gXZUdZddlZddlZddlZddlZddlZddlZddlmZddl m Z ddl m Z m Z mZmZmZddlZddlmZmZddlmZddlmZdd lmZd d lmZd d lmZmZmZm Z m!Z!m"Z"m#Z#d dlm$Z$d dl%m&Z&d dl'm(Z(d dl)m*Z*e$jVe,Z-dZ.dZ/ej`dejbZ2GddeZ3GddeZ4dejjfdZ6e gejjfZ7e6a8e7e9d<e6fde7ddfdZ:dejjfdZ;d8d Zd$d d%ej~ejfe jd&d'e*d(eBd)e=d*eCd+eCd,eeeDeeeDd-ffd.ee=ee=d-ffdefd/ZEd(eBd0e eBdeBfd1ZFd9d2ed3e eBddfd4ZGd5ee!d6eBd2ede!fd7ZHy):z>Contains utilities to handle HTTP requests in Huggingface Hub.N) lru_cache) HTTPStatus)CallableOptionalTupleTypeUnion) HTTPErrorResponse) HTTPAdapter)PreparedRequest)OfflineModeIsEnabled) constants)BadRequestErrorDisabledRepoErrorEntryNotFoundErrorGatedRepoErrorHfHubHTTPErrorRepositoryNotFoundErrorRevisionNotFoundError)logging)JSONDecodeError) SliceFileObj) HTTP_METHOD_TX-Amzn-Trace-Idz x-request-ida  # staging or production endpoint ^https://[^/]+ ( # on /api/repo_type/repo_id /api/(models|datasets|spaces)/(.+) | # or /repo_id/resolve/revision/... /(.+)/resolve/(.+) ) )flagsc6eZdZdZfdZdedeffd ZxZS)UniqueRequestIdAdapterrc t||fi|t|jvrO|jj t xst tj|jt<t |jj ddjd}tjd|jtd|jd|jd|d y) N authorizationz Bearer hf_zRequest z:  z (authenticated: ))super add_headersX_AMZN_TRACE_IDheadersget X_REQUEST_IDstruuiduuid4 startswithloggerdebugmethodurl)selfrequestkwargs has_token __class__s P/var/www/openai/venv/lib/python3.12/site-packages/huggingface_hub/utils/_http.pyr'z"UniqueRequestIdAdapter.add_headersMs G.v. '// 1/6/B/B

>:J!GKK=Xijsittu v r5returnc t||g|i|S#tj$rA}|jj t }|g|jd|d|_d}~wwxYw)zSCatch any RequestException to append request id to the error message for debugging.Nz (Request ID: r%)r&sendrequestsRequestExceptionr)r*r(args)r4r5r@r6e request_idr8s r9r=zUniqueRequestIdAdapter.sendZsr 7<9$9&9 9((  ,,_=J%A166A]:,a#@A   sA*SessionrHF_HUB_OFFLINEmountrHr )sessions r9_default_backend_factoryrPmsm G i!12 j."23 N  i!7!9: j"8":; Nr:_GLOBAL_BACKEND_FACTORYbackend_factoryc|aty)a Configure the HTTP backend by providing a `backend_factory`. Any HTTP calls made by `huggingface_hub` will use a Session object instantiated by this factory. This can be useful if you are running your scripts in a specific environment requiring custom configuration (e.g. custom proxy or certifications). Use [`get_session`] to get a configured Session. Since `requests.Session` is not guaranteed to be thread-safe, `huggingface_hub` creates 1 Session instance per thread. They are all instantiated using the same `backend_factory` set in [`configure_http_backend`]. A LRU cache is used to cache the created sessions (and connections) between calls. Max size is 128 to avoid memory leaks if thousands of threads are spawned. See [this issue](https://github.com/psf/requests/issues/2766) to know more about thread-safety in `requests`. Example: ```py import requests from huggingface_hub import configure_http_backend, get_session # Create a factory function that returns a Session with configured proxies def backend_factory() -> requests.Session: session = requests.Session() session.proxies = {"http": "http://10.10.1.10:3128", "https": "https://10.10.1.11:1080"} return session # Set it as the default session factory configure_http_backend(backend_factory=backend_factory) # In practice, this is mostly done internally in `huggingface_hub` session = get_session() ``` N)rQreset_sessions)rRs r9configure_http_backendrU|s@.r:cdttjtjS)a Get a `requests.Session` object, using the session factory from the user. Use [`get_session`] to get a configured Session. Since `requests.Session` is not guaranteed to be thread-safe, `huggingface_hub` creates 1 Session instance per thread. They are all instantiated using the same `backend_factory` set in [`configure_http_backend`]. A LRU cache is used to cache the created sessions (and connections) between calls. Max size is 128 to avoid memory leaks if thousands of threads are spawned. See [this issue](https://github.com/psf/requests/issues/2766) to know more about thread-safety in `requests`. Example: ```py import requests from huggingface_hub import configure_http_backend, get_session # Create a factory function that returns a Session with configured proxies def backend_factory() -> requests.Session: