Create app.py

app.py

@@ -0,0 +1,63 @@
+import os
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_community.embeddings import OpenAIEmbeddings
+from langchain_community.vectorstores import Chroma
+from langchain_community.llms import OpenAI
+from langchain.chains import ConversationalRetrievalChain
+from langchain.memory import ConversationBufferMemory
+
+# Set up your API key for OpenAI
+os.environ["OPENAI_API_KEY"] = "your_openai_api_key"
+
+def load_document(file_path):
+    """Load and parse the document."""
+    loader = PyPDFLoader(file_path)
+    documents = loader.load()
+    return documents
+
+def setup_vector_store(documents):
+    """Create embeddings and store them in a vector database."""
+    embeddings = OpenAIEmbeddings()
+    vector_store = Chroma.from_documents(documents, embeddings)
+    return vector_store
+
+def setup_retrieval_chain(vector_store):
+    """Set up the conversational retrieval chain with memory."""
+    memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+    retrieval_chain = ConversationalRetrievalChain.from_llm(
+        OpenAI(model_name="gpt-4"),
+        retriever=vector_store.as_retriever(),
+        memory=memory
+    )
+    return retrieval_chain
+
+def query_document(retrieval_chain):
+    """CLI loop to interactively query the document."""
+    print("Interactive Document Query Tool")
+    print("Type 'exit' to stop the session.\n")
+    while True:
+        user_query = input("Enter your question: ")
+        if user_query.lower() == "exit":
+            print("Exiting the query tool. Goodbye!")
+            break
+        response = retrieval_chain({"question": user_query})
+        print("Answer:", response['answer'])
+        print("\n")
+
+def main():
+    # Load the document
+    file_path = input("Enter the path to your PDF document: ")
+    documents = load_document(file_path)
+    print("DOC Loaded")
+    
+    # Set up the vector store
+    vector_store = setup_vector_store(documents)
+    
+    # Set up the retrieval chain
+    retrieval_chain = setup_retrieval_chain(vector_store)
+    
+    # Start querying the document
+    query_document(retrieval_chain)
+
+if __name__ == "__main__":
+    main()