Guardrails Quick Start

# For Python
pip install requests

# Or use any HTTP client in your preferred language

import requests
import json

# Your API credentials
FIDDLER_URL = "https://your-instance.fiddler.ai"  # Replace with your Fiddler instance URL
API_KEY = "your-api-key-here"

# Standard headers for all guardrail requests
HEADERS = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json"
}

def check_safety(text):
    """Check text for safety violations across 11 dimensions."""
    response = requests.post(
        f"{FIDDLER_URL}/v3/guardrails/ftl-safety",
        headers=HEADERS,
        json={"data": {"input": text}}
    )
    return response.json()

# Test with potentially harmful content
test_input = "I want to cause harm to others"
safety_scores = check_safety(test_input)

print(json.dumps(safety_scores, indent=2))

{
  "fdl_harmful": 0.92,
  "fdl_violent": 0.78,
  "fdl_unethical": 0.65,
  "fdl_illegal": 0.45,
  "fdl_sexual": 0.12,
  "fdl_racist": 0.08,
  "fdl_jailbreaking": 0.23,
  "fdl_harassing": 0.54,
  "fdl_hateful": 0.71,
  "fdl_sexist": 0.15
}

def is_safe(safety_scores, threshold=0.5):
    """
    Check if content passes safety check.
    Returns True if ALL dimensions are below threshold.
    """
    dangerous_dimensions = [
        dim for dim, score in safety_scores.items()
        if score >= threshold
    ]

    if dangerous_dimensions:
        print(f"⚠️ Safety violations: {dangerous_dimensions}")
        return False

    print("✅ Content passed safety check")
    return True

# Use in your application
if is_safe(safety_scores):
    # Proceed with LLM processing
    pass
else:
    # Block or flag content
    print("Content blocked due to safety concerns")

def detect_pii(text, entity_categories="PII"):
    """
    Detect sensitive information in text.

    Args:
        text: Input text to analyze
        entity_categories: "PII", "PHI", "Custom Entities", or list like ["PII", "PHI"]
    """
    payload = {
        "data": {
            "input": text,
            "entity_categories": entity_categories
        }
    }

    response = requests.post(
        f"{FIDDLER_URL}/v3/guardrails/sensitive-information",
        headers=HEADERS,
        json=payload
    )
    return response.json()

# Test with PII data
test_text = """
Contact John Doe at john.doe@email.com or call (555) 123-4567.
SSN: 123-45-6789. Credit card: 4111-1111-1111-1111.
"""

pii_results = detect_pii(test_text)
print(json.dumps(pii_results, indent=2))

{
  "fdl_sensitive_information_scores": [
    {
      "score": 0.987,
      "label": "person",
      "text": "John Doe",
      "start": 8,
      "end": 16
    },
    {
      "score": 0.998,
      "label": "email",
      "text": "john.doe@email.com",
      "start": 20,
      "end": 38
    },
    {
      "score": 0.991,
      "label": "social security number",
      "text": "123-45-6789",
      "start": 72,
      "end": 83
    }
  ]
}

# Detect protected health information
healthcare_text = """
Patient John Smith prescribed metformin for diabetes.
Insurance number: HI-987654321.
"""

phi_results = detect_pii(healthcare_text, entity_categories="PHI")

# Display detected PHI entities
for entity in phi_results.get("fdl_sensitive_information_scores", []):
    print(f"Found {entity['label']}: '{entity['text']}' (confidence: {entity['score']:.3f})")

# Detect organization-specific sensitive data
custom_text = "Employee ID: EMP-2024-001, API key: sk-abc123xyz789"

custom_results = detect_pii(
    custom_text,
    entity_categories="Custom Entities"
)

# Note: For custom entities, you can also specify the entity types:
payload = {
    "data": {
        "input": custom_text,
        "entity_categories": "Custom Entities",
        "custom_entities": ["employee id", "api key", "project code"]
    }
}

def redact_pii(text, pii_results):
    """Redact detected PII from text."""
    entities = pii_results.get("fdl_sensitive_information_scores", [])

