Text embeddings from Forge, Voxell's OpenAI-compatible embedding API. Three models (turbo 1024d, pro 2560d, ultra 4096d), with separate query and document embeddings for retrieval.
Author: voxell
Version: 0.0.1
Type: model provider (text embedding)
Source: https://github.com/VoxellInc/dify-plugin-forge
Adds Forge, Voxell's OpenAI-compatible embedding API, as a text-embedding
model provider in Dify. Use it for knowledge base indexing and retrieval.
is free and rate-limited; and are billed per token. Current prices:
https://voxell.ai/pricing
Forge embeds retrieval queries and indexed documents differently (). This plugin passes
Dify's input type through: knowledge base chunks are embedded as , and the question at
retrieval time is embedded as . The generic OpenAI-API-compatible provider sends neither, so
queries are embedded as documents.
See PRIVACY.md.
MIT
Some outbound calls build their address at runtime, so the list may be incomplete.
Last checked 09/28/2026 01:42 AM · version 0.0.1