"j?SSKJrJrJr SSKJr SSKJr SSKJ r SSK J r J r J r Jr SSKJr SSKJr SSKJr SS KJrJr SS KJr SS KJrJr S S KJr S SKJ r J!r! S SK"J#r#J$r$ S SK%J&r&J'r' S SK(J)r) S SK*J+r+ /SQr,\"S\ S5r-\\-r.\S.S\\--\/-S\\//\\ 4S\4Sjjr0\ "SS9"SS55r1g) )Callable GeneratorSequence)contextmanager) ContextVar) dataclass)AnyClassVarLiteralget_args) TypeAliasType)_utils) UserError)OpenAIChatCompatibleProvider!OpenAIResponsesCompatibleProvider)InstrumentationSettings)Providerinfer_provider)EmbeddingModel)InstrumentedEmbeddingModelinstrument_embedding_model)EmbeddingResultEmbedInputType)EmbeddingSettingsmerge_embedding_settings)TestEmbeddingModel)WrapperEmbeddingModel) EmbedderrrrrKnownEmbeddingModelNameinfer_embedding_modelrrrrr ) z!google-cloud:gemini-embedding-001z'google-cloud:gemini-embedding-2-previewzgoogle-cloud:gemini-embedding-2zgoogle-cloud:text-embedding-005z,google-cloud:text-multilingual-embedding-002zgoogle:gemini-embedding-001z!google:gemini-embedding-2-previewzgoogle:gemini-embedding-2zopenai:text-embedding-ada-002zopenai:text-embedding-3-smallzopenai:text-embedding-3-largezcohere:embed-v4.0zcohere:embed-english-v3.0zcohere:embed-english-light-v3.0zcohere:embed-multilingual-v3.0z$cohere:embed-multilingual-light-v3.0zvoyageai:voyage-4-largezvoyageai:voyage-4zvoyageai:voyage-4-litezvoyageai:voyage-3-largezvoyageai:voyage-3.5zvoyageai:voyage-3.5-litezvoyageai:voyage-code-3zvoyageai:voyage-finance-2zvoyageai:voyage-law-2zvoyageai:voyage-code-2z"bedrock:amazon.titan-embed-text-v1z$bedrock:amazon.titan-embed-text-v2:0zbedrock:cohere.embed-english-v3z$bedrock:cohere.embed-multilingual-v3zbedrock:cohere.embed-v4:0z0bedrock:amazon.nova-2-multimodal-embeddings-v1:0)provider_factorymodelr"returncN[U[5(aU$URSSS9up#U"U5nUnUR S5(aSSKJn U"U5nUS /[[R5Q[[R5Q7;a SS K J n U"X5S 9$US :Xa SS K Jn U "X5S 9$US:Xa SSKJn U "X5S 9$US;a SSKJn U "X5S 9$US:XaSSKJn U "U5$US:Xa SSKJn U "X5S 9$[/SU35e![an[S5UeSnAff=f)zInfer the model from the name.:r)maxsplitzJYou must provide a provider prefix when specifying an embedding model nameNzgateway/)normalize_gateway_provideropenai)OpenAIEmbeddingModel)providercohere)CohereEmbeddingModelbedrock)BedrockEmbeddingModel)googlez google-cloud)GoogleEmbeddingModelzsentence-transformers)!SentenceTransformerEmbeddingModelvoyageai)VoyageAIEmbeddingModelzUnknown embeddings model: ) isinstancersplit ValueError startswithproviders.gatewayr)r r __value__rr*r+r-r.r/r0r1r2sentence_transformersr3r4r5r)r#r" provider_name model_nameer, model_kindr)r+r.r0r2r3r5s \/home/mande/repo/quber/.venv/lib/python3.13/site-packages/pydantic_ai/embeddings/__init__.pyr!r!SsS %(( n$)KKaK$@!  .HJZ((B/ ;   .88 9  3== >   1#JBB x 0#JBB y 2$ZCC 1 10#JBB . .L0<< z !4%jDD4UG<==[ neflmmnsD D$ DD$F)initc \rSrSr%Sr\\-S-\S'Sr\ \\-\S'SSSS.S \ \ -\ -S \ S-S \S\\-S-S S4 S jjr\S$S\\-S S4Sjj5r\S \ \ -\ -4Sj5r\\R*S.S \ \ -\ -\R,-S \S4Sjj5rSS.S\ \\ -S \ S-S \4SjjrSS.S\ \\ -S \ S-S \4SjjrSS.S\ \\ -S\S \ S-S \4SjjrS \S-4Sjr S\ S \4Sjr!SS.S\ \\ -S \ S-S \4Sjjr"SS.S\ \\ -S \ S-S \4Sjjr#SS.S\ \\ -S\S \ S-S \4Sjjr$S \S-4S jr%S\ S \4S!jr&S \ 4S"jr'S#r(g)%ra6High-level interface for generating text embeddings. The `Embedder` class provides a convenient way to generate vector embeddings from text using various embedding model providers. It handles model inference, settings management, and optional OpenTelemetry instrumentation. Example: ```python from pydantic_ai import Embedder embedder = Embedder('openai:text-embedding-3-small') async def main(): result = await embedder.embed_query('What