Update app.py

app.py

@@ -28,17 +28,37 @@ from langchain.chains import ConversationalRetrievalChain
 GROQ_API_KEY = os.getenv("groq")
 # gemni_KEY = os.getenv("gemni")
 # export GOOGLE_API_KEY=gemni_KEY
-loaders = [
-    DirectoryLoader("bonusGeneralTerms_bs.pdf", loader_cls=PyPDFLoader),
-    DirectoryLoader("FAQ.pdf", loader_cls=PyPDFLoader),
+# loaders = [
+#     DirectoryLoader("bonusGeneralTerms_bs.pdf", loader_cls=PyPDFLoader),
+#     DirectoryLoader("FAQ.pdf", loader_cls=PyPDFLoader),
+# ]
+# documents = []
+# for ldr in loaders:
+#     docs = ldr.load()
+#     documents.extend(docs)
+
+# print(f"Loaded {len(documents)} file(s)")
+file_paths = [
+    "bonusGeneralTerms_bs.pdf",
+    "FAQ.pdf"
 ]
-documents = []
-for ldr in loaders:
-    docs = ldr.load()
-    documents.extend(docs)
-
-print(f"Loaded {len(documents)} file(s)")
 
+documents = []
+# 2. Loop through the list of file paths.
+for path in file_paths:
+    try:
+        # 3. Use PyPDFLoader for each individual file path.
+        loader = PyPDFLoader(path)
+        # Load the documents for the current file and add them to the list.
+        # .load() returns a list of Document objects (one per page).
+        documents.extend(loader.load())
+    except Exception as e:
+        # Optional: Add error handling in case a file is missing or corrupt.
+        print(f"Error loading file {path}: {e}")
+
+# The user's original print statement works perfectly here.
+# Note: This will print the total number of *pages*, not files.
+print(f"Loaded {len(documents)} document pages from {len(file_paths)} file(s)")
 # --------------------------------------------------------------------------------------
 # 2. Chunk documents & build FAISS index
 # --------------------------------------------------------------------------------------