Bedrock embedding models.
To authenticate, the AWS client uses the following methods to automatically load credentials: https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html
If a specific credential profile should be used, you must pass the name of the profile from the ~/.aws/credentials file that is to be used.
Make sure the credentials / roles used have the required policies to access the Bedrock service.
Bedrock models.
To authenticate, the AWS client uses the following methods to automatically load credentials: https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html
If a specific credential profile should be used, you must pass
the name of the profile from the ~/.aws/credentials file that is to be used.
Make sure the credentials / roles used have the required policies to access the Bedrock service.
Sagemaker Inference Endpoint models.
To use, you must supply the endpoint name from your deployed Sagemaker model & the region where it is deployed.
To authenticate, the AWS client uses the following methods to automatically load credentials: https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html
If a specific credential profile should be used, you must pass
the name of the profile from the ~/.aws/credentials file that is to be used.
Make sure the credentials / roles used have the required policies to access the Sagemaker endpoint.
See: https://docs.aws.amazon.com/IAM/latest/UserGuide/access_policies.html
Amazon Bedrock Knowledge Bases retrieval.
See https://aws.amazon.com/bedrock/knowledge-bases for more info.
S3Vectors is Amazon S3 Vectors database.
To use, you MUST first manually create a S3 vector bucket. There is no need to create a vector index. See: https://docs.aws.amazon.com/AmazonS3/latest/userguide/s3-vectors-getting-started.html
Pay attention to s3 vectors limitations and restrictions. By default, metadata for s3 vectors includes page_content and metadata for the Document. See: https://docs.aws.amazon.com/AmazonS3/latest/userguide/s3-vectors-limitations.html
Examples:
The following examples show various ways to use the AmazonS3Vectors with LangChain.
For all the following examples assume we have the following:
from langchain_aws.embeddings import BedrockEmbeddings
from langchain_aws.vectorstores.s3_vectors import AmazonS3Vectors
embedding = BedrockEmbeddings()Initialize, create vector index if it does not exist, and add texts:
vector_store = AmazonS3Vectors.from_texts(
["hello", "developer", "wife"],
vector_bucket_name="<vector bucket name>",
index_name="<vector index name>",
embedding=embedding,
)Initialize, create vector index if it does not exist, and add Documents:
from langchain_core.documents import Document
vector_store = AmazonS3Vectors(
vector_bucket_name="<vector bucket name>",
index_name="<vector index name>",
embedding=embedding,
)
vector_store.add_documents(
[
Document("Star Wars", id="key1", metadata={"genre": "scifi"}),
Document("Jurassic Park", id="key2", metadata={"genre": "scifi"}),
Document("Finding Nemo", id="key3", metadata={"genre": "family"}),
]
)Search with score(distance) and metadata filter:
vector_store.similarity_search_with_score(
"adventures in space", filter={"genre": {"$eq": "family"}}
)Chain for question-answering against a Neptune graph by generating openCypher statements.
Security note: Make sure that the database connection uses credentials that are narrowly-scoped to only include necessary permissions. Failure to do so may result in data corruption or loss, since the calling code may attempt commands that would result in deletion, mutation of data if appropriately prompted or reading sensitive data if such data is present in the database. The best way to guard against such negative outcomes is to (as appropriate) limit the permissions granted to the credentials used with this tool.
See https://docs.langchain.com/oss/python/security-policy for more information.
Chain for question-answering against a Neptune graph by generating SPARQL statements.
Security note: Make sure that the database connection uses credentials that are narrowly-scoped to only include necessary permissions. Failure to do so may result in data corruption or loss, since the calling code may attempt commands that would result in deletion, mutation of data if appropriately prompted or reading sensitive data if such data is present in the database. The best way to guard against such negative outcomes is to (as appropriate) limit the permissions granted to the credentials used with this tool.
See https://docs.langchain.com/oss/python/security-policy for more information.