vera-embed-openai

Official OpenAI embeddings plugin for VERA. Registers the openai provider under the vera.embedders entry-point group.

vera-cli and vera-app depend on this package so hosted OpenAI conversion works out of the box. The client uses stdlib urllib — there is no openai SDK dependency.

Install

python -m pip install "vera-embed-openai>=0.3.0"

From a repository checkout with uv, the workspace installs it by default (via vera-cli / vera-app):

uv sync

Usage

set OPENAI_API_KEY=...
vera convert "manual.pdf" --model openai:text-embedding-3-small

import os

from vera_ingest import convert

os.environ["OPENAI_API_KEY"] = "..."
convert("manual.pdf", "manual.vera", model="openai:text-embedding-3-small")

Keep the API key in OPENAI_API_KEY. Optional OPENAI_BASE_URL (default https://api.openai.com/v1) points at Azure, OpenRouter, or a local OpenAI-compatible server. Archives still record openai:<model-id>, so two endpoints that embed different models under the same id are indistinguishable at search time.

Notes

  • Known dimensions (no network in the constructor): text-embedding-3-small 1536, text-embedding-3-large 3072, text-embedding-ada-002 1536. Unrecognized model ids probe once on first use.
  • Convert-time options: batch_size (1–2048) and timeout seconds. Search resolves get_embedder(stored_model_name) with defaults.
  • Semantic search of a hosted archive needs the same provider and credentials on the searching machine. Keyword search still works without a key.
  • Desktop Convert Cancel does not interrupt an in-flight embeddings HTTP batch; conversion checks cancellation after embed() returns.

See the vera-embed-openai documentation and conversion guide.

Project links

Data verified by PyPI on Aug 25, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for dkylewillis from gravatar.com dkylewillis

Credits

Author: Kyle Willis

GitHub Statistics

Data verified by PyPI on Aug 25, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License

Apache Software License (Apache-2.0)

Requires

Python >=3.10

Tags

embeddings openai semantic-search vera

Classifiers

Report project as malware

Download files

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

Source Distribution

vera_embed_openai-0.3.1.tar.gz (8.9 kB view details)

Uploaded Source

Built Distribution

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

vera_embed_openai-0.3.1-py3-none-any.whl (8.6 kB view details)

Uploaded Python 3

File details

Details for the file vera_embed_openai-0.3.1.tar.gz.

File metadata

  • Download URL: vera_embed_openai-0.3.1.tar.gz
  • Upload date:
  • Size: 8.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for vera_embed_openai-0.3.1.tar.gz
Algorithm Hash digest
SHA256 46859a09e0b5309bcc6bb107a405bfc4c587c6f1f0d29f38457235e0301f3f6a
MD5 1b8531464302cbb6a5912d45f7d59939
BLAKE2b-256 0a9eaac3dec5e6d9da44e72107e80bd7fd8869549407e4ea1cbd9aad4c836421

See more details on using hashes here.

Provenance

The following attestation bundles were made for vera_embed_openai-0.3.1.tar.gz:

Publisher: publish-pypi.yml on dkylewillis/vera

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

File details

Details for the file vera_embed_openai-0.3.1-py3-none-any.whl.

File metadata

File hashes

Hashes for vera_embed_openai-0.3.1-py3-none-any.whl
Algorithm Hash digest
SHA256 f4bbdec35b8fe538d9b5a415aa1c7c9de65557d7d53dc0d49f944569a39f3ab0
MD5 2bea41e4fbdfc8ca00c0dbe6d0a96947
BLAKE2b-256 1230a22d84b53503d68ab8140beba7225a989ca1ea4620c229545600fc7dd7f7

See more details on using hashes here.

Provenance

The following attestation bundles were made for vera_embed_openai-0.3.1-py3-none-any.whl:

Publisher: publish-pypi.yml on dkylewillis/vera

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

Release history Release notifications | RSS feed

This release

0.3.1 This release

2 files

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page