LlamaIndex Embeddings Integration: Voxell
Voxell Forge is a hosted text-embedding API with three tiers (turbo, pro, and ultra) on an OpenAI-compatible endpoint.
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.
Installation
pip install llama-index-embeddings-voxell
Setup
Create a free API key at dash.voxell.ai (new accounts include 10M free tokens), then set it in your environment:
export FORGE_API_KEY="your_api_key_here"
Usage
from llama_index.embeddings.voxell import VoxellEmbedding
emb = VoxellEmbedding(model="turbo") # reads FORGE_API_KEY from the environment
vector = emb.get_text_embedding("Voxell Forge turns text into vectors.")
print(len(vector)) # 1024
query_vector = emb.get_query_embedding("How do I turn text into vectors?")
Tiers
Pick your point on the quality and cost curve:
| Tier | Dimensions |
|---|---|
turbo |
1024 |
pro |
2560 |
ultra |
4096 |
Shorter vectors with Matryoshka
Pass dimensions to get a shorter, re-normalized vector, which means a smaller index with minimal quality loss.
emb = VoxellEmbedding(model="turbo", dimensions=256)
short_vector = emb.get_query_embedding("a compact embedding")
Async
vector = await emb.aget_text_embedding("async text")
1 maintainer
Metadata
1 maintainer
Release files for llama-index-embeddings-voxell 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| llama_index_embeddings_voxell-0.1.0.tar.gz | 5.0 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| llama_index_embeddings_voxell-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 9.8 kB
Release files / llama_index_embeddings_voxell-0.1.0.tar.gz
| Download URL | llama_index_embeddings_voxell-0.1.0.tar.gz |
|---|---|
| Size | 5.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
db7dbc36808f8f8a75a4c70fafe15b9cb39a3e3331b3646a56d127e448c7fcd7
|
|
BLAKE2b-256 checksum How to use checksums |
d25f323dfc6d502a0143eb075e104fc6d863273405ef4882f1851b86b67a5db4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jun 11, 2026.
Transparency logRelease files / llama_index_embeddings_voxell-0.1.0-py3-none-any.whl
| Download URL | llama_index_embeddings_voxell-0.1.0-py3-none-any.whl |
|---|---|
| Size | 4.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
91aaf7192edce8be7bdd7db66e09d5377dcd6943a92d4a1ef49eb54bfa589714
|
|
BLAKE2b-256 checksum How to use checksums |
0a8d6c76123eb5e074c209edec0ae0ca8554945f9ee8aac07118065c666ec23a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jun 11, 2026.
Transparency logSecurity for llama-index-embeddings-voxell 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for llama_index_embeddings_voxell-0.1.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jun 11, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
