langchain-voxell

LangChain embeddings for Forge, Voxell's hosted text-embedding API.

Voxell's Ingot-8B-R3 ranks #1 for English on the public MTEB leaderboard (English v2), with a 75.98 mean task score across 41 tasks. It is the top usable English embedding model. See the model card, or try Forge with no signup on the playground.

Why Forge

One API, three tiers. Pick your point on the quality and cost curve:

Matryoshka (MRL) dimensions are real: truncated vectors are re-normalized, so a shorter dim is a unit-norm prefix of the full vector, which means a smaller index with minimal quality loss. Forge logs request metadata only (model, tokens, latency), never your text or vectors.

Install

pip install langchain-voxell

Usage

from langchain_voxell import ForgeEmbeddings

# FORGE_API_KEY is read from the environment; or pass api_key=...
emb = ForgeEmbeddings(model="turbo")

doc_vectors = emb.embed_documents(["the quick brown fox", "lazy dog"])
query_vector = emb.embed_query("fast animal")

embed_query and embed_documents set the Forge input_type (query / document) for you.

Async

vectors = await emb.aembed_documents(["alpha", "beta"])
q = await emb.aembed_query("a search query")

Matryoshka (shorter vectors)

emb = ForgeEmbeddings(model="turbo", dimensions=256)  # re-normalized 256-d vectors

With a vector store

from langchain_community.vectorstores import FAISS
from langchain_voxell import ForgeEmbeddings

store = FAISS.from_texts(["doc one", "doc two"], ForgeEmbeddings(model="pro"))
hits = store.similarity_search("query", k=2)

Configuration

License

MIT © Voxell, Inc.