Skip to main content

langchain-hubris

This package contains the LangChain integration with Hubris — a ruble-billed, OpenAI-compatible LLM gateway giving access to 400+ models (OpenAI, Anthropic, Google, and more) behind a single API key.

Installation

pip install -U langchain-hubris

And set your HUBRIS_API_KEY environment variable — create one at hubris.pw/keys.

Chat Models

ChatHubris exposes the full model catalog at hubris.pw/models:

from langchain_hubris import ChatHubris

llm = ChatHubris(model="claude-sonnet-5")
llm.invoke("Write a haiku about the sea.")

ChatHubris extends BaseChatOpenAI, so streaming, tool calling, and structured output all work out of the box.

Documentation

Full docs: hubris.pw/docs/integrations/langchain

Download files

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

Source Distribution

langchain_hubris-0.1.0.tar.gz (4.5 kB view details)

Uploaded Source

Built Distribution

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

langchain_hubris-0.1.0-py3-none-any.whl (4.6 kB view details)

Uploaded Python 3

File details

Details for the file langchain_hubris-0.1.0.tar.gz.

File metadata

  • Download URL: langchain_hubris-0.1.0.tar.gz
  • Upload date:
  • Size: 4.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for langchain_hubris-0.1.0.tar.gz
Algorithm Hash digest
SHA256 5ce3c7e6730ac2dcf4ffe4fec03f441e80a6bf7a1884c9b566fb4de41a610d6a
MD5 e92f3d4efbe34111786d19fc2d8a61c7
BLAKE2b-256 514d70941c39f09b34966717f163b5fea71be415c102a77dbb67da582e00d2cf

See more details on using hashes here.

Provenance

The following attestation bundles were made for langchain_hubris-0.1.0.tar.gz:

Publisher: publish.yml on Aimagine-life/langchain-hubris

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

File details

Details for the file langchain_hubris-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for langchain_hubris-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 0451d449deb7444431bb0b1e0114846e1ae17af71c111f28ac477aaf944ee900
MD5 cc0115227ac8cf4e7f043a7697dcdeb9
BLAKE2b-256 86c055f3ee7f7c36c89f182b4372e99dde67285c8aa10261d0cce057cde9bd3f

See more details on using hashes here.

Provenance

The following attestation bundles were made for langchain_hubris-0.1.0-py3-none-any.whl:

Publisher: publish.yml on Aimagine-life/langchain-hubris

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

Release history Release notifications | RSS feed

0.1.1

2 files

This release

0.1.0 This release

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page