Skip to content

Document the confidence scoring algorithm #29

Description

@rajkumarsakthivel

Add documentation explaining how CCE's confidence scorer works.

Why: The README mentions "a confidence scorer blends similarity (50%), keyword match (30%), and recency (20%)" but there's no deeper explanation for users who want to understand or tune retrieval quality.

Steps:

  1. Read the scorer implementation in src/context_engine/
  2. Document the algorithm in docs/wiki/Confidence-Scoring.md
  3. Cover: inputs, weight formula, how scores map to results ordering, and how confidence_threshold config works
  4. Add a link from the existing How It Works wiki page

Keep it concise. A diagram or formula would be helpful but not required.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Labels

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions