Q i|0ddlZddlZddlZddlZddlmZddlmZmZm Z m Z m Z m Z m Z ddlmZddlmZmZmZddlmZerddlmZddlmZ dd lmZd Zn #e$rd ZYnwxYwGd d eZdS)N)Path) TYPE_CHECKINGAnyDictListLiteralOptionalUnion) ConfigDict)retrystop_after_attemptwait_random_exponential)retry_if_not_exception_type)EmbeddingsCache)BaseVectorizer)ImageTFc neZdZdZedZ d#dedeeeefd ed ed d df fd Z ded e e e e ffdZdeefdZdeefdZd efdZeeddedeeded e e fdZeeddedee d$de eded e e e fdZded eedeffdZed e d efd!Ze d efd"Z!xZ"S)%BedrockVectorizera The BedrockVectorizer class utilizes Amazon Bedrock's API to generate embeddings for text or image data. This vectorizer is designed to interact with Amazon Bedrock API, requiring AWS credentials for authentication. The credentials can be provided directly in the `api_config` dictionary or through environment variables: - AWS_ACCESS_KEY_ID - AWS_SECRET_ACCESS_KEY - AWS_REGION (defaults to us-east-1) The vectorizer supports synchronous operations with batch processing and preprocessing capabilities. You can optionally enable caching to improve performance when generating embeddings for repeated inputs. .. code-block:: python # Basic usage with explicit credentials vectorizer = BedrockVectorizer( model="amazon.titan-embed-text-v2:0", api_config={ "aws_access_key_id": "your_access_key", "aws_secret_access_key": "your_secret_key", "aws_region": "us-east-1" } ) # With environment variables and caching from redisvl.extensions.cache.embeddings import EmbeddingsCache cache = EmbeddingsCache(name="bedrock_embeddings_cache") vectorizer = BedrockVectorizer( model="amazon.titan-embed-text-v2:0", cache=cache ) # First call will compute and cache the embedding embedding1 = vectorizer.embed("Hello, world!") # Second call will retrieve from cache embedding2 = vectorizer.embed("Hello, world!") # Generate batch embeddings embeddings = vectorizer.embed_many(["Hello", "World"], batch_size=2) # Multimodal usage from pathlib import Path vectorizer = BedrockVectorizer( model="amazon.titan-embed-image-v1:0", api_config={ "aws_access_key_id": "your_access_key", "aws_secret_access_key": "your_secret_key", "aws_region": "us-east-1" } ) image_embedding = vectorizer.embed(Path("path/to/your/image.jpg")) # Embedding a list of mixed modalities embeddings = vectorizer.embed_many( ["Hello", "world!", Path("path/to/your/image.jpg")], batch_size=2 ) T)arbitrary_types_allowedamazon.titan-embed-text-v2:0Nfloat32model api_configdtypecacherreturnc lt||||j|fi|dS)aInitialize the AWS Bedrock Vectorizer. Args: model (str): The Bedrock model ID to use. Defaults to amazon.titan-embed-text-v2:0 api_config (Optional[Dict[str, str]]): AWS credentials and config. Can include: aws_access_key_id, aws_secret_access_key, aws_region If not provided, will use environment variables. dtype (str): the default datatype to use when embedding text as byte arrays. Used when setting `as_buffer=True` in calls to embed() and embed_many(). Defaults to 'float32'. cache (Optional[EmbeddingsCache]): Optional EmbeddingsCache instance to cache embeddings for better performance with repeated texts. Defaults to None. Raises: ValueError: If credentials are not provided in config or environment. ImportError: If boto3 is not installed. ValueError: If an invalid dtype is provided. )rrrN)super__init___setup)selfrrrrkwargs __class__s C:\Users\Dell Inspiron 16\Desktop\tws\AgrotaPowerBi\back-agrota-powerbi\mcp-client-agrota\venv\Lib\site-packages\redisvl/utils/vectorize/bedrock.pyrzBedrockVectorizer.