upload app.py

app.py

@@ -0,0 +1,50 @@
+from cgitb import text
+import streamlit as st
+from dotenv import load_dotenv
+from PyPDF2 import PdfReader
+from langchain_text_splitters import CharacterTextSplitter
+from langchain.embeddings import HuggingFaceInstructEmbeddings
+from langchain.vectorstores import FAISS 
+
+
+def get_text_chunks(raw_text):
+    text_splitter = CharacterTextSplitter(
+        separator="\n",
+        chunk_size=1000, chunk_overlap=200,
+        length_function= len
+    )
+    chunks = text_splitter.split(text)
+    return chunks
+    
+def get_pdf_text(pdf_docs):
+    text =""
+    for pdf in pdf_docs:
+        pdf_reader = PdfReader(pdf)
+        for page in pdf_reader.pages:
+            text += page.extract_text()
+    return text 
+
+def get_vectorestore(text_chunks):
+    embeddings = 
+    return 
+         
+    
+def main():
+    load_dotenv()
+    st.set_page_config(page_title="Chat with your PDFs", page_icon= ":books:")
+    st.header("Chat with your PDFs :books:")
+    st.text_input("Ask a question about your documents:")
+    with st.sidebar:
+        st.subheader("Your Documemts")
+        pdf_docs = st.file_uploader("Upload your PDFs here", accept_multiple_files= True)
+        if st.button("Enter"):
+            with st.spinner("Processing"):
+            # get pdf text
+                raw_text = get_pdf_text(pdf_docs)
+            # get text chunks
+                text_chunks = get_text_chunks(raw_text)
+            # create vector store
+                vectorstore = get_vectorstore(text_chunks)
+        
+if __name__ == "__main__":
+    main()