Skip to content

Question: Handling chunks longer than BGE-large-en-v1.5’s 512-token limit #58

Description

@lixiaoguai11

Hi, thank you for releasing GraphRAG-Benchmark.

I noticed that BAAI/bge-large-en-v1.5 supports at most 512 input tokens, while some pipelines can generate longer chunks. For example, LightRAG uses chunk_token_size=1200, but truncates text to about 400 tokens before embedding.

Does this mean that only the prefix of a long chunk is represented in the vector index?

If so, relevant information located after the truncation point may not affect retrieval similarity, even if the full chunk text is retained for later generation.

Could you clarify:

  1. Is truncating overlong chunks before embedding the intended behavior?
  2. How should information beyond the 512-token limit be handled?

I would greatly appreciate any guidance or recommended configuration for using BGE-large safely while preserving retrieval coverage.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions