Upload app.py

app.py

@@ -52,6 +52,54 @@ if "faq" not in st.session_state:
 
 st.divider()
 
+# def upload_file():
+#     uploaded_file = st.file_uploader("Upload a file")
+#     if uploaded_file is not None:
+#         return uploaded_file.read()
+
+def create_pickle_file(filepath):
+
+    from langchain_community.document_loaders import PyMuPDFLoader
+    loader = PyMuPDFLoader(filepath)
+    pages = loader.load()
+
+    # Load a pre-trained sentence transformer model
+    model_name = "sentence-transformers/all-mpnet-base-v2"
+    model_kwargs = {'device': 'cpu'}
+    encode_kwargs = {'normalize_embeddings': False}
+
+    # Create a HuggingFaceEmbeddings object
+    from langchain_community.embeddings import HuggingFaceEmbeddings
+    embeddings = HuggingFaceEmbeddings(model_name=model_name, model_kwargs=model_kwargs, encode_kwargs=encode_kwargs)
+
+    from pathlib import Path
+
+    path = Path(filepath)
+
+    filename = path.name
+
+    print(filename)
+
+    from datetime import datetime
+
+    # Get current date and time
+    now = datetime.now()
+
+    # Format as string with milliseconds
+    formatted_datetime = now.strftime("%Y-%m-%d_%H:%M:%S.%f")[:-3]
+
+    print(formatted_datetime)
+
+    # Create FAISS index with the HuggingFace embeddings
+    faiss_index = FAISS.from_documents(pages, embeddings)
+    with open(f"./{filename}_{formatted_datetime}.pkl", "wb") as f:
+        pickle.dump(faiss_index, f)
+
+
+uploaded_file = st.file_uploader("Upload a file", type=["pdf"])
+if uploaded_file is not None:
+    create_pickle_file(uploaded_file)
+
 def highlight_pdf(file_path, text_to_highlight, page_numbers):
     # Create a temporary file to save the modified PDF
     # temp_pdf_path = "temp_highlighted_pdf.pdf"
@@ -150,8 +198,8 @@ def get_faiss_semantic_index():
     except Exception as e:
         st.error(f"Error loading embeddings: {e}")
         return None
-faiss_index = get_faiss_semantic_index()
-print(faiss_index)
+# faiss_index = get_faiss_semantic_index()
+# print(faiss_index)
 
 # def promt_engineer(text):
 PROMPT_TEMPLATE = """