a ag@slddlmZddlmZddlmZGdddeeeefZdZ ee gddZ d Z ee gd dZ d S) )Tuple)BaseOutputParser)PromptTemplatec@s6eZdZUdZdZeed<eeeefdddZ dS)FinishedOutputParserz4Output parser that checks if the output is finished.FINISHEDfinished_value)textreturncCs$|}|j|v}||jd|fS)N)striprreplace)selfrcleanedfinishedrl/var/www/html/cobodadashboardai.evdpl.com/venv/lib/python3.9/site-packages/langchain/chains/flare/prompts.pyparse s zFinishedOutputParser.parseN) __name__ __module__ __qualname____doc__rstr__annotations__rboolrrrrrrs  rzRespond 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)templateZinput_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:)rZcurrent_responseZuncertain_spanN) typingrZlangchain_core.output_parsersrZlangchain_core.promptsrrrrZPROMPT_TEMPLATEZPROMPTZ"QUESTION_GENERATOR_PROMPT_TEMPLATEZQUESTION_GENERATOR_PROMPTrrrrs