is machine learning?') print(result.embeddings[0][:5]) # First 5 dimensions #> [1.0, 1.0, 1.0, 1.0, 1.0] ``` N instrumentF_instrument_defaultT)settingsdefer_model_checkrEr#rGrHr$clU(aUO [U5UlX lX@l[ SSS9Ulg)aInitialize an Embedder. Args: model: The embedding model to use. Can be specified as: - A model name string in the format `'provider:model-name'` (e.g., `'openai:text-embedding-3-small'`) - An [`EmbeddingModel`][pydantic_ai.embeddings.EmbeddingModel] instance settings: Optional [`EmbeddingSettings`][pydantic_ai.embeddings.EmbeddingSettings] to use as defaults for all embed calls. defer_model_check: Whether to defer model validation until first use. Set to `False` to validate the model immediately on construction. instrument: OpenTelemetry instrumentation settings. Set to `True` to enable with defaults, or pass an [`InstrumentationSettings`][pydantic_ai.models.instrumented.InstrumentationSettings] instance to customize. If `None`, uses the value from [`Embedder.instrument_all()`][pydantic_ai.embeddings.Embedder.instrument_all]. _override_modelN)default)r!_model _settingsrErrJ)selfr#rGrHrEs rA__init__Embedder.__init__s02 1e6KE6R !$BLM^hlBmcU[lg)aSet the default instrumentation options for all embedders where `instrument` is not explicitly set. This is useful for enabling instrumentation globally without modifying each embedder individually. Args: instrument: Instrumentation settings to use as the default. Set to `True` for default settings, `False` to disable, or pass an [`InstrumentationSettings`][pydantic_ai.models.instrumented.InstrumentationSettings] instance to customize. N)rrF)rEs rAinstrument_allEmbedder.instrument_alls (2$rQcUR$)z*The embedding model used by this embedder.)rLrNs rAr#Embedder.models{{rQ)r#c# # [R"U5(a%URR[ U55nOSnSv UbURR U5 gg!UbURR U5 ff=f7f)a2Context manager to temporarily override the embedding model. Useful for testing or dynamically switching models. Args: model: The embedding model to use within this context. Example: ```python from pydantic_ai import Embedder embedder = Embedder('openai:text-embedding-3-small') async def main(): # Temporarily use a different model with embedder.override(model='openai:text-embedding-3-large'): result = await embedder.embed_query('test') print(len(result.embeddings[0])) # 3072 dimensions for large model #> 3072 ``` N)ris_setrJsetr!reset)rNr# model_tokens rAoverrideEmbedder.overrides}8 ==  ..223H3OPKK 8 &$$**;7'{&$$**;7'sABA* B*!B  BrGqueryc@# URUSUS9IShvN $N7f)aEmbed one or more query texts. Use this method when embedding search queries that will be compared against document embeddings. Some models optimize embeddings differently based on whether the input is a query or document. Args: query: A single query string or sequence of query strings to embed. settings: Optional settings to override the embedder's default settings for this call. Returns: An [`EmbeddingResult`][pydantic_ai.embeddings.EmbeddingResult] containing the embeddings and metadata about the operation. r` input_typerGNembedrNr`rGs rA embed_queryEmbedder.embed_query s" ZZ'HZMMMM  documentsc@# URUSUS9IShvN $N7f)aEmbed one or more document texts. Use this method when embedding documents that will be stored and later searched against. Some models optimize embeddings differently based on whether the input is a query or document. Args: documents: A single document string or sequence of document strings to embed. settings: Optional settings to override the embedder's default settings for this