Update src/PDFprocess_sample.py

src/PDFprocess_sample.py

@@ -1,7 +1,7 @@
 import tempfile
 import streamlit as st
 import pickle
-# from langchain_google_genai import GoogleGenerativeAIEmbeddings
+from langchain_google_genai import GoogleGenerativeAIEmbeddings
 from langchain_community.document_loaders import PyPDFLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.vectorstores import FAISS
@@ -73,22 +73,22 @@ def process_pdf(uploaded_files):
         doc = loader.load()
         main_placeholder.text("Text Splitter...Started...✅✅✅")
 
-        # text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-        # final_documents = text_splitter.split_documents(doc)
-        # all_documents.extend(final_documents)
+        text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+        final_documents = text_splitter.split_documents(doc)
+        all_documents.extend(final_documents)
 
-    # if all_documents:
-    #     main_placeholder.text("Embedding Vector Started Building...✅✅✅")
+    if all_documents:
+        main_placeholder.text("Embedding Vector Started Building...✅✅✅")
         
-    #     # ⏬ Move embedding initialization here
-    #     st.session_state.embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
-    #     st.session_state.vectors = FAISS.from_documents(all_documents, st.session_state.embeddings)
-    #     st.session_state.docs = all_documents
+        # ⏬ Move embedding initialization here
+        st.session_state.embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+        st.session_state.vectors = FAISS.from_documents(all_documents, st.session_state.embeddings)
+        st.session_state.docs = all_documents
 
-    #     faiss_index = st.session_state.vectors.index
-    #     faiss.write_index(faiss_index, "faiss_index.bin")
-    #     main_placeholder.text("Vector database created!...✅✅✅")
+        faiss_index = st.session_state.vectors.index
+        faiss.write_index(faiss_index, "faiss_index.bin")
+        main_placeholder.text("Vector database created!...✅✅✅")
 
-    # else:
-    #     st.error("No documents found or the PDF is corrupted.")
+    else:
+        st.error("No documents found or the PDF is corrupted.")