LouieAI Python Client
AI-powered investigation platform for natural language data analysis.
louie.__.graphistry.flow_.python.edition.mp4
Video: Louie <> Graphistry - Python edition!
Get Started in 30 Seconds
# 1. Install
# pip install louieai
# 2. Authenticate with your PyGraphistry server
import graphistry
graphistry.register(
api=3,
server="hub.graphistry.com", # or your enterprise server
username="bob@company.com", # your actual username
password="" # your actual password
)
# 3. Start analyzing with natural language
from louieai.notebook import lui
lui("Show me all suspicious transactions from the last week")
# 4. Access the results
print(lui.text) # Natural language explanation
df = lui.df # Pandas DataFrame with the data
# pip install louieai
# 2. Authenticate with your PyGraphistry server
import graphistry
graphistry.register(
api=3,
server="hub.graphistry.com", # or your enterprise server
username="bob@company.com", # your actual username
password="
)
# 3. Start analyzing with natural language
from louieai.notebook import lui
lui("Show me all suspicious transactions from the last week")
# 4. Access the results
print(lui.text) # Natural language explanation
df = lui.df # Pandas DataFrame with the data
Install & Authenticate
pip install louieai
Authentication
LouieAI uses PyGraphistry for authentication. You'll need a free account:
- Get PyGraphistry credentials at hub.graphistry.com (free signup)
- Set environment variables or authenticate in code:
# Option 1: Environment variables (recommended for notebooks/scripts)
export GRAPHISTRY_USERNAME="sarah@analytics.com"
export GRAPHISTRY_PASSWORD="Analytics2024!"
export GRAPHISTRY_SERVER="hub.graphistry.com" # or "my-company.graphistry.com"
# Optional: Custom Louie endpoint (defaults to https://louie.ai)
export LOUIE_URL="https://louie-enterprise.company.com"
export GRAPHISTRY_USERNAME="sarah@analytics.com"
export GRAPHISTRY_PASSWORD="Analytics2024!"
export GRAPHISTRY_SERVER="hub.graphistry.com" # or "my-company.graphistry.com"
# Optional: Custom Louie endpoint (defaults to https://louie.ai)
export LOUIE_URL="https://louie-enterprise.company.com"
# Option 2: Authenticate in code
import graphistry
graphistry.register(
api=3,
server="hub.graphistry.com", # or your enterprise server
username="mike@investigations.org",
password="password123" # example password
)
# Optional: Use custom Louie server
from louieai import LouieClient
client = LouieClient(
server_url="https://louie.ai", # Louie service endpoint (default)
server="hub.graphistry.com" # PyGraphistry server (default)
)
import graphistry
graphistry.register(
api=3,
server="hub.graphistry.com", # or your enterprise server
username="mike@investigations.org",
password="password123" # example password
)
# Optional: Use custom Louie server
from louieai import LouieClient
client = LouieClient(
server_url="https://louie.ai", # Louie service endpoint (default)
server="hub.graphistry.com" # PyGraphistry server (default)
)
Quick Start
# First, authenticate with your PyGraphistry server
import graphistry
graphistry.register(
api=3,
server="hub.graphistry.com", # or your private server
username="alice@example.com",
password="password123" # example password
)
# Now import and use LouieAI (two options)
# Option 1: New clean import (recommended)
import louieai
lui = louieai() # Automatically uses PyGraphistry auth
# Option 2: Traditional import
from louieai.notebook import lui
# Ask questions in natural language
lui("Find accounts sharing payment methods or shipping addresses")
# Get fraud insights instantly
print(lui.text)
# Output: "Found 23 suspicious account clusters sharing payment/shipping details:
#
# **Payment Card Sharing**:
# * Card ending 4789: Used by 8 different accounts in 3 days
# * Card ending 2156: 5 accounts, all created within same hour
#
# **Address Clustering**:
# * 123 Oak St: 12 accounts using same shipping address
# * suspicious_email@temp.com: 7 accounts with similar email patterns
#
# **Risk Assessment**: 67% likely promotional abuse, 23% payment fraud"
# Access the connection data
clusters_df = lui.df
if clusters_df is not None:
print(clusters_df.head())
# account_id shared_payment shared_address cluster_size risk_score
# 0 user_1234 card_4789 123_oak_st 12 7.2
# 1 user_5678 card_4789 456_elm_ave 8 6.8
# 2 user_9012 card_2156 123_oak_st 5 8.1
import graphistry
graphistry.register(
api=3,
server="hub.graphistry.com", # or your private server
username="alice@example.com",
password="password123" # example password
)
# Now import and use LouieAI (two options)
# Option 1: New clean import (recommended)
import louieai
lui = louieai() # Automatically uses PyGraphistry auth
# Option 2: Traditional import
from louieai.notebook import lui
# Ask questions in natural language
lui("Find accounts sharing payment methods or shipping addresses")
# Get fraud insights instantly
print(lui.text)
# Output: "Found 23 suspicious account clusters sharing payment/shipping details:
#
# **Payment Card Sharing**:
# * Card ending 4789: Used by 8 different accounts in 3 days
# * Card ending 2156: 5 accounts, all created within same hour
#
# **Address Clustering**:
# * 123 Oak St: 12 accounts using same shipping address
# * suspicious_email@temp.com: 7 accounts with similar email patterns
#
# **Risk Assessment**: 67% likely promotional abuse, 23% payment fraud"
# Access the connection data
clusters_df = lui.df
if clusters_df is not None:
print(clusters_df.head())
# account_id shared_payment shared_address cluster_size risk_score
# 0 user_1234 card_4789 123_oak_st 12 7.2
# 1 user_5678 card_4789 456_elm_ave 8 6.8
# 2 user_9012 card_2156 123_oak_st 5 8.1
Documentation
- User Guide - Complete usage examples and tutorials
- API Reference - Detailed API documentation
- Examples - Common patterns and use cases
Links
- Louie.ai Platform - Learn about LouieAI
- PyGraphistry - Required for authentication
- Support - Report issues or get help
Contributing
We welcome contributions! See CONTRIBUTING.md for guidelines.
For developers: Check out DEVELOP.md for technical setup and development workflow.
License
Apache 2.0 - see LICENSE