o htC@sddlZddlmZmZddlmZddlmZddlmZm Z m Z m Z ddl m Z mZddlmZdd lmZdd lmZmZmZerJdd lmZeeZGd d d eeZGdddeeZeGdddZdS)N) dataclassfield)datetime)Enum) TYPE_CHECKINGDictOptionalUnion)InferenceEndpointErrorInferenceEndpointTimeoutError)InferenceClient)AsyncInferenceClient) get_sessionloggingparse_datetimeHfApic@s,eZdZdZdZdZdZdZdZdZ dZ d S) InferenceEndpointStatuspending initializingupdating updateFailedrunningpausedfailed scaledToZeroN) __name__ __module__ __qualname__PENDING INITIALIZINGUPDATING UPDATE_FAILEDRUNNINGPAUSEDFAILEDSCALED_TO_ZEROr(r(x/var/www/html/construction_image-detection-poc/venv/lib/python3.10/site-packages/huggingface_hub/_inference_endpoints.pyrsrc@seZdZdZdZdZdS)InferenceEndpointTypepublic protectedprivateN)rrrPUBlIC PROTECTEDPRIVATEr(r(r(r)r* sr*c@sxeZdZUdZeddZeed<eed<eddZeed<eddZ e ed<eddZ e eed<eddd Z eed <eddd Zeed <eddd Zeed <eddd Zeed <eddd Zeed<eddd Zeed<eddZeed<edddZeeedfed<edddZded<e d@dededeeedfde dddf ddZdAddZedefddZ ede!fd d!Z"dBd#e e#d$e#ddfd%d&Z$dCd'd(Z%ddddddddddddd) d*e ed+e ed,e ed-e e#d.e e#d/e e#de ed e ed e ed e ed0e ed1e eeefddfd2d3Z&dCd4d5Z'dDd7eddfd8d9Z(dCd:d;Z)dAdd?Z+dS)EInferenceEndpointa Contains information about a deployed Inference Endpoint. Args: name (`str`): The unique name of the Inference Endpoint. namespace (`str`): The namespace where the Inference Endpoint is located. repository (`str`): The name of the model repository deployed on this Inference Endpoint. status ([`InferenceEndpointStatus`]): The current status of the Inference Endpoint. url (`str`, *optional*): The URL of the Inference Endpoint, if available. Only a deployed Inference Endpoint will have a URL. framework (`str`): The machine learning framework used for the model. revision (`str`): The specific model revision deployed on the Inference Endpoint. task (`str`): The task associated with the deployed model. created_at (`datetime.datetime`): The timestamp when the Inference Endpoint was created. updated_at (`datetime.datetime`): The timestamp of the last update of the Inference Endpoint. type ([`InferenceEndpointType`]): The type of the Inference Endpoint (public, protected, private). raw (`Dict`): The raw dictionary data returned from the API. token (`str` or `bool`, *optional*): Authentication token for the Inference Endpoint, if set when requesting the API. Will default to the locally saved token if not provided. Pass `token=False` if you don't want to send your token to the server. Example: ```python >>> from huggingface_hub import get_inference_endpoint >>> endpoint = get_inference_endpoint("my-text-to-image") >>> endpoint InferenceEndpoint(name='my-text-to-image', ...) # Get status >>> endpoint.status 'running' >>> endpoint.url 'https://my-text-to-image.region.vendor.endpoints.huggingface.cloud' # Run inference >>> endpoint.client.text_to_image(...) # Pause endpoint to save $$$ >>> endpoint.pause() # ... # Resume and wait for deployment >>> endpoint.resume() >>> endpoint.wait() >>> endpoint.client.text_to_image(...) ``` F)initname namespace repositorystatusurl)reprr2 frameworkrevisiontask created_at updated_attype)r8raw)r8compareN_tokenr_apitokenapireturncCs8|dur ddlm}|}|dur|j}|||||dS)z&Initialize object from raw dictionary.Nr r)r?r4rArB)hf_apirrC)clsr?r4rCrDrr(r(r)from_rawys  zInferenceEndpoint.from_rawcCs |dS)z$Populate fields from raw dictionary.N)_populate_from_rawselfr(r(r) __post_init__s zInferenceEndpoint.__post_init__cC"|jdur tdt|j|jdS)aReturns a client to make predictions on this Inference Endpoint. Returns: [`InferenceClient`]: an inference client pointing to the deployed endpoint. Raises: [`InferenceEndpointError`]: If the Inference Endpoint is not yet deployed. NCannot create a client for this Inference Endpoint as it is not yet deployed. Please wait for the Inference Endpoint to be deployed using `endpoint.wait()` and try again.modelrC)r7r r rArJr(r(r)client zInferenceEndpoint.clientcCrM)a3Returns a client to make predictions on this Inference Endpoint. Returns: [`AsyncInferenceClient`]: an asyncio-compatible inference client pointing to the deployed endpoint. Raises: [`InferenceEndpointError`]: If the Inference Endpoint is not yet deployed. NrNrO)r7r rrArJr(r(r) async_clientrRzInferenceEndpoint.async_clienttimeout refresh_everycCs|dur |dkr td|dkrtdt} |jtjkr(td|jd|jtjkr7td|jd|jtjkr]|j dur]t j |j |j j |jd d }|jd kr]td |S|durmt||krmtd td|jd|dt||q)a+Wait for the Inference Endpoint to be deployed. Information from the server will be fetched every 1s. If the Inference Endpoint is not deployed after `timeout` seconds, a [`InferenceEndpointTimeoutError`] will be raised. The [`InferenceEndpoint`] will be mutated in place with the latest data. Args: timeout (`int`, *optional*): The maximum time to wait for the Inference Endpoint to be deployed, in seconds. If `None`, will wait indefinitely. refresh_every (`int`, *optional*): The time to wait between each fetch of the Inference Endpoint status, in seconds. Defaults to 5s. Returns: [`InferenceEndpoint`]: the same Inference Endpoint, mutated in place with the latest data. Raises: [`InferenceEndpointError`] If the Inference Endpoint ended up in a failed state. [`InferenceEndpointTimeoutError`] If the Inference Endpoint is not deployed after `timeout` seconds. Nrz`timeout` cannot be negative.z!`refresh_every` must be positive.TzInference Endpoint z> failed to deploy. Please check the logs for more information.z> failed to update. Please check the logs for more information.)rC)headersz'Inference Endpoint is ready to be used.zN) r?r3r5r6r[r7r9r:r;rr<r=r>rJr(r(r)rIs z$InferenceEndpoint._populate_from_raw)NN)rEN)NrT)rEr1)T),rrr__doc__rr3str__annotations__r5r6rr7rr9r:r;r<rr=r>r*r?rrAr boolrB classmethodrHrLpropertyr rQrrSintrdrarsruryr{r}rIr(r(r(r)r1&s <   4     P   r1) rZ dataclassesrrrenumrtypingrrrr huggingface_hub.errorsr r inference._clientr "inference._generated._async_clientrutilsrrrrFr get_loggerrr^rrr*r1r(r(r(r)s