Skip to main content
Archived

This project has been archived by its maintainers, and is no longer receiving any updates.

Eunomia SDK for LangChain

This package provides integrations between LangChain and Eunomia, allowing you to:

Installation

Install the eunomia-sdk-langchain package via pip:

pip install eunomia-sdk-langchain

Usage

Document Loader

The EunomiaLoader class is a wrapper around any loader class from LangChain that sends documents to the Eunomia server.

from eunomia_sdk_langchain import EunomiaLoader
from langchain_community.document_loaders.csv_loader import CSVLoader

# Create a document loader
loader = CSVLoader("data.csv")

# Wrap the loader with Eunomia
wrapped_loader = EunomiaLoader(loader)

# Load documents and register them with the Eunomia server
docs = wrapped_loader.load(additional_metadata={"group": "financials"})

All loaded documents will be automatically sent to the Eunomia server which will assign an identifier to each document and store their metadata. The identifiers and metadata can then be used to configure or reference policies in the Eunomia server.

Document Retriever

The EunomiaRetriever class wraps any LangChain retriever and filters allowed documents using the Eunomia server.

from eunomia_core import schemas
from eunomia_sdk_langchain import EunomiaRetriever
from langchain_community.retrievers import BM25Retriever
from langchain_core.documents import Document

# Create a retriever with some documents
retriever = BM25Retriever.from_documents([
    Document(page_content="foo", metadata={"confidentiality": "public"}),
    Document(page_content="bar", metadata={"confidentiality": "public"}),
    Document(page_content="foo bar", metadata={"confidentiality": "private"}),
])

# Wrap the retriever with Eunomia
wrapped_retriever = EunomiaRetriever(
    retriever=retriever,
    principal=schemas.PrincipalCheck(uri="test-uri"),
)

# Only documents the principal has access to will be returned
docs = wrapped_retriever.invoke("foo")

Documentation

For detailed usage, check out the SDK's documentation.

Metadata

Release files for eunomia-sdk-langchain 0.3.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for eunomia-sdk-langchain 0.3.2
File Size Uploaded Provenance
eunomia_sdk_langchain-0.3.2.tar.gz 3.5 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for eunomia-sdk-langchain 0.3.2
File Interpreter ABI Platform
eunomia_sdk_langchain-0.3.2-py3-none-any.whl Python 3 none any Details

Total release size: 8.6 kB

Release files / eunomia_sdk_langchain-0.3.2.tar.gz

Download URL eunomia_sdk_langchain-0.3.2.tar.gz
Size 3.5 kB
Tags Source
SHA-256 checksum
How to use checksums
6e815204cc47b8541d69e57ff7fe2e2d432afa88e3dba012e90e94a1d1a32725
BLAKE2b-256 checksum
How to use checksums
edf27369ff99bc8fb5b40439e3b06f76892d7fdb216825c16c6743881ef1fd69
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.6.3

Release files / eunomia_sdk_langchain-0.3.2-py3-none-any.whl

Download URL eunomia_sdk_langchain-0.3.2-py3-none-any.whl
Size 5.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
1fb71a04261bbe0f965ec14d3eacd7bf35f3e8bece1259b249923f57e2098af7
BLAKE2b-256 checksum
How to use checksums
b3d887fd7bf1294fc81434517d4acd5d98462e63409af3e919796e4c9d28caf0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.6.3

Security for eunomia-sdk-langchain 0.3.2

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.

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