettivi di apprendimento.pdf",
+    "title": "Obiettivi di apprendimento",
+    "author": "Daniele",
+    "upload_date": "2025-01-02 15:14:19",
+    "chunks": 2
+  }
+]

faiss_index_E-learning/metadata.json

@@ -1,16 +0,0 @@
-[
-  {
-    "filename": "istruzioni obiettivi di apprendimento.pdf",
-    "title": "Obiettivi",
-    "author": "Daniele",
-    "upload_date": "2024-12-31 19:21:10",
-    "chunks": 6
-  },
-  {
-    "filename": "mastery_Bloom.pdf",
-    "title": "Mastery Learingi",
-    "author": "Bloom",
-    "upload_date": "2024-12-31 20:25:00",
-    "chunks": 43
-  }
-]