answerai-colbert-small-v1

Late-interaction (ColBERT) retrieval for Dakera · a verified mirror by Dakera, the self-hosted memory engine for AI agents

An unmodified, checksum-verified copy of the files Dakera uses from answerdotai/answerai-colbert-small-v1. The model is by Answer.AI; all credit goes to its authors.

In Dakera

Token-level (ColBERT) vectors for precise retrieval: DAKERA_MODEL=colbert-small.

Dakera fetches this late-interaction model from this repository first and from the original repositories if it is unreachable, so installs never depend on a single source. Both are checked against the same SHA-256, and the Dakera Docker image ships the default models ready to run, with no download at startup.

Files

Copied byte for byte from:

File	Source	Size
model_int8.onnx	answerdotai/answerai-colbert-small-v1	33.9 MB
tokenizer.json	answerdotai/answerai-colbert-small-v1	711.4 kB

SHA-256 checksums

de45baeaa7a48cda647fcf71582e2a0920dca303654034570aa6144d84526283  model_int8.onnx
d241a60d5e8f04cc1b2b3e9ef7a4921b27bf526d9f6050ab90f9267a1f9e5c66  tokenizer.json

Licence and credit

Apache-2.0, the same as the original model (see LICENSE). For what the model does, how it was trained and how to cite it, see the original model card.

About Dakera

Dakera is a self-hosted memory engine for AI agents. It gives agents long-term memory that survives sessions: hybrid vector and full-text retrieval, reranking, entity extraction and importance decay, in a single Rust binary that runs on your own servers, with an MCP server for Claude, Cursor and other agents.

docker run -p 3000:3000 -e DAKERA_ROOT_API_KEY=dk-mykey ghcr.io/dakera-ai/dakera:latest

🌐 Website	dakera.ai
📚 Documentation	dakera.ai/docs
💻 GitHub	github.com/Dakera-AI
🚀 Self-hosting (Docker, Kubernetes, Helm)	dakera-deploy
🔌 MCP server	dakera-mcp
🧰 SDKs	Python · TypeScript · Go · Rust
💼 LinkedIn	Dakera AI

Questions or feedback: amine@dakera.ai.