__init__^sD4 uE??? J))&))))) image_pathc 8|jt|fi|S)zHEmbed an image (from its path on disk) using a Bedrock multimodal model.)embedr)r!r&r"s r$ embed_imagezBedrockVectorizer.embed_image|s$tz$z**55f555r%c T|j|fi|||_dS)zASet up the Bedrock client and determine the embedding dimensions.N)_initialize_client_set_model_dimsdims)r!rr"s r$r zBedrockVectorizer._setups6  55f555((** r%c  ddl}n#t$rtdwxYw|i}|dtjd}|dtjd}|dtjd d }|r|st d |j d|||d ||_dS)a Setup the Bedrock client using the provided API keys or environment variables. Args: api_config: Dictionary with AWS credentials and configuration **kwargs: Additional arguments to pass to boto3 client Raises: ImportError: If boto3 is not installed ValueError: If AWS credentials are not provided rNzQAmazon Bedrock vectorizer requires boto3. Please install with `pip install boto3`aws_access_key_idAWS_ACCESS_KEY_IDaws_secret_access_keyAWS_SECRET_ACCESS_KEY aws_region AWS_REGIONz us-east-1zuAWS credentials required. Provide via api_config or environment variables AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEYbedrock-runtime)r/r1 region_name)r5)boto3 ImportErrorgetosgetenv ValueErrorclient_client)r!rr"r7r/r1r3s r$r+z$BedrockVectorizer._initialize_clients  LLLL   :    J&NN +>!?!?  !+ #RY/F%G%G! !  ^^L")L+2V2VWW   (= >  $u|  /"7"       s!c |d}t|S#ttf$r$}t dt |d}~wt $r$}t dt |d}~wwxYw)z Determine the dimensionality of the embedding model by making a test call. Returns: int: Dimensionality of the embedding model Raises: ValueError: If embedding dimensions cannot be determined zdimension checkz*Unexpected response from the Bedrock API: Nz*Error setting embedding model dimensions: )_embedlenKeyError IndexErrorr<str Exception)r! embeddingkees r$r,z!BedrockVectorizer._set_model_dimss T $566Iy>> !*% U U US#b''SSTT T T T TR#a&&RRSS S Ts #&BA B#BB<)minmax)waitstopr contentc ddlm}||} |jjd |jt j|d|}t j|d }|dS#|$r<}dt|vrd|vrtd|td |d }~wt$r}td |d }~wwxYw) a# Generate a vector embedding for a single input using the AWS Bedrock API. Args: content: Text or PIL.Image.Image or Path to image-file to embed **kwargs: Additional parameters to pass to the AWS Bedrock API Returns: List[float]: Vector embedding as a list of floats Raises: TypeError: If content is not a string, Path, or PIL.Image.Image ValueError: If attempting to embed an image with a text model ValueError: If embedding fails rValidationErrormodelIdbodyrVrFMalformed input request inputImage)Attempted to embed image with text model.zEmbedding text failed: N) botocore.exceptionsrS_serialize_request_bodyr> invoke_modelrjsondumpsloadsreadrDr<rE)r!rPr"rSrVresponse response_bodyrHs r$r@zBedrockVectorizer._embeds$* 877777++G44 <0t|0 D)9)9=CH!Jx'7'<'<'>'>??M - - < < <(CFF22|t7K7K !LMMSTT:q::;; ; < < <:q::;; ; r]rr^r_rDr<r`raappendextendrE) r!rerfr"rS embeddingsbatchbatch_embeddingsrPrVrbrHrcs r$ _embed_manyzBedrockVectorizer._embed_manys2 877777(D)) 9788 8 =,.Jx<< 4 4$& $HHG77@@D  #<4<#<$$(J!%D!1!1$$%$$ +   4A>>s# ++227;;;r%cdS)NbedrockrZ)r!s r$typezBedrockVectorizer.typeCsyr%)rNrN)rd)#__name__ __module__ __qualname____doc__r model_configrDr rrr rfloatbytesr)r r+intr,r rr rrjrr@rqdictrr\ staticmethodrvpropertyr __classcell__)r#s@r$rrs@@D:d;;;L4/3-1 ***T#s(^,* * )* * ******<6c6d5k5>P8Q6666+$++++- Xd^- - - - ^TTTTT( U $ $ 3 3 3   " ")))44 rsi KKKKKKKKKKKKKKKKKKGGGGGGGGGG666666ONNNNNN777777 llllllllllsAA! A!