+ i6Ha0t$^RIHt^RIt^RIHt^RIt^RIHtHtH t H t H t ^RI H t ^RIHuHt^RIHt^RIHtHt^RIHt^R IHt^R IHt^R IHt^R IHt^R IHtRt]P@PBt!] ]"]#]!3,t$/]!PJ]!PJb^]!PJbR]!PJbR]!PJb]!PL]!PLb^]!PLbR]!PLbR]!PLb]!PN]!PNb^]!PNbR]!PNbR]!PNb]!PP]!PPb^]!PPbR]!PPbR]!PPbt)R]*R&RRlt+] ]PX]-]#]P\3,]P\3,3t/] ]P`]]/,] ]#]P\3,3,t1RRlt2] ]#]Pf]Pf]Ph]Ph3,t5!RR] 4t6] ]5]6]Pn3,t8RR lt9R!R"lt:R#]R$RR%RR&RR'RR(R/R)R*llt;R#]R$RR%RR&RR'RR(RR+RR,R/R-R.llt ? % ?>??"?r&c \P!V4p\P!V4pV'd\P !V4pVeVe\ RV RV R24hVe \V4pM)Ve\W1R,4pM\RV RV R24hV'd \V4p\P!VVVVVVVR7#)a constructs a protos.GenerateAnswerRequest object by organizing the input parameters for the API call to generate a grounded answer from the model. Args: model: Name of the model used to generate the grounded response. contents: Content of the current conversation with the model. For single-turn query, this is a single question to answer. For multi-turn queries, this is a repeated field that contains conversation history and the last `Content` in the list containing the question. inline_passages: Grounding passages (a list of `Content`-like objects or `(id, content)` pairs, or a `protos.GroundingPassages`) to send inline with the request. Exclusive with `semantic_retriever`, one must be set, but not both. semantic_retriever: A Corpus, Document, or `protos.SemanticRetrieverConfig` to use for grounding. Exclusive with `inline_passages`, one must be set, but not both. answer_style: Style for grounded answers. safety_settings: Safety settings for generated output. temperature: The temperature for randomness in the output. Returns: Call for protos.GenerateAnswerRequest(). zInvalid configuration: Please set either 'inline_passages' or 'semantic_retriever_config', but not both. Received for inline_passages: z, and for semantic_retriever: .zInvalid configuration: Either 'inline_passages' or 'semantic_retriever_config' must be provided, but currently both are 'None'. Received for inline_passages: rZrbr[r\r^r_r]) r make_model_namer to_contentsrnormalize_safety_settings ValueErrorr@rYr5r,r GenerateAnswerRequest)rZrbr[r\r]r^r_s$$$$$$$r$_make_generate_answer_requestrqs<  ' ' .E((2H&@@Q"'9'E--<,==[\n[oop r    $2?C  '<=OZ\Q]^--<,==[\n[oop r  &|4  ' ''-'! r&clientrequest_optionsc<V^8dQhRRRRRRRRR R R R R RRRRR/ #rrZrarbrDr[rcr\rdr]rer^rfr_rgrrz"glm.GenerativeServiceClient | Nonersz&helper_types.RequestOptionsType | Noner")r#s"r$r%r%soEE *E)E5 E > E % E>EE /E<Er&c xVf/pVf \4p\VVVVVVVR7p VP!V 3/VBp V #)aCCalls the GenerateAnswer API and returns a `types.Answer` containing the response. You can pass a literal list of text chunks: >>> from google.generativeai import answer >>> answer.generate_answer( ... content=question, ... inline_passages=splitter.split(document) ... ) Or pass a reference to a retreiver Document or Corpus: >>> from google.generativeai import answer >>> from google.generativeai import retriever >>> my_corpus = retriever.get_corpus('my_corpus') >>> genai.generate_answer( ... content=question, ... semantic_retriever=my_corpus ... ) Args: model: Which model to call, as a string or a `types.Model`. contents: The question to be answered by the model, grounded in the provided source. inline_passages: Grounding passages (a list of `Content`-like objects or (id, content) pairs, or a `protos.GroundingPassages`) to send inline with the request. Exclusive with `semantic_retriever`, one must be set, but not both. semantic_retriever: A Corpus, Document, or `protos.SemanticRetrieverConfig` to use for grounding. Exclusive with `inline_passages`, one must be set, but not both. answer_style: Style in which the grounded answer should be returned. safety_settings: Safety settings for generated output. Defaults to None. temperature: Controls the randomness of the output. client: If you're not relying on a default client, you pass a `glm.GenerativeServiceClient` instead. request_options: Options for the request. Returns: A `types.Answer` containing the model's text answer response. rj)r rqgenerate_answer rZrbr[r\r]r^r_rrrsrequestresponses $$$$$$$$$ r$rwrwsXf ~.0+'-'!G%%gAAH Or&c<V^8dQhRRRRRRRRR R R R R RRRRR/ #rur")r#s"r$r%r%9sd22 *2)25 2 > 2 % 2>22 /2<2r&c "Vf/pVf \4p\VVVVVVVR7p VP!V 3/VBGRjxL p V #L5i)a Calls the API and returns a `types.Answer` containing the answer. Args: model: Which model to call, as a string or a `types.Model`. contents: The question to be answered by the model, grounded in the provided source. inline_passages: Grounding passages (a list of `Content`-like objects or (id, content) pairs, or a `protos.GroundingPassages`) to send inline with the request. Exclusive with `semantic_retriever`, one must be set, but not both. semantic_retriever: A Corpus, Document, or `protos.SemanticRetrieverConfig` to use for grounding. Exclusive with `inline_passages`, one must be set, but not both. answer_style: Style in which the grounded answer should be returned. safety_settings: Safety settings for generated output. Defaults to None. temperature: Controls the randomness of the output. client: If you're not relying on a default client, you pass a `glm.GenerativeServiceClient` instead. Returns: A `types.Answer` containing the model's text answer response. Nrj)r rqrwrxs $$$$$$$$$ r$generate_answer_asyncr}9sd@ ~46+'-'!G++GGGGH OHs=AAA)>__conditional_annotations__ __future__r dataclassescollections.abcr itertoolstypingrrrrtyping_extensionsr google.ai.generativelanguageaigenerativelanguageglmgoogle.generativeair google.generativeai.clientr r google.generativeai.typesr rrrr)google.generativeai.types.retriever_typesrDEFAULT_ANSWER_MODELrpr!intr*rANSWER_STYLE_UNSPECIFIED ABSTRACTIVE EXTRACTIVEVERBOSErrLr,r:r< ContentTypeGroundingPassageOptionsr4r/r@rPrQrCrBrWrUrSrYrqrwr})r~s@r$rs#"$::'**&22235D#**66 3[019((+*N*N9{++9 D D9;77 9 [44 9 { 9 7 79;**9K229{9{559+((9,,9{9K//9 {""!95( sM,E,E'E!F HaHaa !  $% C** *+- 7F  0H0H&//Y -)-"' ""$"26?-A?8< ? AE ? (, ?AE?!%?DE-AE8< E AE E (, EAEE!%E26E?CEP2-A28< 2 AE 2 (, 2AE2!%2262?C22r&