How to work around the Bedrock FM token limit?

Have you looked at using Bedrock Knowledge Bases?

https://aws.amazon.com/bedrock/knowledge-bases

If you have unstructured data sources, Amazon Bedrock Knowledge Bases automatically fetches data from sources such as Amazon Simple Storage Service (Amazon S3), and Confluence, Salesforce, SharePoint, or Web Crawler, in preview. In addition, you also receive programmatic document ingestion to enable customers to ingest streaming data or data from unsupported sources. Once the content is ingested, Amazon Bedrock Knowledge Bases converts it into blocks of text, the text into embeddings, and stores the embeddings in your vector database. You can choose from multiple supported vector stores, including Amazon Aurora, Amazon Opensearch Serverless, Amazon Neptune Analytics, MongoDB, Pinecone, and Redis Enterprise Cloud. You can also choose to connect to an Amazon Kendra hybrid search index for managed retrieval.

Using Amazon Bedrock Knowledge Bases, you can also connect to your structured data stores to generate grounded responses. This can be especially useful when you have source material like transactional details which are stored in data warehouses, and datalakes. Amazon Bedrock Knowledge Bases uses Natural Language to SQL to convert queries to SQL commands and execute the commands to retrieve the data, without needing to move them from your source.