Update app.py

app.py

@@ -20,7 +20,7 @@ template = """Use the following pieces of context to answer the question at the
               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: """
 
-QA_CHAIN_PROMPT = PromptTemplate(input_variables = ["context", "question"], template = template)
+CHAIN_PROMPT = PromptTemplate(input_variables = ["context", "question"], template = template)
 
 CHROMA_DIR  = "docs/chroma"
 YOUTUBE_DIR = "docs/youtube"
@@ -40,13 +40,11 @@ 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": QA_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": CHAIN_PROMPT})
         result = rag_chain({"query": prompt})
     else:
-        #qa_chain = RetrievalQA.from_chain_type(llm, retriever = None, return_source_documents = True, cchain_type_kwargs = {"prompt": QA_CHAIN_PROMPT})
-        #result = qa_chain({"query": prompt})
-        chain = LLMChain(llm = llm)
-        result = chain({"query": prompt})
+        chain = LLMChain(llm = llm, prompt = CHAIN_PROMPT)
+        result = chain.run(prompt)
     #print(result)
     return result["result"]