ugotddlZddlmZmZmZddlmZmZmZeje Z GddeeZ y)N)MappingOptionalcast) DocumentsEmbeddingFunction EmbeddingsceZdZ ddeededeedeedeedeedeed eeeefd eefd Zd ed e fdZ y)OpenAIEmbeddingFunctionNapi_key model_nameorganization_idapi_baseapi_type api_version deployment_iddefault_headers dimensionsc H ddl} |xs | j|_|j td||| _||| _||_||| _||| _ | jjd|_ |jrN|dk(r%| j||||j|_n5| j!|||j|_n| j"|_||_||_| xs | j(|_y#t$r tdwxYw) al Initialize the OpenAIEmbeddingFunction. Args: api_key (str, optional): Your API key for the OpenAI API. If not provided, it will raise an error to provide an OpenAI API key. organization_id(str, optional): The OpenAI organization ID if applicable model_name (str, optional): The name of the model to use for text embeddings. Defaults to "text-embedding-ada-002". api_base (str, optional): The base path for the API. If not provided, it will use the base path for the OpenAI API. This can be used to point to a different deployment, such as an Azure deployment. api_type (str, optional): The type of the API deployment. This can be used to specify a different deployment, such as 'azure'. If not provided, it will use the default OpenAI deployment. api_version (str, optional): The api version for the API. If not provided, it will use the api version for the OpenAI API. This can be used to point to a different deployment, such as an Azure deployment. deployment_id (str, optional): Deployment ID for Azure OpenAI. default_headers (Mapping, optional): A mapping of default headers to be sent with each API request. dimensions (int, optional): The number of dimensions for the embeddings. Only supported for `text-embedding-3` or later models from OpenAI. https://platform.openai.com/docs/api-reference/embeddings/create#embeddings-create-dimensions rNzWThe openai python package is not installed. Please install it with `pip install openai`zaPlease provide an OpenAI API key. You can get one at https://platform.openai.com/account/api-keysz1.azure)r razure_endpointr)r base_urlr)openai ImportError ValueErrorr _api_keyrr _api_typer organization __version__ startswith_v1 AzureOpenAI embeddings_clientOpenAI Embedding _model_name_deployment_id NOT_GIVEN _dimensions) selfr r r rrrrrrrs q/var/www/openai/venv/lib/python3.12/site-packages/chromadb/utils/embedding_functions/openai_embedding_function.py__init__z OpenAIEmbeddingFunction.__init__ sDH    16>> == s   &FO  "!,F !  &FO  &"1F %%006 887"%11# +#+$3 2  *   &}}#h - * "++DL%+%9)9)9U i  s D D!inputreturnc|Dcgc]}|jdd}}|jr|jj||jxs |j |j j}t|d}tt|Dcgc]}|jc}S|jdk(r9|jj||jxs |j d}n*|jj||j d}t|d }tt|Dcgc]}|d  c}Scc}wcc}wcc}w) aB Generate the embeddings for the given `input`. # About ignoring types We are not enforcing the openai library, therefore, `mypy` has hard times trying to figure out what the types are for `self._client.create()` which throws an error when trying to sort the list. If, eventually we include the `openai` lib we can remove the type ignore tag. Args: input (Documents): A list of texts to get embeddings for. Returns: Embeddings: The embeddings for the given input sorted by index   )r-modelrc|jS)N)indexes r+z2OpenAIEmbeddingFunction.__call__..ys!'')keyr)r-enginedata)r-r2c |dS)Nr4r5s r+r7z2OpenAIEmbeddingFunction.__call__..s!G*r8 embedding) replacer r#creater'r&r)r;sortedrrr>r)r*r-tr"sorted_embeddingsresults r+__call__z OpenAIEmbeddingFunction.__call__\se"055u!4%u5 88,,))=T-=-=++-d !' 1!   DU$VDU&V%5%5DU$VW W~~(!\\00(;(;(Ot?O?O1 "\\00uDDTDT0U !' 4!  ?PQ?PVVK0?PQ C6 %W$RsE E : E ) Nztext-embedding-ada-002NNNNNNN) __name__ __module__ __qualname__rstrrintr,rrrEr=r8r+r r s"&2)-"&"&%)'+7;$(P:#P:P:"# P: 3- P: 3- P:c]P: }P:"'#s("34P:SMP:d4i4J4r8r ) loggingtypingrrrchromadb.api.typesrrr getLoggerrFloggerr r=r8r+rPs:**GG   8 $G/ :Gr8