call. Returns: An [`EmbeddingResult`][pydantic_ai.embeddings.EmbeddingResult] containing the embeddings and metadata about the operation. documentrbNrdrNrjrGs rAembed_documentsEmbedder.embed_documentss" ZZ j8ZTTTTriinputsrcc# UR5n[URU5nURXUS9IShvN $N7f)ayEmbed text inputs with explicit input type specification. This is the low-level embedding method. For most use cases, prefer [`embed_query()`][pydantic_ai.embeddings.Embedder.embed_query] or [`embed_documents()`][pydantic_ai.embeddings.Embedder.embed_documents]. Args: inputs: A single string or sequence of strings to embed. input_type: The type of input, either `'query'` or `'document'`. settings: Optional settings to override the embedder's default settings for this call. Returns: An [`EmbeddingResult`][pydantic_ai.embeddings.EmbeddingResult] containing the embeddings and metadata about the operation. rbN) _get_modelrrMre)rNrprcrGr#s rAreEmbedder.embed.s<$!+DNNHE[[[RRRRs:AAAc^# UR5nUR5IShvN $N7f)zGet the maximum number of tokens the model can accept as input. Returns: The maximum token count, or `None` if the limit is unknown for this model. N)rrmax_input_tokens)rNr#s rAruEmbedder.max_input_tokensDs( !++----s $-+-textc`# UR5nURU5IShvN $N7f)aCount the number of tokens in the given text. Args: text: The text to tokenize and count. Returns: The number of tokens in the text. Raises: NotImplementedError: If the model doesn't support token counting. UserError: If the model or tokenizer is not supported. N)rr count_tokens)rNrwr#s rAryEmbedder.count_tokensMs*!''----s %.,.cH[R"URXS95$)zVSynchronous version of [`embed_query()`][pydantic_ai.embeddings.Embedder.embed_query].r_)rrun_until_completergrfs rAembed_query_syncEmbedder.embed_query_sync]s#(()9)9%)9)STTrQcH[R"URXS95$)z^Synchronous version of [`embed_documents()`][pydantic_ai.embeddings.Embedder.embed_documents].r_)rr|rnrms rAembed_documents_syncEmbedder.embed_documents_synccs#(()=)=i)=)[\\rQcJ[R"URXUS95$)zJSynchronous version of [`embed()`][pydantic_ai.embeddings.Embedder.embed].rb)rr|re)rNrprcrGs rA embed_syncEmbedder.embed_syncis#((F\d)effrQcJ[R"UR55$)z`Synchronous version of [`max_input_tokens()`][pydantic_ai.embeddings.Embedder.max_input_tokens].)rr|rurVs rAmax_input_tokens_syncEmbedder.max_input_tokens_syncos(()>)>)@AArQcL[R"URU55$)zXSynchronous version of [`count_tokens()`][pydantic_ai.embeddings.Embedder.count_tokens].)rr|ry)rNrws rAcount_tokens_syncEmbedder.count_tokens_syncss(():):4)@AArQcURR5=n(aUnO[UR5=o lUR nUc UR n[X#5$)zCreate a model configured for this embedder. Returns: The embedding model to use, with instrumentation applied if configured. )rJgetr!r#rLrErFr)rN some_modelmodel_rEs rArrEmbedder._get_modelws[--113 3: 3F#8#D DF[__  11J)&==rQ)rLrJrMrE)T))__name__ __module__ __qualname____firstlineno____doc__rbool__annotations__rFr rr strrrO staticmethodrSpropertyr#rrUNSETUnsetrr]rrrgrnrreintruryr}rrrrrr__static_attributes__rQrArrs(($.55EJ"9D"@AI .2"&<@ n 77#=n$d* n  n ,d2T9 n n> 2#:T#A 2T 2 2~(??#EPV||$8 77#= L$8 4 $8$8NSWN8C=(N7H47ON N&W[Ux},U;Lt;SU U&ptSHSM)S:HSTehlTlS S,.d ..s.s."SWU8C=(U7H47OU UW[]x},];Lt;S] ]ptgHSM)g:HgTehlTlg g BsTzBBcBcB>N>rQrN)2collections.abcrrr contextlibr contextvarsr dataclassesrtypingr r r r typing_extensionsr pydantic_airpydantic_ai.exceptionsrpydantic_ai.modelsrrpydantic_ai.models.instrumentedrpydantic_ai.providersrrbaser instrumentedrrresultrrrGrrtestrwrapperr__all__r "OpenAIEmbeddingsCompatibleProviderrr!rrrQrArs99%"!33+,^C: P3A$* (  <!$J&BDe%e" 8F8> 3 3c 98>uhsm348> 8>v x>x>x>rQ