Create app.py

app.py

@@ -0,0 +1,93 @@
+import streamlit as st
+import os
+# import pickle
+from PyPDF2 import PdfReader
+# from langchain import FAISS
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings.openai import OpenAIEmbeddings
+
+from langchain.vectorstores import Pinecone
+import pinecone
+from langchain.llms import OpenAI
+from langchain.chains.question_answering import load_qa_chain
+from langchain.callbacks import get_openai_callback
+
+# Sidebar contents
+with st.sidebar:
+    st.title('🤗💬 LLM Chat App')
+    st.markdown('''
+    ## About
+    This app is an LLM-powered chatbot built using:
+    - [Streamlit](https://streamlit.io/)
+    - [LangChain](https://python.langchain.com/)
+    - [OpenAI](https://platform.openai.com/docs/models) LLM model
+
+    ''')
+    # add_vertical_space(5)
+    st.write('Made by Nick')
+
+
+def main():
+    st.header("Chat with PDF 💬")
+
+    # upload a PDF file
+    pdf = st.file_uploader("Upload your PDF", type='pdf')
+
+    if pdf is not None:
+        pdf_reader = PdfReader(pdf)
+
+        text = ""
+        for page in pdf_reader.pages:
+            text += page.extract_text()
+
+        text_splitter = RecursiveCharacterTextSplitter(
+            chunk_size=512,
+            chunk_overlap=128,
+            length_function=len
+        )
+        chunks = text_splitter.split_text(text=text)
+
+        # # embeddings
+        store_name = pdf.name[:-4]
+        st.write(f'{store_name}')
+
+        # if os.path.exists(f"{store_name}.pkl"):
+        #     with open(f"{store_name}.pkl", "rb") as f:
+        #         VectorStore = pickle.load(f)
+        #     st.write('Embeddings Loaded from the Disk')
+        # else:
+        #     st.write('Embeddings calculate to the Pinecone')
+        #     embeddings = OpenAIEmbeddings()
+        #     VectorStore = FAISS.from_texts(chunks, embedding=embeddings)
+        #     with open(f"{store_name}.pkl", "wb") as f:
+        #         pickle.dump(VectorStore, f)
+
+        PINECONE_API_KEY = os.environ.get('PINECONE_API_KEY', '894d5f1f-df46-4b01-8407-d9977eaee2eb')
+        PINECONE_API_ENV = os.environ.get('PINECONE_API_ENV',
+                                          'asia-southeast1-gcp-free')  # You may need to switch with your env
+        embeddings = OpenAIEmbeddings()
+        # initialize pinecone
+        pinecone.init(
+            api_key=PINECONE_API_KEY,  # find at app.pinecone.io
+            environment=PINECONE_API_ENV  # next to api key in console
+        )
+        index_name = "indexer"  # put in the name of your pinecone index here
+        VectorStore = Pinecone.from_texts([t.page_content for t in chunks], embeddings, index_name=index_name)
+
+        # Accept user questions/query
+        query = st.text_input("Ask questions about your PDF file:")
+        # st.write(query)
+
+        if query:
+            docs = VectorStore.similarity_search(query=query, k=3)
+
+            llm = OpenAI()
+            chain = load_qa_chain(llm=llm, chain_type="stuff")
+            with get_openai_callback() as cb:
+                response = chain.run(input_documents=docs, question=query)
+                print(cb)
+            st.write(response)
+
+
+if __name__ == '__main__':
+    main()