Missing output keys "language" intentional?

prompt template 1: translate to english

first_prompt = ChatPromptTemplate.from_template(
    "Translate the following review to english:"

chain 1: input= Review and output= English_Review

chain_one = LLMChain(llm=llm, prompt=first_prompt, 
second_prompt = ChatPromptTemplate.from_template(
    "Can you summarize the following review in 1 sentence:"

chain 2: input= English_Review and output= summary

chain_two = LLMChain(llm=llm, prompt=second_prompt, 

prompt template 3: translate to english

third_prompt = ChatPromptTemplate.from_template(
    "What language is the following review:\n\n{Review}")

chain 3: input= Review and output= language

chain_three = LLMChain(llm=llm, prompt=third_prompt,

prompt template 4: follow up message

fourth_prompt = ChatPromptTemplate.from_template(
    "Write a follow up response to the following "
    "summary in the specified language:"
    "\n\nSummary: {summary}\n\nLanguage: {language}")

chain 4: input= summary, language and output= followup_message

chain_four = LLMChain(llm=llm, prompt=fourth_prompt,

overall_chain: input= Review

and output= English_Review,summary, followup_message

overall_chain = SequentialChain(
    chains=[chain_one, chain_two, chain_three, chain_four],
    output_variables=["English_Review", "summary","followup_message"],

The argument “output_variables” of the SequentialChain function has only output of 3 LLMChains.The output of the third chain is “language” and it is missing from the “output_variables” argument list. Why could it be so ?
Will always be thankful for any kind of lessons.

Thanks in advance

If you’re going to copy-and-paste formatted text (like notebook code), please enclose it in the “preformatted text” tag. Otherwise it renders on the forum using Markdown (which also eats all of the indentations).

First time’s error. Sorry. The same has been corrected

Hopefully someone who is a mentor for that course will reply here.

I thought it was because you can choose what are the outputs of the chain for further parsing and use. You can try this by adding and/or omitting some of the other variables and the output will be changed accordingly. Short answer: you may not need language in the final output.