# This file was auto-generated by Fern from our API Definition. import typing from json.decoder import JSONDecodeError from ..core.api_error import ApiError from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper from ..core.http_response import AsyncHttpResponse, HttpResponse from ..core.pydantic_utilities import parse_obj_as from ..core.request_options import RequestOptions from ..errors.bad_gateway_error import BadGatewayError from ..errors.internal_server_error import InternalServerError from ..errors.service_unavailable_error import ServiceUnavailableError from ..errors.unprocessable_entity_error import UnprocessableEntityError from ..types.error_message import ErrorMessage from ..types.ollama_connection_test_response import OllamaConnectionTestResponse from ..types.ollama_model import OllamaModel # this is used as the default value for optional parameters OMIT = typing.cast(typing.Any, ...) class RawOllamaClient: def __init__(self, *, client_wrapper: SyncClientWrapper): self._client_wrapper = client_wrapper def list_models( self, *, base_url: str, api_key: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[typing.List[OllamaModel]]: """ Fetches the list of models available from the Ollama instance. URL may be provided with or without /v1 suffix (e.g., http://localhost:11434 or http://localhost:11434/v1). The /v1 suffix will be automatically removed for model discovery. For actual LLM inference, use the URL with /v1 suffix for OpenAI-compatible endpoints. Parameters ---------- base_url : str Base URL of the Ollama instance. May include /v1 suffix which will be automatically removed for connection testing. For inference, use the URL with /v1 suffix for OpenAI-compatible endpoints. api_key : typing.Optional[str] Optional API key for authenticated Ollama instances. If provided, will be sent as Bearer token in Authorization header. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[typing.List[OllamaModel]] Models retrieved successfully """ _response = self._client_wrapper.httpx_client.request( "v1/private/ollama/models", method="POST", json={ "base_url": base_url, "api_key": api_key, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( typing.List[OllamaModel], parse_obj_as( type_=typing.List[OllamaModel], # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) if _response.status_code == 422: raise UnprocessableEntityError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 500: raise InternalServerError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 503: raise ServiceUnavailableError( headers=dict(_response.headers), body=typing.cast( ErrorMessage, parse_obj_as( type_=ErrorMessage, # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def test_connection( self, *, base_url: str, api_key: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[OllamaConnectionTestResponse]: """ Validates that the provided Ollama URL is reachable. URL may be provided with or without /v1 suffix (e.g., http://localhost:11434 or http://localhost:11434/v1). The /v1 suffix will be automatically removed for connection testing. For inference, use the URL with /v1 suffix. Parameters ---------- base_url : str Base URL of the Ollama instance. May include /v1 suffix which will be automatically removed for connection testing. For inference, use the URL with /v1 suffix for OpenAI-compatible endpoints. api_key : typing.Optional[str] Optional API key for authenticated Ollama instances. If provided, will be sent as Bearer token in Authorization header. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[OllamaConnectionTestResponse] Connection test successful """ _response = self._client_wrapper.httpx_client.request( "v1/private/ollama/test-connection", method="POST", json={ "base_url": base_url, "api_key": api_key, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( OllamaConnectionTestResponse, parse_obj_as( type_=OllamaConnectionTestResponse, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) if _response.status_code == 422: raise UnprocessableEntityError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 502: raise BadGatewayError( headers=dict(_response.headers), body=typing.cast( OllamaConnectionTestResponse, parse_obj_as( type_=OllamaConnectionTestResponse, # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 503: raise ServiceUnavailableError( headers=dict(_response.headers), body=typing.cast( ErrorMessage, parse_obj_as( type_=ErrorMessage, # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) class AsyncRawOllamaClient: def __init__(self, *, client_wrapper: AsyncClientWrapper): self._client_wrapper = client_wrapper async def list_models( self, *, base_url: str, api_key: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[typing.List[OllamaModel]]: """ Fetches the list of models available from the Ollama instance. URL may be provided with or without /v1 suffix (e.g., http://localhost:11434 or http://localhost:11434/v1). The /v1 suffix will be automatically removed for model discovery. For actual LLM inference, use the URL with /v1 suffix for OpenAI-compatible endpoints. Parameters ---------- base_url : str Base URL of the Ollama instance. May include /v1 suffix which will be automatically removed for connection testing. For inference, use the URL with /v1 suffix for OpenAI-compatible endpoints. api_key : typing.Optional[str] Optional API key for authenticated Ollama instances. If provided, will be sent as Bearer token in Authorization header. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[typing.List[OllamaModel]] Models retrieved successfully """ _response = await self._client_wrapper.httpx_client.request( "v1/private/ollama/models", method="POST", json={ "base_url": base_url, "api_key": api_key, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( typing.List[OllamaModel], parse_obj_as( type_=typing.List[OllamaModel], # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) if _response.status_code == 422: raise UnprocessableEntityError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 500: raise InternalServerError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 503: raise ServiceUnavailableError( headers=dict(_response.headers), body=typing.cast( ErrorMessage, parse_obj_as( type_=ErrorMessage, # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def test_connection( self, *, base_url: str, api_key: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[OllamaConnectionTestResponse]: """ Validates that the provided Ollama URL is reachable. URL may be provided with or without /v1 suffix (e.g., http://localhost:11434 or http://localhost:11434/v1). The /v1 suffix will be automatically removed for connection testing. For inference, use the URL with /v1 suffix. Parameters ---------- base_url : str Base URL of the Ollama instance. May include /v1 suffix which will be automatically removed for connection testing. For inference, use the URL with /v1 suffix for OpenAI-compatible endpoints. api_key : typing.Optional[str] Optional API key for authenticated Ollama instances. If provided, will be sent as Bearer token in Authorization header. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[OllamaConnectionTestResponse] Connection test successful """ _response = await self._client_wrapper.httpx_client.request( "v1/private/ollama/test-connection", method="POST", json={ "base_url": base_url, "api_key": api_key, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( OllamaConnectionTestResponse, parse_obj_as( type_=OllamaConnectionTestResponse, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) if _response.status_code == 422: raise UnprocessableEntityError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 502: raise BadGatewayError( headers=dict(_response.headers), body=typing.cast( OllamaConnectionTestResponse, parse_obj_as( type_=OllamaConnectionTestResponse, # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 503: raise ServiceUnavailableError( headers=dict(_response.headers), body=typing.cast( ErrorMessage, parse_obj_as( type_=ErrorMessage, # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)