jzddlmZddlmZGddeeeefZdZeegdZ dZ ee gd Z y ) )BaseOutputParser)PromptTemplatec<eZdZUdZdZeed< dedeeeffdZ y)FinishedOutputParserz4Output parser that checks if the output is finished.FINISHEDfinished_valuetextreturncz|j}|j|v}|j|jd|fS)N)striprreplace)selfr cleanedfinisheds h/var/www/html/Fitness-lenito-AI-main/venv/lib/python3.12/site-packages/langchain/chains/flare/prompts.pyparsezFinishedOutputParser.parse s9**,&&'1t22B7AAN) __name__ __module__ __qualname____doc__rstr__annotations__tupleboolrrrrrs1>$NC$6B#B%T "2BrrzRespond to the user message using any relevant context. If context is provided, you should ground your answer in that context. Once you're done responding return FINISHED. >>> CONTEXT: {context} >>> USER INPUT: {user_input} >>> RESPONSE: {response}) user_inputcontextresponse)templateinput_variablesa&Given a user input and an existing partial response as context, ask a question to which the answer is the given term/entity/phrase: >>> USER INPUT: {user_input} >>> EXISTING PARTIAL RESPONSE: {current_response} The question to which the answer is the term/entity/phrase "{uncertain_span}" is:)rcurrent_responseuncertain_spanN) langchain_core.output_parsersrlangchain_core.promptsrrrrrPROMPT_TEMPLATEPROMPT"QUESTION_GENERATOR_PROMPT_TEMPLATEQUESTION_GENERATOR_PROMPTrrrr+s]:1 B+E#t),<= B  9  &U"+ /Hr