Update app.py

updated FAISS indexing and file and metadata storing to avoid keyError: '0'

app.py

@@ -30,58 +30,55 @@ embedding_dim = 768  # Adjust according to model
 index = faiss.IndexFlatL2(embedding_dim)
 documents = []  # Store raw text for reference
 
-
-# initialize the variables to store documents
+# Initialize paths
 DOCUMENT_DIR = os.path.join(os.path.dirname(__file__), "documents")
-INDEX_FILE = "faiss_index.py" # stores embeddings
-METADATA_FILE = "metadata.json" # stores Document metadata
+INDEX_FILE = "faiss_index.bin"  # FAISS index file (binary format)
+METADATA_FILE = "metadata.json"  # Document metadata
 
-# create the directory
+# Create the documents directory if it doesn’t exist
 os.makedirs(DOCUMENT_DIR, exist_ok=True)
 
-# load the faiss indexes file
-if os.path.exists(INDEX_FILE): # check if index file exists
-    stored_embeddings = np.load(INDEX_FILE) # load emeddings
-    if stored_embeddings.shape[0] > 0:
-        index.add(stored_embeddings)
+# Load FAISS index if it exists
+if os.path.exists(INDEX_FILE):
+    index = faiss.read_index(INDEX_FILE)
 
-# load the document metadata
-if os.path.exists(METADATA_FILE): # check if metadata exists
+# Load metadata
+if os.path.exists(METADATA_FILE):
     with open(METADATA_FILE, "r") as f:
         metadata = json.load(f)
 else:
     metadata = {}
 
 def store_document(text):
-    print("storing document")
+    print(" Storing document...")
 
     # Generate a unique filename
-    filename = os.path.join(DOCUMENT_DIR, f"doc_{len(metadata) + 1}.txt")
+    doc_id = len(metadata) + 1
+    filename = os.path.join(DOCUMENT_DIR, f"doc_{doc_id}.txt")
+    print(f"Saving document at: {filename}")
 
-    print(filename)
-    
-    # Save document in a file
-    with open(filename, "w") as f:
+    # Save document to file
+    with open(filename, "w", encoding="utf-8") as f:
         f.write(text)
+    print(" Document saved")
 
-    print("document saved")
-    
-   # Generate and store embedding
+    # Generate and store embedding
     embedding = embedding_model.encode([text]).astype(np.float32)
-    index.add(embedding)
+    index.add(embedding)  # Add to FAISS index
+    print(" Embeddings generated")
 
-    print("emeddings generated")
-    
-     # Update metadata
-    metadata[len(metadata)] = filename
+    # Get FAISS index for the new document
+    doc_index = index.ntotal - 1
+
+    # Update metadata with FAISS index
+    metadata[str(doc_index)] = filename
     with open(METADATA_FILE, "w") as f:
         json.dump(metadata, f)
 
-     # Save FAISS index
-    np.save(INDEX_FILE, index.reconstruct_n(0, index.ntotal))
-    
-    print(f"your document has been stored at: {filename}")
-    
+    # Save FAISS index properly
+    faiss.write_index(index, INDEX_FILE)
+
+    print(f" Document stored successfully at: {filename}")
     return "Document stored!"
 
 def retrieve_document(query):
@@ -90,6 +87,10 @@ def retrieve_document(query):
     query_embedding = embedding_model.encode([query]).astype(np.float32)
     _, closest_idx = index.search(query_embedding, 1)
 
+    if not closest_idx or closest_idx[0][0] not in metadata:
+        return "No relevant document found."
+
+    
     if closest_idx[0][0] in metadata:  # Ensure a valid match
         filename = metadata[str(closest_idx[0][0])]
         with open(filename, "r") as f: