Update app.py

app.py

@@ -16,11 +16,16 @@ _ = load_dotenv(find_dotenv())
 
 #openai.api_key = os.environ["OPENAI_API_KEY"]
 
-template = """Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up 
-              an answer. Keep the answer as concise as possible. Always say "🔥 Thanks for using the app - Bernd Straehle." at the end of the answer. 
-              {context} Question: {question} Helpful Answer: """
+template     = """Answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer. Keep the answer as concise as 
+                  possible. Always say "🚀 Thanks for using the app - Bernd Straehle." at the end of the answer. 
+                  Question: {question} Helpful Answer: """
 
-CHAIN_PROMPT = PromptTemplate(input_variables = ["context", "question"], template = template)
+rag_template = """Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up 
+                  an answer. Keep the answer as concise as possible. Always say "🔥 Thanks for using the app - Bernd Straehle." at the end of the answer. 
+                  {context} Question: {question} Helpful Answer: """
+
+CHAIN_PROMPT     = PromptTemplate(input_variables = ["question"], template = template)
+RAG_CHAIN_PROMPT = PromptTemplate(input_variables = ["context", "question"], template = rag_template)
 
 CHROMA_DIR  = "docs/chroma"
 YOUTUBE_DIR = "docs/youtube"
@@ -40,12 +45,12 @@ def invoke(openai_api_key, use_rag, prompt):
             text_splitter = RecursiveCharacterTextSplitter(chunk_size = 1500, chunk_overlap = 150)
             splits = text_splitter.split_documents(docs)
             vector_db = Chroma.from_documents(documents = splits, embedding = OpenAIEmbeddings(), persist_directory = CHROMA_DIR)
-        rag_chain = RetrievalQA.from_chain_type(llm, retriever = vector_db.as_retriever(search_kwargs = {"k": 3}), return_source_documents = True, chain_type_kwargs = {"prompt": CHAIN_PROMPT})
+        rag_chain = RetrievalQA.from_chain_type(llm, retriever = vector_db.as_retriever(search_kwargs = {"k": 3}), return_source_documents = True, chain_type_kwargs = {"prompt": RAG_CHAIN_PROMPT})
         result = rag_chain({"query": prompt})
         result = result["result"]
     else:
         chain = LLMChain(llm = llm, prompt = prompt)
-        result = chain.run({})
+        result = chain.run({"question": prompt})
     #print(result)
     return result