aether-ai

Python SDK for the Aether decentralized RAG API.

Installation

pip install aether-ai

Quick Start

from aether import AetherClient

client = AetherClient(api_key="aether_your_key_here")

# Insert a file — content type is auto-detected from the extension
doc = client.insert("report.pdf")
print(f"Inserted: {doc.doc_id}")

# Insert raw text
doc = client.insert_text("Some text content to index")

# Search
results = client.search("machine learning", k=5)
for r in results:
    print(f"  {r.doc_id} (distance: {r.distance:.3f})")

# List documents
for doc in client.list():
    print(f"  {doc.doc_id}: {doc.title}")

Supported File Formats

Aether automatically extracts clean text from binary documents before embedding. No need to specify content_type -- it's guessed from the file extension.

Format	Extensions
PDF	.pdf
Word	.docx, .doc
PowerPoint	.pptx, .ppt
Excel	.xlsx, .xls
HTML	.html, .htm
CSV	.csv
Plain text	.txt, .md, .json, .xml

Binary-format parsing is handled automatically server-side — no setup required.

RAG Quick Start

Use retrieve() to search and get document content in a single call -- ready to pass into any LLM:

from aether import AetherClient

client = AetherClient(api_key="your_key")

# Insert documents (PDF, DOCX, XLSX — all auto-detected)
client.insert("company-handbook.pdf")
client.insert("benefits-guide.docx")
client.insert_text("Remote work is allowed 3 days per week...")

# Retrieve relevant documents with content
results = client.retrieve("How much PTO do I get?", k=3)
for r in results:
    print(f"{r.title}: {r.content[:100]}...")

For complete RAG examples with Anthropic, OpenAI, Azure, and more, see examples/.

Async Processing

For large files or frontend integrations that need progress feedback, use the async REST endpoint:

import httpx, time

resp = httpx.post(
    "https://api.aetherdb.ai/documents/async?filename=report.pdf",
    content=open("report.pdf", "rb").read(),
    headers={"Authorization": "Bearer aether_..."},
)
job = resp.json()  # {"job_id": "...", "poll_url": "/documents/jobs/..."}

while True:
    status = httpx.get(
        f"https://api.aetherdb.ai{job['poll_url']}",
        headers={"Authorization": "Bearer aether_..."},
    ).json()
    print(f"{status['progress']:.0%} - {status['message']}")
    if status["status"] in ("completed", "failed"):
        break
    time.sleep(0.5)

CLI

aether-py status
aether-py insert document.pdf
aether-py search "your query"
aether-py list

License

MIT

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

aether_ai-0.2.0.tar.gz (31.1 kB view details)

Uploaded Jun 15, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

aether_ai-0.2.0-py3-none-any.whl (26.5 kB view details)

Uploaded Jun 15, 2026 Python 3

File details

Details for the file aether_ai-0.2.0.tar.gz.

File metadata

Download URL: aether_ai-0.2.0.tar.gz
Upload date: Jun 15, 2026
Size: 31.1 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for aether_ai-0.2.0.tar.gz
Algorithm	Hash digest
SHA256	`4107b4c186d24d37f74a71fec69c6dc7db9e13d8df50a3da4812225f2dfe26f3`
MD5	`9349f68abedd10be090928175e43ee4c`
BLAKE2b-256	`5ca3b473117ec8e6b0672dade746528ca492f0c4e08858d81fca2f45c30f428c`

See more details on using hashes here.

Provenance

The following attestation bundles were made for aether_ai-0.2.0.tar.gz:

Publisher: release.yml on Quintessence-Group/aether-sdk-python

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: aether_ai-0.2.0.tar.gz
- Subject digest: 4107b4c186d24d37f74a71fec69c6dc7db9e13d8df50a3da4812225f2dfe26f3
- Sigstore transparency entry: 1828412750
- Sigstore integration time: Jun 15, 2026
Source repository:
- Permalink: Quintessence-Group/aether-sdk-python@15bb5ab428509290debd1c8ab9ad370faddffb2f
- Branch / Tag: refs/tags/v0.2.0
- Owner: https://github.com/Quintessence-Group
- Access: private
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release.yml@15bb5ab428509290debd1c8ab9ad370faddffb2f
- Trigger Event: push