Create chatpdf.py

chatpdf.py

@@ -0,0 +1,53 @@
+import streamlit as st
+from PyPDF2 import PdfReader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.chains.question_answering import load_qa_chain
+from langchain.llms import OpenAI
+from langchain.callbacks import get_openai_callback
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
+
+def main():
+    st.set_page_config(page_title="PDF Chat")
+    st.header("Chat with your PDFs 💬")
+    
+    # Upload PDF files
+    pdf_files = st.file_uploader("Upload your PDF files", type="pdf", accept_multiple_files=True)
+    
+    if pdf_files:
+        for pdf_file in pdf_files:
+            pdf_reader = PdfReader(pdf_file)
+            
+            text = ""
+            for page in pdf_reader.pages:
+                text += page.extract_text()
+            
+            text_splitter = CharacterTextSplitter(
+                separator="\n",
+                chunk_size=1000,
+                chunk_overlap=200,
+                length_function=len
+            )
+            chunks = text_splitter.split_text(text)
+            
+            embeddings = OpenAIEmbeddings()
+            knowledge_base = FAISS.from_texts(chunks, embeddings)
+            
+            user_question = st.text_input("Ask a question about your PDF:")
+            if user_question:
+                docs = knowledge_base.similarity_search(user_question)
+                
+                llm = OpenAI()
+                chain = load_qa_chain(llm, chain_type="stuff")
+                with get_openai_callback() as cb:
+                    response = chain.run(input_documents=docs, question=user_question)
+                    print(cb)
+                
+                st.write(response)
+
+if __name__ == '__main__':
+    main()