ragas-ainative
Configure ragas to use AINative's free LLMs + embeddings for RAG evaluation. No OpenAI key needed.
Zero setup. Evaluate faithfulness, answer relevancy, and more with Llama 3.3 70B — completely free.
Install
pip install ragas-ainative
Quick Start
from ragas_ainative import configure_ragas
from ragas.metrics import faithfulness, answer_relevancy
from ragas import evaluate
configure_ragas() # Auto-provisions free API key
results = evaluate(dataset, metrics=[faithfulness, answer_relevancy])
print(results)
How It Works
ragas-ainative is a companion package (NOT a fork) that configures ragas to use AINative's free, OpenAI-compatible API. It sets OPENAI_API_KEY and OPENAI_API_BASE so ragas routes all LLM judge calls and embeddings through AINative.
On first use, the package auto-provisions a free API key (72-hour TTL). Claim your account at ainative.studio/signup for permanent access.
Available Models
from ragas_ainative import configure_ragas
configure_ragas(model="llama") # meta-llama/Llama-3.3-70B-Instruct (default)
configure_ragas(model="qwen") # qwen3-coder-flash
configure_ragas(model="deepseek") # deepseek-4-flash
configure_ragas(model="kimi") # kimi-k2
Store Results to ZeroDB
Track evaluation scores over time:
from ragas_ainative import configure_ragas, store_results
configure_ragas()
# After evaluation
results = {"faithfulness": 0.85, "answer_relevancy": 0.92}
store_results(results, dataset_name="my-rag-pipeline")
# Stored to ZeroDB — searchable and trackable
Explicit API Key
configure_ragas(api_key="your-key-here")
Or set the environment variable:
export AINATIVE_API_KEY=your-key-here
API Key Resolution Order
- Explicit
api_keyparameter AINATIVE_API_KEYenvironment variableZERODB_API_KEYenvironment variable~/.zerodb/credentials.json(shared with zerodb ecosystem)- Auto-provision via instant-db
Requirements
- Python >= 3.9
- ragas >= 0.1.0
License
MIT
Metadata
Release files for ragas-ainative 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 | Actions |
|---|---|---|---|---|
| ragas_ainative-0.1.0.tar.gz | 8.9 kB | Without provenance | Details for ragas_ainative-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ragas_ainative-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for ragas_ainative-0.1.0-py3-none-any.whl |
Total release size: 17.0 kB
Release files / ragas_ainative-0.1.0.tar.gz
| Download URL | ragas_ainative-0.1.0.tar.gz |
|---|---|
| Size | 8.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
273442464f0681e61d342232fad872894fb2fd100bf03f357f9054cd3c5c967c
|
|
BLAKE2b-256 checksum How to use checksums |
90a94e99c586388cb4b369ca6692f469283cd00d411e5b4d76f811c93726d290
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.2
|
Release files / ragas_ainative-0.1.0-py3-none-any.whl
| Download URL | ragas_ainative-0.1.0-py3-none-any.whl |
|---|---|
| Size | 8.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a04fdb36e29dcc3dcacfab0d6db1e36fe45138b0a4249b57a7642089a3c50deb
|
|
BLAKE2b-256 checksum How to use checksums |
086c57b6c3178b8137543b2b82b2828b9f3d535aa682d269294a76ed61c62442
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.2
|
Security for ragas-ainative 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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A 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.