session = requests.Session() session.proxies = {"http": "http://10.10.1.10:3128", "https": "https://10.10.1.11:1080"} return session # Set it as the default session factory configure_http_backend(backend_factory=backend_factory) # In practice, this is mostly done internally in `huggingface_hub` session = get_session() ```  process_id thread_id)_get_session_from_cacheosgetpid threading get_identrJr:r9 get_sessionr_s : #biikYEXEXEZ [[r:c,tjy)zReset the cache of sessions. Mostly used internally when sessions are reconfigured or an SSLError is raised. See [`configure_http_backend`] for more details. N)rZ cache_clearrJr:r9rTrTs '')r:rXrYctS)z Create a new session per thread using global factory. Using LRU cache (maxsize 128) to avoid memory leaks when using thousands of threads. Cache is cleared when `configure_http_backend` is called. )rQrWs r9rZrZs # $$r:) max_retriesbase_wait_time max_wait_timeretry_on_exceptionsretry_on_status_codesr2r3rerfrgrh.ric $t|tr|f}t|tr|f}d}|} d} d|vr6t|dtjt fr|dj } t} |dz } | |dj| | jd||d|} | j|vr| Stjd| jd|d|||kDr| j| S tjd | d |d |dt#j$| t'|| dz} #|$rS} tjd | d |d|t| tjr t!||kDr| Yd} ~ d} ~ wwxYw)a# Wrapper around requests to retry calls on an endpoint, with exponential backoff. Endpoint call is retried on exceptions (ex: connection timeout, proxy error,...) and/or on specific status codes (ex: service unavailable). If the call failed more than `max_retries`, the exception is thrown or `raise_for_status` is called on the response object. Re-implement mechanisms from the `backoff` library to avoid adding an external dependencies to `hugging_face_hub`. See https://github.com/litl/backoff. Args: method (`Literal["GET", "OPTIONS", "HEAD", "POST", "PUT", "PATCH", "DELETE"]`): HTTP method to perform. url (`str`): The URL of the resource to fetch. max_retries (`int`, *optional*, defaults to `5`): Maximum number of retries, defaults to 5 (no retries). base_wait_time (`float`, *optional*, defaults to `1`): Duration (in seconds) to wait before retrying the first time. Wait time between retries then grows exponentially, capped by `max_wait_time`. max_wait_time (`float`, *optional*, defaults to `8`): Maximum duration (in seconds) to wait before retrying. retry_on_exceptions (`Type[Exception]` or `Tuple[Type[Exception]]`, *optional*): Define which exceptions must be caught to retry the request. Can be a single type or a tuple of types. By default, retry on `requests.Timeout` and `requests.ConnectionError`. retry_on_status_codes (`int` or `Tuple[int]`, *optional*, defaults to `503`): Define on which status codes the request must be retried. By default, only HTTP 503 Service Unavailable is retried. **kwargs (`dict`, *optional*): kwargs to pass to `requests.request`. Example: ``` >>> from huggingface_hub.utils import http_backoff # Same usage as "requests.request". >>> response = http_backoff("GET", "https://www.google.com") >>> response.raise_for_status() # If you expect a Gateway Timeout from time to time >>> http_backoff("PUT", upload_url, data=data, retry_on_status_codes=504) >>> response.raise_for_status() ``` When using `requests` it is possible to stream data by passing an iterator to the `data` argument. On http backoff this is a problem as the iterator is not reset after a failed call. This issue is mitigated for file objects or any IO streams by saving the initial position of the cursor (with `data.tell()`) and resetting the cursor between each call (with `data.seek()`). For arbitrary iterators, http backoff will fail. If this is a hard constraint for you, please let us know by opening an issue on [Github](https://github.com/huggingface/huggingface_hub). rNdatar)r2r3z HTTP Error z thrown while requesting r$'z' thrown while requesting z Retrying in z s [Retry /z].rrJ) isinstancetypeintioIOBasertellr_seekr5 status_coder0warningraise_for_statusr>ConnectionErrorrTtimesleepmin)r2r3rerfrgrhrir6nb_tries sleep_timeio_obj_initial_posrOresponseerrs r9 http_backoffrsN%t,24'-!6 8HJ  Jvf~ <7PQ#F^002mG A  "-v##$67'wHf#HHH##+@@ NN[)=)=(>>WX^W__`ad`ef g+%))+  & j\8*Ak]RTUV : Q7 G *#  NNQse#=fXQseL M#x778 +% &  