Update app.py

app.py

@@ -622,7 +622,47 @@ memory.load_memory_variables({})
 
 
 
+standalone_question_template = """Given the following conversation and a follow up question, 
+rephrase the follow up question to be a standalone question, in its original language.\n\n
+Chat History:\n{chat_history}\n
+Follow Up Input: {question}\n
+Standalone question:"""
 
+standalone_question_prompt = PromptTemplate(
+    input_variables=['chat_history', 'question'], 
+    template=standalone_question_template
+)
+
+
+def answer_template(language="english"):
+    """Pass the standalone question along with the chat history and context 
+    to the `LLM` wihch will answer"""
+    
+    template = f"""Answer the question at the end, using only the following context (delimited by <context></context>).
+    Your answer must be in the language at the end. 
+    
+    <context>
+    {{chat_history}}
+    
+    {{context}} 
+    </context>
+    
+    Question: {{question}}
+    Language: {language}.
+    
+    """
+    return template
+
+answer_prompt = ChatPromptTemplate.from_template(answer_template())
+
+
+
+# invoke the ChatPromptTemplate
+answer_prompt.invoke(
+    {"question":"plaese give more details about DTC, including its use cases and implementation.",
+     "context":[Document(page_content="DTC use cases include...")], # the context is a list of retrieved documents.
+     "chat_history":memory.chat_memory}
+)
 
 
 
@@ -659,7 +699,7 @@ chain_gemini,memory_gemini = custom_ConversationalRetrievalChain(
 memory_gemini.clear()
 """
 
-
+"""
 chain = ConversationalRetrievalChain.from_llm(
     condense_question_prompt=standalone_question_prompt,
     combine_docs_chain_kwargs={'prompt': answer_prompt},
@@ -675,7 +715,7 @@ chain = ConversationalRetrievalChain.from_llm(
     verbose= False,
     return_source_documents=True   
 )
-
+"""
 
 """
 # let's invoke the chain