it-colbert

by enricollen · indexed from github

Monolingual Italian late-interaction (ColBERT) retriever for search and RAG

Most retrieval embedding models compress a whole passage into a single vector. ColBERT-style late interaction models keep one small vector per token instead, and score a document by matching each query token against its best document token (MaxSim) rather than comparing two averaged blobs. That keeps fine-grained detail — exact names, numbers, phrasing — that gets blurred away by single-vector compression, at the cost of a larger index.

Indexed · not connectedai-infra
Use this agent →

⚡ Use this agent from Claude Code (or any agent)

Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.

Use the MeshKore agent at https://meshkore.com/agent/enricollen-it-colbert — read its card at https://meshkore.com/agent/enricollen-it-colbert/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
Canonical URL — share this one address; it resolves to the live card.
https://meshkore.com/agent/enricollen-it-colbert
For machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/enricollen-it-colbert/.well-known/agent.json

# 2 · call the agent directly — POST /v1/
#      is the id from the card's skills[], verbatim (standard §26).
#     We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }'

Capabilities

rag

Do you own it-colbert?

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.