AuditAI – AI Reliability & Compliance Auditor SDK
Project description
🛡️ AuditAI Client
Python SDK for AuditAI — a production-grade AI Reliability, Compliance, and SLA Observability platform ("Datadog for LLM Agents").
🚀 Installation
Install the official package directly from PyPI:
pip install auditai-client
⚡ Quick Start
Log an LLM execution trace in just a few lines of code:
from auditai import AuditAI
# 1. Initialize the client
client = AuditAI(api_key="your-jwt-token", base_url="http://localhost:8000")
# 2. Log trace with prompt, response, and retrieved context
result = client.log_execution(
project_name="support-agent",
prompt="What is the capital of France?",
response="The capital of France is Paris.",
retrieval_docs=["France is a country in Europe. Its capital is Paris."]
)
print(f"Logged trace ID: {result['id']}")
🔗 Repository & Documentation
For full setup guides, Docker deployment templates, Kubernetes manifests, and evaluation configurations, visit the main repository:
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file auditai_client-1.0.1.tar.gz.
File metadata
- Download URL: auditai_client-1.0.1.tar.gz
- Upload date:
- Size: 3.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d7db5de26957caadd640508b6f047d48936cbda5a0e9fbcf4e3382fde083023c
|
|
| MD5 |
2409a12e2440b6638daf6c35c0e912a9
|
|
| BLAKE2b-256 |
f45919d7194079f2775d3fad790439ab9f025f4cc85f5df83856668f12ab1e67
|
File details
Details for the file auditai_client-1.0.1-py3-none-any.whl.
File metadata
- Download URL: auditai_client-1.0.1-py3-none-any.whl
- Upload date:
- Size: 4.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
17c4588e8459a319603388eae5bcedbb90d78bd79529503853e7a8137e15595a
|
|
| MD5 |
417ba62dec60bb1d08844f16e01daac8
|
|
| BLAKE2b-256 |
d26de9586197e6cdb0cd28be5d19adff1db95999498997b51bcfce5aa2728b7d
|