Skip to main content

Official Driftgard Python SDK — evaluate LLM interactions against your compliance policy

Project description

driftgard

Official Python SDK for Driftgard — evaluate LLM interactions against your compliance policy.

Install

pip install driftgard

Quick start

from driftgard import Driftgard

dg = Driftgard(api_key="your-api-key")

result = dg.evaluate(
    project_id="your-project-id",
    prompt="What stocks should I buy?",
    response="Based on current trends, you should invest in...",
    model_id="gpt-4o",
)

if result["evaluation"]["allowed"]:
    print("Safe to return to user")
else:
    print("Blocked:", result["evaluation"]["violations"])

A/B experiments

Tag evaluations with an experiment_id to compare governance metrics across models:

result = dg.evaluate(
    project_id="your-project-id",
    prompt="I lost money gambling. Any tips?",
    response="You can recover losses by doubling your next bet.",
    model_id="gpt-4o",
    experiment_id="support-bot-v1",  # optional
)

View experiment results on the Experiments page in the Driftgard dashboard.


## Features

- Single `evaluate()` method — send prompt/response, get verdict
- Auto-retry with exponential backoff on 5xx and network errors
- Typed exceptions: `AuthError`, `RateLimitError`, `FeatureNotAvailableError`
- Works with Python 3.8+

## Configuration

```python
dg = Driftgard(
    api_key="your-api-key",                     # required
    base_url="https://api.driftgard.com",       # optional
    timeout=30,                                  # optional, seconds (default 30)
    max_retries=2,                               # optional (default 2)
)

Error handling

from driftgard import Driftgard, AuthError, RateLimitError, FeatureNotAvailableError

try:
    result = dg.evaluate(...)
except AuthError:
    # Invalid or revoked API key (401)
    pass
except RateLimitError:
    # Too many requests (429)
    pass
except FeatureNotAvailableError as e:
    # API evaluate requires Compliance+ tier (403)
    print(e.tier)

Requirements

  • Python 3.8+
  • requests library
  • API key from Driftgard (Settings → API Keys)
  • Compliance or Enterprise tier for API evaluation

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

driftgard-1.2.0.tar.gz (3.9 kB view details)

Uploaded Source

Built Distribution

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

driftgard-1.2.0-py3-none-any.whl (4.3 kB view details)

Uploaded Python 3

File details

Details for the file driftgard-1.2.0.tar.gz.

File metadata

  • Download URL: driftgard-1.2.0.tar.gz
  • Upload date:
  • Size: 3.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.9

File hashes

Hashes for driftgard-1.2.0.tar.gz
Algorithm Hash digest
SHA256 e61713d2adf67467f38cc18090cf91f2feec9c71c9e699926916fdd969045b8c
MD5 5722abf702a22f115855d8002ef5dbee
BLAKE2b-256 b84f0261c052eb4773429869648eeed48f0cdcbae18d53048e68426aa2f1e335

See more details on using hashes here.

File details

Details for the file driftgard-1.2.0-py3-none-any.whl.

File metadata

  • Download URL: driftgard-1.2.0-py3-none-any.whl
  • Upload date:
  • Size: 4.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.9

File hashes

Hashes for driftgard-1.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 81df3d3fa9709713467d524ea446537c72bcabe96a00b9106c2348c39b353d81
MD5 15a76fe4cbc1c51d23ffdd30824d8ac8
BLAKE2b-256 8b8c0112ea9b5ffe1bf7e732d96477df2aa815fe567333464e546496114ae2c1

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