Create app.py

app.py

@@ -0,0 +1,62 @@
+import os
+import streamlit as st
+from langchain.document_loaders import PDFLoader
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import Pinecone
+from langchain.llms import OpenAI
+from dotenv import load_dotenv
+import pinecone
+
+# Load the environment variables from the .env file
+load_dotenv()
+openai_api_key = os.getenv('OPENAI_API_KEY')
+pinecone_api_key = os.getenv('PINECONE_API_KEY')
+pinecone_environment = os.getenv('PINECONE_ENVIRONMENT')
+
+# Initialize Pinecone
+pinecone.init(api_key=pinecone_api_key, environment=pinecone_environment)
+
+# Streamlit app
+st.title("Chat with Your Document")
+st.write("Upload a PDF file to chat with its content using LangChain, Pinecone, and OpenAI.")
+
+# File upload
+uploaded_file = st.file_uploader("Choose a PDF file", type="pdf")
+
+if uploaded_file is not None:
+    # Load the PDF file
+    pdf_loader = PDFLoader(file_path=uploaded_file)
+    documents = pdf_loader.load()
+
+    # Extract text from the PDF
+    pdf_text = ""
+    for doc in documents:
+        pdf_text += doc.text
+
+    # Initialize OpenAI embeddings
+    embeddings = OpenAIEmbeddings(api_key=openai_api_key)
+
+    # Create a Pinecone vector store
+    index_name = "pdf-analysis"
+    if index_name not in pinecone.list_indexes():
+        pinecone.create_index(index_name, dimension=embeddings.dimension)
+    vector_store = Pinecone(index_name=index_name, embeddings=embeddings)
+
+    # Add the PDF text to the vector store
+    vector_store.add_texts([pdf_text])
+
+    # Initialize OpenAI LLM
+    llm = OpenAI(api_key=openai_api_key)
+
+    # Chat with the document
+    user_input = st.text_input("Ask a question about the document:")
+    if st.button("Ask"):
+        if user_input:
+            response = llm.generate(prompt=f"Analyze the following text and answer the question: {pdf_text}\n\nQuestion: {user_input}")
+            st.write(response)
+        else:
+            st.write("Please enter a question to ask.")
+
+    # Display the PDF text
+    st.write("Extracted Text from PDF:")
+    st.write(pdf_text)