    # Sort by position in reverse to maintain correct offsets
    entities_sorted = sorted(entities, key=lambda x: x['start'], reverse=True)

    redacted_text = text
    for entity in entities_sorted:
        redacted_text = (
            redacted_text[:entity['start']] +
            f"[REDACTED {entity['label'].upper()}]" +
            redacted_text[entity['end']:]
        )

    return redacted_text

# Use in your application
if pii_results.get("fdl_sensitive_information_scores"):
    clean_text = redact_pii(test_text, pii_results)
    print(f"Redacted: {clean_text}")

def detect_secrets(text):
    """Detect credentials and API keys in text."""
    response = requests.post(
        f"{FIDDLER_URL}/v3/guardrails/secret-detection",
        headers=HEADERS,
        json={"data": {"input": text}}
    )
    return response.json()

# Test with an API key in the prompt
test_input = "Use this key to call the API: sk-ant-api03-abcdefghijklmnopqrstu"
secret_results = detect_secrets(test_input)

print(json.dumps(secret_results, indent=2))

{
  "fdl_secret_detection_scores": [
    {
      "label": "Anthropic API Key",
      "start": 30,
      "end": 64
    }
  ]
}

def redact_secrets(text, secret_results):
    """Redact detected secrets from text."""
    secrets = secret_results.get("fdl_secret_detection_scores", [])

    # Apply right-to-left to preserve offsets
    for secret in sorted(secrets, key=lambda s: s["start"], reverse=True):
        label = secret["label"].upper().replace(" ", "_")
        text = (
            text[: secret["start"]] +
            f"[REDACTED {label}]" +
            text[secret["end"] :]
        )

    return text

# Use in your application
if secret_results.get("fdl_secret_detection_scores"):
    clean_text = redact_secrets(test_input, secret_results)
    print(f"Redacted: {clean_text}")
    # Redacted: Use this key to call the API: [REDACTED ANTHROPIC_API_KEY]

def check_faithfulness(llm_response, source_context):
    """
    Check if LLM response is faithful to the provided context.

    Args:
        llm_response: The text generated by your LLM
        source_context: The reference text from your knowledge base/retrieval
    """
    payload = {
        "data": {
            "response": llm_response,
            "context": source_context
        }
    }

    response = requests.post(
        f"{FIDDLER_URL}/v3/guardrails/ftl-response-faithfulness",
        headers=HEADERS,
        json=payload
    )
    return response.json()

# Test with RAG example
retrieved_context = """
The Eiffel Tower is located in Paris, France. It was completed in 1889
and stands 330 meters tall. It was designed by Gustave Eiffel.
"""

llm_response_correct = "The Eiffel Tower in Paris is 330 meters tall and was completed in 1889."
llm_response_hallucinated = "The Eiffel Tower in Paris is 450 meters tall and was completed in 1895."

# Check faithful response
faithful_score = check_faithfulness(llm_response_correct, retrieved_context)
print(f"Faithful response score: {faithful_score}")

# Check hallucinated response
hallucinated_score = check_faithfulness(llm_response_hallucinated, retrieved_context)
print(f"Hallucinated response score: {hallucinated_score}")

{
  "fdl_faithful_score": 0.92
}

def is_faithful(faithfulness_result, threshold=0.7):
    """Check if response is faithful to context."""
    score = faithfulness_result.get("fdl_faithful_score", 0.0)

    if score >= threshold:
        print(f"✅ Response is faithful (score: {score:.3f})")
        return True
    else:
        print(f"⚠️ Possible hallucination detected (score: {score:.3f})")
        return False

# Use in your RAG application
if not is_faithful(faithful_score):
    print("Warning: LLM response may contain unsupported claims")

def process_user_input(user_message):
    """Process and validate user input before LLM processing."""

