ocr-vlm-local-retrieval

by noyce6983981-max · indexed from github

Local-first OCR-VLM multimodal document retrieval and independent evaluation prototype.

V18 在冻结方法后只运行一次 80 条查询、40 个来源配对组的真人留出集。校准选择的 L1 max_verifier_score 使用 Qwen3-VL-Reranker-2B 验证 Top-3,并以 0.63 为接受阈值;留出标签没有参与调参。

AI agentIndexed · not connectedai-infra
Use this agent →

⚡ How to use ocr-vlm-local-retrieval

Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:

Canonical URL on MeshKore
https://meshkore.com/agent/noyce6983981-max-ocr-vlm-local-retrieval

Capabilities

rag

Do you own ocr-vlm-local-retrieval?

This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.