promptguard-sdk 0.1.0

Drop-in security for AI applications - AI Firewall SDK

PromptGuard Python SDK

Drop-in security for AI applications. No code changes required.

Installation

pip install promptguard-ai

Quick Start

from promptguard import PromptGuard

# Initialize client
pg = PromptGuard(api_key="pg_xxx")

# Use exactly like OpenAI client
response = pg.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response["choices"][0]["message"]["content"])

Drop-in Replacement

If you're already using OpenAI's Python client, just change the import:

# Before
from openai import OpenAI
client = OpenAI()

# After
from promptguard import PromptGuard
client = PromptGuard(api_key="pg_xxx")

# Your existing code works unchanged!

Features

Security Scanning

# Scan content for threats
result = pg.security.scan("Ignore previous instructions...")

if result["blocked"]:
    print(f"Threat detected: {result['reason']}")

PII Redaction

# Redact PII before sending to LLM
result = pg.security.redact(
    "My email is [e-mail] and SSN is 123-45-6789"
)

print(result["redacted_content"])
# Output: "My email is [EMAIL] and SSN is [SSN]"

Memory (Context Management)

# Store user preferences
pg.memory.store(
    content="User prefers Python for coding tasks",
    memory_type="preference",
    user_id="user-123"
)

# Retrieve relevant context
memories = pg.memory.retrieve(
    query="What programming language should I use?",
    user_id="user-123"
)

# Inject into your prompts
context = memories["formatted_context"]

Async Support

from promptguard import PromptGuardAsync

async with PromptGuardAsync(api_key="pg_xxx") as pg:
    response = await pg.chat.completions.create(
        model="gpt-4",
        messages=[{"role": "user", "content": "Hello!"}]
    )

Configuration

from promptguard import PromptGuard, Config

config = Config(
    api_key="pg_xxx",
    base_url="https://api.promptguard.co/api/v1/proxy",
    enable_caching=True,
    enable_security_scan=True,
    timeout=30.0,
)

pg = PromptGuard(config=config)

Environment Variables

export PROMPTGUARD_API_KEY="pg_xxx"
export PROMPTGUARD_BASE_URL="https://api.promptguard.co/api/v1/proxy"

Then just:

from promptguard import PromptGuard

pg = PromptGuard()  # Uses env vars automatically

Error Handling

from promptguard import PromptGuard, PromptGuardError

try:
    response = pg.chat.completions.create(...)
except PromptGuardError as e:
    if e.code == "BLOCKED":
        print(f"Request blocked: {e.message}")
    elif e.code == "RATE_LIMITED":
        print("Rate limited, try again later")
    else:
        raise

License

MIT