+ ˆåºi+>ãó€^RIHt^RIt^RIHtHt^RIHuHt^RI H t ^RI H t ^RI H t ^RIHt^RIHt^R IHt^R IHt^R IHt^R IHtR RRR/RRlltR RRR/RRlltR RRR/RRlltR4RRlltR^2R RRR/RRlltR^2R RRR/RRlltRRRRRRRRR RR!RR"RR#RR$RR%R&R'R(R RRR/ R)R*llt]P>R4R RRR/R+R,lll4t ]P>R RRR/R-R.ll4t R4R RRR/R/R0lllt R1t!R5R2R3llt"R#)6é)Ú annotationsN)ÚAnyÚLiteral)Úprotos)Ú operations)Úget_default_model_client)Ú model_types)Ú helper_types)Ú operation)Úprotobuf_helpers)Úfield_mask_pb2)Úflatten_update_pathsÚclientÚrequest_optionscó$€V^8„dQhRRRRRR/#)éÚnameúmodel_types.AnyModelNameOptionsrú&helper_types.RequestOptionsType | NoneÚreturnz*model_types.Model | model_types.TunedModel©)Úformats"Úm/Users/igloo/.openclaw/workspace/scratch/fb_ad_env/lib/python3.14/site-packages/google/generativeai/models.pyÚ __annotate__r!s(€÷ ñ Ø )ð ð<ð  ð 0ñ  ócóÚ€\P!V4pVPR4'd\WVR7#VPR4'd\ WVR7#\ RV 24h)a?Calls the API to fetch a model by name. ``` import pprint model = genai.get_model('models/gemini-1.5-flash') pprint.pprint(model) ``` Args: name: The name of the model to fetch. Should start with `models/` client: The client to use. request_options: Options for the request. Returns: A `types.Model` úmodels/)rrú tunedModels/zWInvalid model name: Model names must start with `models/` or `tunedModels/`. Received: )r Úmake_model_nameÚ startswithÚget_base_modelÚget_tuned_modelÚ ValueError)rrrs&$$rÚ get_modelr$!se€ô, × &Ò & tÓ ,€DØ ‡y×!Ò!ܘdÀ?ÔSÐSØ ‰˜× (Ò (ܘtÀOÔTÐTäØeÐfjÐekÐ ló ð rcó$€V^8„dQhRRRRRR/#)rrz model_types.BaseModelNameOptionsrrrzmodel_types.Modelr)rs"rrrBs(€÷$'ñ$'Ø *ð$'ð<ð $'ð ñ $'rcó(€Vf/pVf \4p\P!V4pVPR4'g\ RV 24hVP !RRV/VBp\ V4PV4p\P!R/VB#)aHCalls the API to fetch a base model by name. ``` import pprint model = genai.get_base_model('models/chat-bison-001') pprint.pprint(model) ``` Args: name: The name of the model to fetch. Should start with `models/` client: The client to use. request_options: Options for the request. Returns: A `types.Model`. rzJInvalid model name: Base model names must start with `models/`. Received: rr) rr rr r#r$ÚtypeÚto_dictÚModel©rrrÚresults&$$ rr!r!Bs–€ð,ÒØˆà ‚~Ü)Ó+ˆä × &Ò & tÓ ,€DØ ?‰?˜9× %Ò %ÜØXÐY]ÐX^Ð _ó ð ð× Ò Ñ ; 4Ð ;¨?Ñ ;€FÜ &‹\× !Ñ ! &Ó )€FÜ × Ò Ñ &˜vÑ &Ð&rcó$€V^8„dQhRRRRRR/#)rrú!model_types.TunedModelNameOptionsrrrúmodel_types.TunedModelr)rs"rrris(€÷%2ñ%2Ø +ð%2ð<ð %2ð ñ %2rcóô€Vf/pVf \4p\P!V4pVPR4'g\ RV 24hVP !RRV/VBp\P !V4#)a[Calls the API to fetch a tuned model by name. ``` import pprint model = genai.get_tuned_model('tunedModels/gemini-1.5-flash') pprint.pprint(model) ``` Args: name: The name of the model to fetch. Should start with `tunedModels/` client: The client to use. request_options: Options for the request. Returns: A `types.TunedModel`. rzPInvalid model name: Tuned model names must start with `tunedModels/`. Received: rr)rr rr r#r"Údecode_tuned_modelr*s&$$ rr"r"is€ð,ÒØˆà ‚~Ü)Ó+ˆä × &Ò & tÓ ,€Dà ?‰?˜>× *Ò *ÜØ^Ð_cÐ^dÐ eó ð ð× #Ò #Ñ A¨Ð A°Ñ A€Fä × )Ò )¨&Ó 1Ð1rcó €V^8„dQhRRRR/#)rÚmodelrrúglm.ModelServiceClient | Noner)rs"rrr‘s€÷ñØ *ðØ4Qñrcóf€\V\4'd7VPR4'd\WR7pVPpV#TpV#\V\ P 4'dVPpV#\V\ P4'dVPpV#\V\P4'dVPpV#\V\P 4'd.\VRR4pV'gVPPpV#\RV R24h)z6Calls the API to fetch the base model name of a model.r)rÚ base_modelNz#Invalid model: The provided model 'z‹' is not recognized or supported. Supported types are: str, model_types.TunedModel, model_types.Model, protos.Model, and protos.TunedModel.) Ú isinstanceÚstrr r$r5r Ú TunedModelr)rrÚgetattrÚtuned_model_sourceÚ TypeError)r2rr5s&& rÚget_base_model_namer<‘s!€ô %œ×ÒØ × Ñ ˜N× +Ò +ܘeÔ3ˆEØ×)Ñ)ˆJð& Ðð#‰Jð" Ðô! Eœ;×1Ñ1× 2Ò 2Ø×%Ñ%ˆ ð Ðô Eœ;×,Ñ,× -Ò -Ø—Z‘Zˆ ð Ðô Eœ6Ÿ<™<× (Ò (Ø—Z‘Zˆ ð Ðô Eœ6×,Ñ,× -Ò -ܘU L°$Ó7ˆ ßØ×1Ñ1×<Ñ<ˆJð Ðô Ø1°%°ð9xð xó ð rÚ page_sizecó(€V^8„dQhRRRRRRRR/#) rr=ú int | Nonerr3rrrzmodel_types.ModelsIterabler)rs"rrr¯s2€÷)ñ)àð)ð *ð)ð<ð )ð  ñ )rc#óÐ"€Vf/pVf \4pVP!RRV/VBF5p\V4PV4p\P !R/VBx€K7 R#5i)avCalls the API to list all available models. ``` import pprint for model in genai.list_models(): pprint.pprint(model) ``` Args: page_size: How many `types.Models` to fetch per page (api call). client: You may pass a `glm.ModelServiceClient` instead of using the default client. request_options: Options for the request. Yields: `types.Model` objects. Nr=r)rÚ list_modelsr'r(r r)©r=rrr2s$$$ rrArA¯seé€ð.ÒØˆà ‚~Ü)Ó+ˆà×#Ò#ÑK¨iÐK¸?ÔKˆÜU“ ×#Ñ# EÓ*ˆÜ×ÒÑ( %Ñ(Ô(óLùó‚A$A&có(€V^8„dQhRRRRRRRR/#) rr=r?rr3rrrzmodel_types.TunedModelsIterabler)rs"rrrÑs2€÷!4ñ!4àð!4ð *ð!4ð<ð !4ð %ñ !4rc#óÐ"€Vf/pVf \4pVP!RRV/VBF5p\V4PV4p\P !V4x€K7 R#5i)a|Calls the API to list all tuned models. ``` import pprint for model in genai.list_tuned_models(): pprint.pprint(model) ``` Args: page_size: How many `types.Models` to fetch per page (api call). client: You may pass a `glm.ModelServiceClient` instead of using the default client. request_options: Options for the request. Yields: `types.TunedModel` objects. Nr=r)rÚlist_tuned_modelsr'r(r r0rBs$$$ rrFrFÑské€ð,ÒØˆà ‚~Ü)Ó+ˆà×)Ò)ñØðà ôˆôU“ ×#Ñ# EÓ*ˆÜ×,Ò,¨UÓ3Ô3ó ùrCÚidÚ display_nameÚ descriptionÚ temperatureÚtop_pÚtop_kÚ epoch_countÚ batch_sizeÚ learning_rateÚ input_keyÚ text_inputÚ output_keyÚoutputc óX€V^8„dQhRRRRRRRRRRR R R R R R RR RR RR RRRRRRRRRR/#)rÚ source_modelrÚ training_datazmodel_types.TuningDataOptionsrGz str | NonerHrIrJz float | NonerKrLr?rMrNrOrPr7rRrr3rrrz$operations.CreateTunedModelOperationr)rs"rrrõsÌ€÷{Oñ{OØ1ð{Oà0ð{Oð ð {Oð ð {Oð ð {Oðð{Oð ð{Oð ð{Oðð{Oðð{Oð ð{Oðð{Oðð{Oð *ð{Oð <ð!{Oð"*ñ#{Orc óV€Vf/pV f \4p \P!V4p\V4pVP R4'dRV/pM/VP R4'd RRVRV//pM\ RV R24h\P !WV R7p\P!VV V R 7p\P!VVR 7p\P!R/VBR VR VR VRVRVRV/BpV P!\VVR73/VBp\PPV4#)a‚ Calls the API to initiate a tuning process that optimizes a model for specific data, returning an operation object to track and manage the tuning progress. Since tuning a model can take significant time, this API doesn't wait for the tuning to complete. Instead, it returns a `google.api_core.operation.Operation` object that lets you check on the status of the tuning job, or wait for it to complete, and check the result. After the job completes you can either find the resulting `TunedModel` object in `Operation.result()` or `palm.list_tuned_models` or `palm.get_tuned_model(model_id)`. ``` my_id = "my-tuned-model-id" operation = palm.create_tuned_model( id = my_id, source_model="models/text-bison-001", training_data=[{'text_input': 'example input', 'output': 'example output'},...] ) tuned_model=operation.result() # Wait for tuning to finish palm.generate_text(f"tunedModels/{my_id}", prompt="...") ``` Args: source_model: The name of the model to tune. training_data: The dataset to tune the model on. This must be either: * A `protos.Dataset`, or * An `Iterable` of: *`protos.TuningExample`, * `{'text_input': text_input, 'output': output}` dicts * `(text_input, output)` tuples. * A `Mapping` of `Iterable[str]` - use `input_key` and `output_key` to choose which columns to use as the input/output * A csv file (will be read with `pd.read_csv` and handles as a `Mapping` above). This can be: * A local path as a `str` or `pathlib.Path`. * A url for a csv file. * The url of a Google Sheets file. * A JSON file - Its contents will be handled either as an `Iterable` or `Mapping` above. This can be: * A local path as a `str` or `pathlib.Path`. id: The model identifier, used to refer to the model in the API `tunedModels/{id}`. Must be unique. display_name: A human-readable name for display. description: A description of the tuned model. temperature: The default temperature for the tuned model, see `types.Model` for details. top_p: The default `top_p` for the model, see `types.Model` for details. top_k: The default `top_k` for the model, see `types.Model` for details. epoch_count: The number of tuning epochs to run. An epoch is a pass over the whole dataset. batch_size: The number of examples to use in each training batch. learning_rate: The step size multiplier for the gradient updates. client: Which client to use. request_options: Options for the request. Returns: A [`google.api_core.operation.Operation`](https://googleapis.dev/python/google-api-core/latest/operation.html) rr5rr:Ú tuned_modelz(Invalid model name: The provided model 'zM' does not match any known model patterns such as 'models/' or 'tunedModels/')rPrR)rMrNrO)rVÚhyperparametersrHrIrJrKrLÚ tuning_task)Útuned_model_idrXr)rr rr<r r#Úencode_tuning_datarÚHyperparametersÚ TuningTaskr8Úcreate_tuned_modelÚdictrÚCreateTunedModelOperationÚfrom_core_operation)rUrVrGrHrIrJrKrLrMrNrOrPrRrrÚsource_model_nameÚbase_model_namerYrZrXr s&&$$$$$$$$$$$$$ rr_r_õs}€ðRÒØˆà ‚~Ü)Ó+ˆä#×3Ò3°LÓAÐÜ)¨,Ó7€OØ×#Ñ# I×.Ò.Ø$Ð&7Ð8‰ Ø × %Ñ % n× 5Ò 5à ØÐ0ؘoð#ð ‰ ôØ6°|°nðERð Só ð ô ×2Ò2Ø°zô€Mô×,Ò,ØØØ#ô€Oô ×#Ò#Ø#Ø'ô€Kô ×#Ò#ñØ ñà!ðð ðð ð ð ð ð ð ð ò€Kð×)Ò)Ü ˜B¨KÔ8ñØr—sûðõ#ã ßç*Ð*å&Ý*Ý?Ý1Ý2Ý%Ý,Ý*Ý:ð ð ð ð?C÷  ðB$'ð ð$'ð?C÷ $'ðN%2ð ð%2ð?C÷ %2÷Pð<)àð)ð-1ð)ð?C÷ )ðD!4àð!4ð-1ð!4ð?C÷ !4ðH{Oðð {Oð $ð {Oð #ð {Oð!%ð{Oðð{Oðð{Oð#ð{Oð"ð{Oð#'ð{Oð"ð{Oðð{Oð-1ð{Oð ?C÷!{Oð|‡ñ ð-1ð  ð ?C÷  óð ð‡ð ð-1ð  ð ?Cö  óð ñ22ð-1ð 22ð ?C÷ 22ð22òj%÷<ñ