Skip to main content

An integration package connecting Bidda source-verified compliance intelligence to LangChain

Project description

langchain-bidda

Source-verified regulatory and compliance intelligence for LangChain agents, from the Bidda registry.

langchain-bidda gives a LangChain agent a tool that looks up what a regulation, law, or standard requires and returns a plain summary traced to a primary legal source with a content hash. Each answer points back to the primary instrument, so an agent can cite what it relied on instead of relying on the model's own recall.

This is reference intelligence, not legal advice. The reader draws the legal conclusion.

Installation

pip install -U langchain-bidda

Tools

BiddaComplianceTool

Looks up source-verified compliance intelligence across the Bidda registry (10,000+ obligations across 39 regulated pillars, including the EU AI Act, GDPR, DORA, NIS2, HIPAA, Basel III, and the MITRE ATT&CK / ATLAS / D3FEND / CAPEC families). Uses the free discovery tier, so no API key is required.

from langchain_bidda import BiddaComplianceTool

tool = BiddaComplianceTool()

print(tool.invoke({"query": "EU AI Act Article 10"}))

Example output:

Regulation: Regulation (EU) 2024/1689 - Article 10: Data and data governance
Pillar: AI Governance & Law
Summary: High-risk AI systems trained on data must meet data governance and management practices ...
Node ID: eu-ai-act-article-10-data-governance-training
Source (full node): https://bidda.com/intelligence/eu-ai-act-article-10-data-governance-training

Use inside an agent

from langchain.chat_models import init_chat_model
from langchain_bidda import BiddaComplianceTool

llm = init_chat_model("gpt-4o-mini", model_provider="openai")
agent = llm.bind_tools([BiddaComplianceTool()])

agent.invoke("What does the EU AI Act require for training data governance?")

Configuration

Field Default Purpose
pillar None Restrict results to one pillar slug, e.g. "cybersecurity" or "ai-governance".
max_results 4 How many related node ids to surface after the top match.
skyfire_token / base_tx_hash None Optional credentials for callers who also pull full (gated) node payloads. Not needed for discovery search.

Links

License

MIT

Project details


Download files

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

Source Distribution

langchain_bidda-0.1.0.tar.gz (5.7 kB view details)

Uploaded Source

Built Distribution

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

langchain_bidda-0.1.0-py3-none-any.whl (6.2 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: langchain_bidda-0.1.0.tar.gz
  • Upload date:
  • Size: 5.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.10

File hashes

Hashes for langchain_bidda-0.1.0.tar.gz
Algorithm Hash digest
SHA256 2272102268e019fd31a9e85fc97fd6600013d75391d4162fc8a804db7db37043
MD5 67f6b38f3d5cd87ce48aee2e2589b3c1
BLAKE2b-256 a7c9b0efdb8620b56fc7707c5801c1b00e8ebc190086042c87e39b1b27f57d6e

See more details on using hashes here.

File details

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

File metadata

File hashes

Hashes for langchain_bidda-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d11f5476e4d0d79b89efbdb15c7a723b294e56dd655d251fcaf59ccef49af73b
MD5 ac0d5ae9a14d05184891b7735482ba71
BLAKE2b-256 55b0bdb3824ffc9e72944a122b462141afad29cfcefca4ca744528665ea7fcb5

See more details on using hashes here.

Supported by

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