s8:D73>D77Fd>deekk)88(Ckk)@@(K Jr:r endpoint_namec |jy#t$r}|jjd}|jjd}|dk(r5|jddzd|j dz}t t||||dk(r5|jddzd |j dz}t t||||d k(r5|jddzd |j dz}t t||||d k(r;|jddzd |j dzdzd z}t t||||dk(sZ|jdk(r|jw|jj atj|jj 8|jddzd|j dzdz}t t||||jdk(r|d|dnd}t t||||jdk(r9d|jd|dd|j dzdz}t t ||||jdk(r[|jjjd}|d|d|jjd d}t t |||t t t#|||d}~wwxYw)!a Internal version of `response.raise_for_status()` that will refine a potential HTTPError. Raised exception will be an instance of `HfHubHTTPError`. This helper is meant to be the unique method to raise_for_status when making a call to the Hugging Face Hub. Example: ```py import requests from huggingface_hub.utils import get_session, hf_raise_for_status, HfHubHTTPError response = get_session().post(...) try: hf_raise_for_status(response) except HfHubHTTPError as e: print(str(e)) # formatted message e.request_id, e.server_message # details returned by server # Complete the error message with additional information once it's raised e.append_to_message(" `create_commit` expects the repository to exist.") raise ``` Args: response (`Response`): Response from the server. endpoint_name (`str`, *optional*): Name of the endpoint that has been called. If provided, the error message will be more complete. Raises when the request has failed: - [`~utils.RepositoryNotFoundError`] If the repository to download from cannot be found. This may be because it doesn't exist, because `repo_type` is not set correctly, or because the repo is `private` and you do not have access. - [`~utils.GatedRepoError`] If the repository exists but is gated and the user is not on the authorized list. - [`~utils.RevisionNotFoundError`] If the repository exists but the revision couldn't be find. - [`~utils.EntryNotFoundError`] If the repository exists but the entry (e.g. the requested file) couldn't be find. - [`~utils.BadRequestError`] If request failed with a HTTP 400 BadRequest error. - [`~utils.HfHubHTTPError`] If request failed for a reason not listed above. z X-Error-CodeX-Error-MessageRevisionNotFoundz Client Error. zRevision Not Found for url: . EntryNotFoundzEntry Not Found for url: GatedRepoz!Cannot access gated repo for url z$Access to this resource is disabled.z!Cannot access repository for url  RepoNotFoundiNzRepository Not Found for url: z Please make sure you specified the correct `repo_id` and `repo_type`. If you are trying to access a private or gated repo, make sure you are authenticated.iz Bad request for z endpoint:z Bad request:iz Forbidden: z Cannot access content at: z2 Make sure your token has the correct permissions.iRangez. Requested range: z. Content-Range: z Content-Range)rwr r)r*rur3_formatrrrrr5REPO_API_REGEXsearchrrrr,)rrrA error_code error_messagemessage range_headers r9hf_raise_for_statusr]s[pH?!!# F?%%)).9  ((,,->? + +!--.n=FKghphthtguuvIwwG/(C J ? *!--.n=FKdemeqeqdrrsIttG,gx@a G ; &''(7&@EfgogsgsfttuCvv .'8 )  C '  ,  $$0%%h&6&6&:&:;G''(728<<.BC44 17HE1 L  ! !S (DQD]&}oZ@cu /7H=1 D  ! !S (x++,LqI0a@AGH  .'8MF?s KJ3KK error_typecustom_messagec g}|jjd}||j| |j}|jd}|3t |t r|j |n|j||jd}| |D]}d|vs|j|d|D cgc]#} | js| j%}} t tj|}dj|} |} | r5| j|jvrd |vr | d| zz } n| d | zz } t|jjtd} | rd | d } n1t|jjt d} | rd | d } | rI| j| jvr)d| vr | j#d}| d| z| |dz} n|  z } || j|| xsd S#t$rY|jjdd}|jr-d|jvr|j|jYwxYwcc} w)Nrerrorerrorsrz Content-Typer#htmlrrz (Request ID: r%z (Amzn Trace ID: )rserver_message)r)r*appendjsonrnlistextendrtextlowerstripdictfromkeysjoinr,r+r(index)rrr server_errors from_headersrkrr content_typelinerfinal_error_messagerBrequest_id_message newline_indexs r9rrsM##''(9:L\*0}}!  %&$$U+$$U+(#  %!((y)9: /<Lmdtzz|TZZ\mML}56MYY}-N)...08L8L8NN ^ # 4.#8 8  6N#: : X%%)),;=I>)r;N)N)I__doc__rqr[rer]ryr- functoolsrhttprtypingrrrrr r>r r requests.adaptersr requests.modelsr huggingface_hub.errorsrr#rrrrrrrrrr_fixesr_lfsr_typingr get_loggerrCr0r(r+compileVERBOSErr rHrLrPBACKEND_FACTORY_TrQ__annotations__rUr_rTrprZTimeoutrxSERVICE_UNAVAILABLEr,float ExceptionrrrrrJr:r9rsuE  99()+7#"   H % $   **  [8 [ ("2"2R!1!112-E*EAY!,=!]a!H\X%%\@* %%%@P@P% %  P:D9W9W{8 {8 {8 {8  {8  {8tId9os6J0KKL{8!eCHo!56{8{8|  x}  @?(@?8C=@?TX@?FGm^,GmcGmXGmZhGmr: