"jVSSKJrJr SSKJr SSKJrJr SSKJ r J r "SS\5r g) )ABCabstractmethod)Sequence)EmbeddingResultEmbedInputType)EmbeddingSettingsmerge_embedding_settingsc p\rSrSr%SrSr\S-\S'SS.S\S-SS4Sjjr\ S\S-4S j5r \ S\ S-4S j5r \ \ S\ 4S j55r\ \ S\ 4S j55r\ SS.S \ \\ -S\S\S-S\4Sjj5rSS \ \\ -S\S-S\\\ \44SjjrS\S-4SjrS\ S\4SjrSrg)EmbeddingModelaYAbstract base class for embedding models. Implement this class to create a custom embedding model. For most use cases, use one of the built-in implementations: - [`OpenAIEmbeddingModel`][pydantic_ai.embeddings.openai.OpenAIEmbeddingModel] - [`CohereEmbeddingModel`][pydantic_ai.embeddings.cohere.CohereEmbeddingModel] - [`GoogleEmbeddingModel`][pydantic_ai.embeddings.google.GoogleEmbeddingModel] - [`BedrockEmbeddingModel`][pydantic_ai.embeddings.bedrock.BedrockEmbeddingModel] - [`SentenceTransformerEmbeddingModel`][pydantic_ai.embeddings.sentence_transformers.SentenceTransformerEmbeddingModel] N _settings)settingsrreturncXlg)zInitialize the model with optional settings. Args: settings: Model-specific settings that will be used as defaults for this model. Nr)selfrs X/home/mande/repo/quber/.venv/lib/python3.13/site-packages/pydantic_ai/embeddings/base.py__init__EmbeddingModel.__init__s "cUR$)z(Get the default settings for this model.rrs rrEmbeddingModel.settings#s~~rcg)z0The base URL for the provider API, if available.Nrs rbase_urlEmbeddingModel.base_url(src[5e)z The name of the embedding model.NotImplementedErrorrs r model_nameEmbeddingModel.model_name- "##rc[5e)zJThe embedding model provider/system identifier (e.g., 'openai', 'cohere').r rs rsystemEmbeddingModel.system3r$rinputs input_typec# [e7f)afGenerate embeddings for the given inputs. Args: inputs: A single string or sequence of strings to embed. input_type: Whether the inputs are queries or documents. settings: Optional settings to override the model's defaults. Returns: An [`EmbeddingResult`][pydantic_ai.embeddings.EmbeddingResult] containing the embeddings and metadata. r )rr(r)rs rembedEmbeddingModel.embed9s "! c[U[5(aU/O [U5n[URU5=(d 0nX4$)apPrepare the inputs and settings for embedding. This method normalizes inputs to a list and merges settings. Subclasses should call this at the start of their `embed()` implementation. Args: inputs: A single string or sequence of strings. settings: Optional settings to merge with defaults. Returns: A tuple of (normalized inputs list, merged settings). ) isinstancestrlistr r)rr(rs r prepare_embedEmbeddingModel.prepare_embedJs;(44&$v,+DNNHEKrc # g7f)z~Get the maximum number of tokens that can be input to the model. Returns: The maximum token count, or `None` if unknown. Nrrs rmax_input_tokensEmbeddingModel.max_input_tokens_s stextc# [e7f)a Count the number of tokens in the given text. Args: text: The text to tokenize and count. Returns: The number of tokens. Raises: NotImplementedError: If the model doesn't support token counting. UserError: If the model or tokenizer is not supported. r )rr7s r count_tokensEmbeddingModel.count_tokensgs "!r-r)N)__name__ __module__ __qualname____firstlineno____doc__rr __annotations__rpropertyrr0rrr"r&rrrr+tupler1r2intr5r9__static_attributes__rrrr r sl +/I 4'. .2 "$d* "  "+d2#*$C$$$$$os"HSM)":H"TehlTl" """QU HSM) 5F5M tCy++ , *d  "s "s "rr N) abcrrcollections.abcrresultrrrr r r rrrrHs#$3Al"Sl"r