Update app.py

app.py

@@ -44,8 +44,8 @@ def invoke(openai_api_key, use_rag, prompt):
         result = rag_chain({"query": prompt})
         result = result["result"]
     else:
-        chain = LLMChain(llm = llm, prompt = CHAIN_PROMPT)
-        result = chain.run({"context": "", "question": prompt})
+        chain = LLMChain(llm = llm, prompt = prompt)
+        result = chain.run()
     #print(result)
     return result
 
@@ -57,7 +57,7 @@ description = """<strong>Overview:</strong> The app demonstrates how to use a La
                  <ul style="list-style-type:square;">
                  <li>Set "Use RAG" to "False" and submit prompt "what is gpt-4". The LLM <strong>without</strong> RAG does not know the answer.</li>
                  <li>Set "Use RAG" to "True" and submit prompt "what is gpt-4". The LLM <strong>with</strong> RAG knows the answer.</li>
-                 <li>Experiment with different prompts, for example "what is gpt-4, answer in german" or "write a haiku about gpt-4".</li>
+                 <li>Experiment with different prompts, for example "what is gpt-4, answer in german" or "write a poem about gpt-4".</li>
                  </ul>
                  In a production system, processing external data would be done in a batch process. An idea for a production system would be to perform LLM use cases on the 
                  <a href='https://www.youtube.com/playlist?list=PL2yQDdvlhXf_hIzmfHCdbcXj2hS52oP9r'>AWS re:Invent playlist</a>.\n\n