Spaces:
Runtime error
Runtime error
Update flask_app.py
Browse files- flask_app.py +15 -20
flask_app.py
CHANGED
|
@@ -55,32 +55,19 @@ def create_faiss_index(docs):
|
|
| 55 |
vector_store = FAISS.from_documents(texts, embedding_model)
|
| 56 |
return vector_store
|
| 57 |
|
| 58 |
-
# Function to extract files from .rar archive
|
| 59 |
-
def extract_rar_files(rar_path, extract_to="extracted_files"):
|
| 60 |
-
with rarfile.RarFile(rar_path) as rf:
|
| 61 |
-
rf.extractall(extract_to)
|
| 62 |
-
return extract_to
|
| 63 |
-
|
| 64 |
# Function to fetch and process PDF files
|
| 65 |
-
def fetch_and_process_pdfs(
|
| 66 |
-
pdf_files = [
|
| 67 |
-
os.path.join(folder_path, file) for file in os.listdir(folder_path) if file.endswith(".pdf")
|
| 68 |
-
]
|
| 69 |
-
|
| 70 |
all_documents = []
|
| 71 |
-
for pdf_file in
|
| 72 |
loader = PyPDFLoader(pdf_file)
|
| 73 |
documents = loader.load()
|
| 74 |
all_documents.extend(documents)
|
| 75 |
return all_documents
|
| 76 |
|
| 77 |
-
# Function to create RAG pipeline
|
| 78 |
-
def create_rag_pipeline(
|
| 79 |
-
# Extract .rar file
|
| 80 |
-
extracted_folder = extract_rar_files(rar_path)
|
| 81 |
-
|
| 82 |
# Fetch and process PDF files
|
| 83 |
-
documents = fetch_and_process_pdfs(
|
| 84 |
|
| 85 |
# Create vector store
|
| 86 |
vector_store = create_faiss_index(documents)
|
|
@@ -88,9 +75,17 @@ def create_rag_pipeline(rar_path):
|
|
| 88 |
|
| 89 |
return retriever
|
| 90 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
# Usage example
|
| 92 |
-
|
| 93 |
-
|
| 94 |
|
| 95 |
|
| 96 |
|
|
|
|
| 55 |
vector_store = FAISS.from_documents(texts, embedding_model)
|
| 56 |
return vector_store
|
| 57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
# Function to fetch and process PDF files
|
| 59 |
+
def fetch_and_process_pdfs(pdf_paths):
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
all_documents = []
|
| 61 |
+
for pdf_file in pdf_paths:
|
| 62 |
loader = PyPDFLoader(pdf_file)
|
| 63 |
documents = loader.load()
|
| 64 |
all_documents.extend(documents)
|
| 65 |
return all_documents
|
| 66 |
|
| 67 |
+
# Function to create RAG pipeline with provided PDF paths
|
| 68 |
+
def create_rag_pipeline(pdf_paths):
|
|
|
|
|
|
|
|
|
|
| 69 |
# Fetch and process PDF files
|
| 70 |
+
documents = fetch_and_process_pdfs(pdf_paths)
|
| 71 |
|
| 72 |
# Create vector store
|
| 73 |
vector_store = create_faiss_index(documents)
|
|
|
|
| 75 |
|
| 76 |
return retriever
|
| 77 |
|
| 78 |
+
# Specify the PDF paths
|
| 79 |
+
pdfs_paths = [
|
| 80 |
+
"Esta_Code_2024_.pdf",
|
| 81 |
+
"KP_Policy_Agriculture1.pdf",
|
| 82 |
+
"THE_KHYBER_PAKHTUNKHWA_SALES_TAX_ON_SERVICES_ACT_2022.pdf",
|
| 83 |
+
"The-Khyber-Pakhtunkhwa-Police-Amendment-Act-2024.pdf"
|
| 84 |
+
]
|
| 85 |
+
|
| 86 |
# Usage example
|
| 87 |
+
retriever = create_rag_pipeline(pdfs_paths)
|
| 88 |
+
|
| 89 |
|
| 90 |
|
| 91 |
|