Update flask_app.py

flask_app.py

@@ -50,10 +50,16 @@ from langchain_core.output_parsers import StrOutputParser
 
 # Function to create FAISS index
 def create_faiss_index(docs):
-    texts = text_splitter.split_documents(docs)
+    texts = text_splitter.split_documents(docs)  # Ensure `text_splitter` is defined in your script
     vector_store = FAISS.from_documents(texts, embedding_model)
     return vector_store
 
+# Function to extract files from .rar archive
+def extract_rar_files(rar_path, extract_to="extracted_files"):
+    with rarfile.RarFile(rar_path) as rf:
+        rf.extractall(extract_to)
+    return extract_to
+
 # Function to fetch and process PDF files
 def fetch_and_process_pdfs(folder_path):
     pdf_files = [
@@ -65,14 +71,15 @@ def fetch_and_process_pdfs(folder_path):
         loader = PyPDFLoader(pdf_file)
         documents = loader.load()
         all_documents.extend(documents)
-    #print(all_documents)
     return all_documents
 
-
 # Function to create RAG pipeline
-def create_rag_pipeline(folder_path):
+def create_rag_pipeline(rar_path):
+    # Extract .rar file
+    extracted_folder = extract_rar_files(rar_path)
+
     # Fetch and process PDF files
-    documents = fetch_and_process_pdfs(folder_path)
+    documents = fetch_and_process_pdfs(extracted_folder)
 
     # Create vector store
     vector_store = create_faiss_index(documents)
@@ -81,8 +88,8 @@ def create_rag_pipeline(folder_path):
     return retriever
 
 # Usage example
-folder_path = "Rules folder.rar"
-retriever = create_rag_pipeline(folder_path)
+rar_path = "Rules folder.rar"
+retriever = create_rag_pipeline(rar_path)