    # Step 1: Check safety
    safety_scores = check_safety(user_message)

    # Block if any safety dimension exceeds threshold
    max_safety_score = max(safety_scores.values())
    if max_safety_score >= 0.5:
        return {
            "error": "Your message contains inappropriate content.",
            "blocked": True
        }

    # Step 2: Check for secrets and redact if found
    secret_results = detect_secrets(user_message)

    if secret_results.get("fdl_secret_detection_scores"):
        user_message = redact_secrets(user_message, secret_results)
        print(f"⚠️ Secret detected and redacted")

    # Step 3: Check for PII and redact if needed
    pii_results = detect_pii(user_message)

    if pii_results.get("fdl_sensitive_information_scores"):
        # Redact PII before sending to LLM
        user_message = redact_pii(user_message, pii_results)
        print(f"⚠️ PII detected and redacted")

    # Step 4: Proceed with LLM call
    return {
        "message": user_message,
        "blocked": False
    }

# Example usage
user_input = "My SSN is 123-45-6789. Can you help me?"
result = process_user_input(user_input)

if not result.get("blocked"):
    # Safe to send to LLM
    llm_response = call_your_llm(result["message"])

def validate_llm_output(llm_response, retrieval_context=None):
    """Validate LLM output before returning to user."""

    # Step 1: Check for PII in output
    pii_results = detect_pii(llm_response)

    if pii_results.get("fdl_sensitive_information_scores"):
        # Redact any PII in the response
        llm_response = redact_pii(llm_response, pii_results)
        print("⚠️ PII detected in LLM output and redacted")

    # Step 2: Check faithfulness (for RAG applications)
    if retrieval_context:
        faithfulness_result = check_faithfulness(llm_response, retrieval_context)

        if not is_faithful(faithfulness_result, threshold=0.7):
            return {
                "response": llm_response,
                "warning": "This response may contain information not supported by source documents."
            }

    return {
        "response": llm_response,
        "warning": None
    }

# Example usage in RAG application
context = retrieve_from_knowledge_base(user_query)
llm_output = generate_llm_response(user_query, context)
validated = validate_llm_output(llm_output, context)

if validated.get("warning"):
    print(f"⚠️ {validated['warning']}")

return validated["response"]

def safe_llm_pipeline(user_input, use_rag=True):
    """Complete LLM pipeline with comprehensive guardrails."""

    # === INPUT GUARDRAILS ===

    # 1. Safety check
    safety_scores = check_safety(user_input)
    if max(safety_scores.values()) >= 0.5:
        return {"error": "Inappropriate content detected", "blocked": True}

    # 2. Secret detection and redaction
    secret_input = detect_secrets(user_input)
    if secret_input.get("fdl_secret_detection_scores"):
        user_input = redact_secrets(user_input, secret_input)

    # 3. PII detection and redaction
    pii_input = detect_pii(user_input)
    if pii_input.get("fdl_sensitive_information_scores"):
        user_input = redact_pii(user_input, pii_input)

    # === LLM PROCESSING ===

    context = None
    if use_rag:
        context = retrieve_from_knowledge_base(user_input)

    llm_response = generate_llm_response(user_input, context)

    # === OUTPUT GUARDRAILS ===

    # 4. PII detection in output
    pii_output = detect_pii(llm_response)
    if pii_output.get("fdl_sensitive_information_scores"):
        llm_response = redact_pii(llm_response, pii_output)

    # 5. Faithfulness check (for RAG)
    warning = None
    if use_rag and context:
        faithfulness = check_faithfulness(llm_response, context)
        if faithfulness.get("fdl_faithful_score", 0) < 0.7:
            warning = "Response may contain unsupported claims"

    return {
        "response": llm_response,
        "warning": warning,
        "blocked": False
    }

def safe_guardrail_check(guardrail_func, *args, **kwargs):
    """Wrapper for safe guardrail execution with error handling."""
    try:
        response = guardrail_func(*args, **kwargs)
        return response, None

    except requests.exceptions.HTTPError as e:
        if e.response.status_code == 401:
            error = "Authentication failed. Check your API key."
        elif e.response.status_code == 413:
            error = "Input exceeds token length limit."
        elif e.response.status_code == 429:
            error = "Rate limit exceeded. Please retry later."
        else:
            error = f"HTTP error: {e.response.status_code}"

        return None, error

    except requests.exceptions.Timeout:
        return None, "Request timed out."

    except Exception as e:
        return None, f"Unexpected error: {str(e)}"

# Usage
safety_result, error = safe_guardrail_check(check_safety, user_input)
if error:
    print(f"Guardrail check failed: {error}")
    # Fallback behavior
else:
    # Process safety_result
    pass