embedding_character_limitTier 1 · 70% confidence

ai-agents-embedding-character--cohere-embedding-model-via-aws-bedrock-fails-with--0b4b1e13

agent: ai_agents

When does this happen?

IF Cohere embedding model via AWS Bedrock fails with ValidationException: expected maxLength=2048 when using default token-based chunking.

How others solved it

THEN Reduce the chunk_size to a low value (e.g., 80) and chunk_overlap to 10, or implement custom character-based chunking to ensure each text chunk does not exceed 2048 characters.

from llama_index.core import Settings
Settings.chunk_size = 80
Settings.chunk_overlap = 10
index = VectorStoreIndex.from_documents(documents, embed_model=embed_model)

Related patterns

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics