o Zh'@sddlZddlZddlmZmZmZmZddlmZm Z ddl m Z ddl m Z ddlmZmZmZmZddlmZddlmZmZdd lmZd Zd ZGd d d ee ZdS)N)AnyDictListOptional)BatchEmbedContentsRequestEmbedContentRequest) Embeddings)secret_from_env) BaseModelField SecretStrmodel_validator)Self)GoogleGenerativeAIErrorget_client_info)build_generative_servicei Ndc@seZdZUdZdZeed<edddZe ed<eddd Z e e ed <ee d dd d dZ e eed<eddddZeed<eddd Ze eed<eddd Ze e ed<eddd Ze eed<edddefddZede dee fd d!Zed"ee d#edeee fd$d%Z   d0de d e e d&e e d'e edef d(d)Zedddd*d"ee d#ed e e d+e ee d'e edeeef d,d-Z   d0de d e e d&e e d'e edeef d.d/Z!dS)1GoogleGenerativeAIEmbeddingsa`Google Generative AI Embeddings`. To use, you must have either: 1. The ``GOOGLE_API_KEY`` environment variable set with your API key, or 2. Pass your API key using the google_api_key kwarg to the GoogleGenerativeAIEmbeddings constructor. Example: .. code-block:: python from langchain_google_genai import GoogleGenerativeAIEmbeddings embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001") embeddings.embed_query("What's our Q1 revenue?") Nclient.zEThe name of the embedding model to use. Example: models/embedding-001) descriptionmodelzThe task type. Valid options include: task_type_unspecified, retrieval_query, retrieval_document, semantic_similarity, classification, and clustering)defaultr task_typeZGOOGLE_API_KEY)rzaThe Google API key to use. If not provided, the GOOGLE_API_KEY environment variable will be used.)default_factoryrgoogle_api_keyTzThe default custom credentials (google.auth.credentials.Credentials) to use when making API calls. If not provided, credentials will be ascertained from the GOOGLE_API_KEY envvar)rexcluder credentialszXA dictionary of client options to pass to the Google API client, such as `api_endpoint`.client_optionsz3A string, one of: [`rest`, `grpc`, `grpc_asyncio`]. transportz[A dictionary of request options to pass to the Google API client.Example: `{'timeout': 10}`request_optionsafter)modereturncCs@t|jtr |j}n|j}td}t|j|||jd|_|S)z@Validates params and passes them to google-generativeai package.r)rZapi_key client_infor) isinstancerr Zget_secret_valuerrrrr)selfrr#r&X/var/www/html/lang_env/lib/python3.10/site-packages/langchain_google_genai/embeddings.pyvalidate_environmentVs  z1GoogleGenerativeAIEmbeddings.validate_environmenttextcCs,tjd}d|d}ddt||DS)z9Splits a string by punctuation and whitespace characters.z z([z])cSsg|]}|r|qSr&r&).0segmentr&r&r' mszFGoogleGenerativeAIEmbeddings._split_by_punctuation..)string punctuationresplit)r)Zsplit_bypatternr&r&r'_split_by_punctuationgs  z2GoogleGenerativeAIEmbeddings._split_by_punctuationtexts batch_sizec Csd}t|}d}g}g}|dkrgS||krq||}tt|d}d} |tkr>t|dkr4|||g}|d7}d} n$||tksJt||krMd} n||dkrUd} ||7}|||d7}| rm||g}d}||ks|S)zlSplits texts in batches based on current maximum batch size and maximum tokens per request. rFT)lenrr2_MAX_TOKENS_PER_BATCHappend) r3r4Z text_indexZ texts_lenZbatch_token_lenZbatchesZ current_batchZ current_textZcurrent_text_token_cntZ end_of_batchr&r&r'_prepare_batchesosD        'z-GoogleGenerativeAIEmbeddings._prepare_batchestitleoutput_dimensionalitycCs4|jp|pd}tdd|igi|j|||d}|S)NZRETRIEVAL_DOCUMENTpartsr))contentrrr;r<)rrrupper)r%r)rr;r<requestr&r&r'_prepare_requests z-GoogleGenerativeAIEmbeddings._prepare_request)r4rtitlesr<rBc sg}d}t||D]W}|r|||t|} |t|7}ndgt|} fddt|| D} z jt| jd} WntyU} zt d| | d} ~ ww| dd| j Dq |S)aEmbed a list of strings. Google Generative AI currently sets a max batch size of 100 strings. Args: texts: List[str] The list of strings to embed. batch_size: [int] The batch size of embeddings to send to the model task_type: task_type (https://ai.google.dev/api/rest/v1/TaskType) titles: An optional list of titles for texts provided. Only applicable when TaskType is RETRIEVAL_DOCUMENT. output_dimensionality: Optional reduced dimension for the output embedding. https://ai.google.dev/api/rest/v1/models/batchEmbedContents#EmbedContentRequest Returns: List of embeddings, one for each text. rNcs"g|] \}}j||dqS))r)rr;r<)rA)r*r)r;r<r%rr&r'r,sz@GoogleGenerativeAIEmbeddings.embed_documents..)requestsrzError embedding content: cSsg|]}t|jqSr&)listvalues)r*er&r&r'r,s) rr:r7ziprZbatch_embed_contentsrr Exceptionrextend embeddings) r%r3r4rrBr<rKZbatch_start_indexbatchZ titles_batchrDresultrGr&rCr'embed_documentss,  z,GoogleGenerativeAIEmbeddings.embed_documentscCs,|jpd}|j|g||r|gnd|ddS)aEmbed a text. Args: text: The text to embed. task_type: task_type (https://ai.google.dev/api/rest/v1/TaskType) title: An optional title for the text. Only applicable when TaskType is RETRIEVAL_DOCUMENT. output_dimensionality: Optional reduced dimension for the output embedding. https://ai.google.dev/api/rest/v1/models/batchEmbedContents#EmbedContentRequest Returns: Embedding for the text. ZRETRIEVAL_QUERYN)rrBr<r)rrN)r%r)rr;r<r&r&r' embed_querys  z(GoogleGenerativeAIEmbeddings.embed_query)NNN)"__name__ __module__ __qualname____doc__rr__annotations__r rstrrrr rr rrrrrr rr( staticmethodrr2intr:rrA_DEFAULT_BATCH_SIZEfloatrNrOr&r&r&r'rs   $7    8r)r/r-typingrrrrZ)google.ai.generativelanguage_v1beta.typesrrZlangchain_core.embeddingsrZlangchain_core.utilsr Zpydanticr r r r Ztyping_extensionsrZlangchain_google_genai._commonrrZ'langchain_google_genai._genai_extensionrr8rXrr&r&r&r's