Question

A legal firm wants to use a foundation model on Amazon Bedrock to summarize entire contract documents. Some contracts are extremely long, and the team notices that when they paste a very large contract into a single prompt, the model returns an error or ignores the later portions of the document. What is the most likely cause of this behavior?

Accepted Answer

The document exceeds the model's context window, which limits the total number of tokens the model can process in a single request

Answer

The temperature parameter is set too low, preventing the model from reading the full document

Answer

The foundation model is nondeterministic, so it randomly drops portions of the input

Answer

The model requires the document to be converted into embeddings before it can accept any text input