Provider Integrations

Drop-in wrappers that add RAIL evaluation to your existing LLM calls. Every response is automatically scored — no code changes needed beyond swapping the client.

Install: pip install "rail-score-sdk[integrations]" for all providers, or install individually with [openai], [anthropic], [google].

OpenAI

Wrap OpenAI chat completions with automatic RAIL scoring.

from rail_score_sdk.integrations import RAILOpenAI

# Drop-in replacement for openai.OpenAI()
client = RAILOpenAI(
    openai_api_key="sk-...",
    rail_api_key="rail_...",
    threshold=7.0   # Optionally set minimum quality threshold
)

# Use exactly like the OpenAI client
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Explain quantum computing"}]
)

# Standard OpenAI response + RAIL scores attached
print(response.choices[0].message.content)
print(response.rail_score)      # RAIL evaluation result
print(response.rail_score.score)  # 8.5

Anthropic

Wrap Anthropic Claude calls with RAIL evaluation.

from rail_score_sdk.integrations import RAILAnthropic

client = RAILAnthropic(
    anthropic_api_key="sk-ant-...",
    rail_api_key="rail_..."
)

response = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Write a hiring policy"}]
)

print(response.content[0].text)
print(response.rail_score.score)  # RAIL evaluation attached

Google Gemini

Wrap Google Gemini calls with RAIL evaluation.

from rail_score_sdk.integrations import RAILGemini

client = RAILGemini(
    google_api_key="AIza...",
    rail_api_key="rail_..."
)

response = client.generate_content(
    model="gemini-2.0-flash",
    contents="Describe the benefits of renewable energy"
)

print(response.text)
print(response.rail_score.score)

Langfuse v3

Add RAIL scores as Langfuse trace metadata for observability.

from rail_score_sdk.integrations import RAILLangfuse

# Integrates RAIL evaluation results into Langfuse traces
rail_langfuse = RAILLangfuse(
    rail_api_key="rail_...",
    langfuse_public_key="pk-...",
    langfuse_secret_key="sk-..."
)

# RAIL scores appear as trace metadata in Langfuse dashboard
rail_langfuse.trace(
    name="chat-response",
    input="User question",
    output="AI response text"
)  # Automatically evaluates and logs RAIL scores

LiteLLM Guardrail

Use RAIL as a guardrail in your LiteLLM proxy.

# In your LiteLLM config, add RAIL as a guardrail:
# litellm_settings:
#   guardrails:
#     - rail_score:
#         api_key: rail_...
#         threshold: 7.0

# Or use programmatically:
from rail_score_sdk.integrations import RAILGuardrail

guardrail = RAILGuardrail(
    rail_api_key="rail_...",
    threshold=7.0,
    action="block"  # "block", "log", or "regenerate"
)

How Provider Wrappers Work

1.Your LLM call executes normally and returns a response
2.The wrapper automatically sends the response text to RAIL for evaluation
3.RAIL scores are attached to the response object as .rail_score
4.If a threshold is set and the score is below it, the wrapper can block or regenerate

← Back to SDK Reference API Reference →