# This file was auto-generated by Fern from our API Definition.

import typing
from ....core.client_wrapper import SyncClientWrapper
from ....types.embedding_model_enum import EmbeddingModelEnum
from ....core.request_options import RequestOptions
from ....types.rag_index_response_model import RagIndexResponseModel
from ....core.jsonable_encoder import jsonable_encoder
from ....core.unchecked_base_model import construct_type
from ....errors.unprocessable_entity_error import UnprocessableEntityError
from ....types.http_validation_error import HttpValidationError
from json.decoder import JSONDecodeError
from ....core.api_error import ApiError
from ....core.client_wrapper import AsyncClientWrapper

# this is used as the default value for optional parameters
OMIT = typing.cast(typing.Any, ...)


class DocumentClient:
    def __init__(self, *, client_wrapper: SyncClientWrapper):
        self._client_wrapper = client_wrapper

    def compute_rag_index(
        self,
        documentation_id: str,
        *,
        model: EmbeddingModelEnum,
        request_options: typing.Optional[RequestOptions] = None,
    ) -> RagIndexResponseModel:
        """
        In case the document is not RAG indexed, it triggers rag indexing task, otherwise it just returns the current status.

        Parameters
        ----------
        documentation_id : str
            The id of a document from the knowledge base. This is returned on document addition.

        model : EmbeddingModelEnum

        request_options : typing.Optional[RequestOptions]
            Request-specific configuration.

        Returns
        -------
        RagIndexResponseModel
            Successful Response

        Examples
        --------
        from elevenlabs import ElevenLabs

        client = ElevenLabs(
            api_key="YOUR_API_KEY",
        )
        client.conversational_ai.knowledge_base.document.compute_rag_index(
            documentation_id="21m00Tcm4TlvDq8ikWAM",
            model="e5_mistral_7b_instruct",
        )
        """
        _response = self._client_wrapper.httpx_client.request(
            f"v1/convai/knowledge-base/{jsonable_encoder(documentation_id)}/rag-index",
            base_url=self._client_wrapper.get_environment().base,
            method="POST",
            json={
                "model": model,
            },
            headers={
                "content-type": "application/json",
            },
            request_options=request_options,
            omit=OMIT,
        )
        try:
            if 200 <= _response.status_code < 300:
                return typing.cast(
                    RagIndexResponseModel,
                    construct_type(
                        type_=RagIndexResponseModel,  # type: ignore
                        object_=_response.json(),
                    ),
                )
            if _response.status_code == 422:
                raise UnprocessableEntityError(
                    typing.cast(
                        HttpValidationError,
                        construct_type(
                            type_=HttpValidationError,  # type: ignore
                            object_=_response.json(),
                        ),
                    )
                )
            _response_json = _response.json()
        except JSONDecodeError:
            raise ApiError(status_code=_response.status_code, body=_response.text)
        raise ApiError(status_code=_response.status_code, body=_response_json)


class AsyncDocumentClient:
    def __init__(self, *, client_wrapper: AsyncClientWrapper):
        self._client_wrapper = client_wrapper

    async def compute_rag_index(
        self,
        documentation_id: str,
        *,
        model: EmbeddingModelEnum,
        request_options: typing.Optional[RequestOptions] = None,
    ) -> RagIndexResponseModel:
        """
        In case the document is not RAG indexed, it triggers rag indexing task, otherwise it just returns the current status.

        Parameters
        ----------
        documentation_id : str
            The id of a document from the knowledge base. This is returned on document addition.

        model : EmbeddingModelEnum

        request_options : typing.Optional[RequestOptions]
            Request-specific configuration.

        Returns
        -------
        RagIndexResponseModel
            Successful Response

        Examples
        --------
        import asyncio

        from elevenlabs import AsyncElevenLabs

        client = AsyncElevenLabs(
            api_key="YOUR_API_KEY",
        )


        async def main() -> None:
            await client.conversational_ai.knowledge_base.document.compute_rag_index(
                documentation_id="21m00Tcm4TlvDq8ikWAM",
                model="e5_mistral_7b_instruct",
            )


        asyncio.run(main())
        """
        _response = await self._client_wrapper.httpx_client.request(
            f"v1/convai/knowledge-base/{jsonable_encoder(documentation_id)}/rag-index",
            base_url=self._client_wrapper.get_environment().base,
            method="POST",
            json={
                "model": model,
            },
            headers={
                "content-type": "application/json",
            },
            request_options=request_options,
            omit=OMIT,
        )
        try:
            if 200 <= _response.status_code < 300:
                return typing.cast(
                    RagIndexResponseModel,
                    construct_type(
                        type_=RagIndexResponseModel,  # type: ignore
                        object_=_response.json(),
                    ),
                )
            if _response.status_code == 422:
                raise UnprocessableEntityError(
                    typing.cast(
                        HttpValidationError,
                        construct_type(
                            type_=HttpValidationError,  # type: ignore
                            object_=_response.json(),
                        ),
                    )
                )
            _response_json = _response.json()
        except JSONDecodeError:
            raise ApiError(status_code=_response.status_code, body=_response.text)
        raise ApiError(status_code=_response.status_code, body=_response_json)