All Content tagged with Knowledge Bases for Amazon Bedrock

Hi team, I’m currently working on setting up a Knowledge Base in AWS Bedrock and have enabled all Titan models in our Sandbox account. However, when trying to test the Knowledge Base, I can’t select...

We are working on ingesting websites into an OpenSearch Serverless Collection, with a requirement to provision the infrastructure at runtime and destroy it once vector generation is complete. We are...

Does anyone know if there is a way to enable the storage of page numbers from a processed PDF in the metadata of the embeddings?

Does anyone know if there is a way to enable the storage of page numbers from a processed PDF in the metadata of the embeddings?

I created a Bedrock knowledge base and specified an S3 bucket with 5 PDFs in it as the data source. When I click "Sync", in the knowledge base configuration, nothing happens. No indication of a sync...

Hello, I am trying to perform a StartIngestionJob operation on my bedrock knowledge base from a lambda function (within a Step functions State Machine) I keep getting "An error occurred...

Is is possible to ingest documents that contain both text an images, and use them as data sources for an Amazon Bedrock Knowledge base? What are the best practices for ingesting image data? I know...

Is Anthropic Claude 3 Sonnet the only model that currently supports conversational history for the on-the-fly knowledge base (i.e., Chat with your document)? I tried having a conversation on a...

Background Info: - My source files are html files. - I am using OpenSearch Serverless Vector Index - I have created a custom chunking lambda, which uses a chunking logic that leverages html...

Hi, I tried to create a KB in Bedrock out of txt files from S3 with "Chunking strategy: No" and when syncing data source I get "Error warning The server encountered an internal error while processing...

In Bedrock, why is it preferable to use an **agent** ***VS*** use a **knowledge base with a Lambda function**? I want a detailed analysis of which option is better and why.

For the same request to Claude Sonnet 3.5, making it from Bedrock takes about 17 seconds whereas it only takes 11 seconds when we call Claude API directly. We have tested this on hundreds of requests...