SDKs & Integrations - Krixai

Because Krixai acts as a reverse proxy, it works natively with almost any LLM framework by simply changing the base_url.

LangChain Integration

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="gpt-4o",
    api_key="sk-...",
    base_url="https://api.krixaisecurity.com/v1",
    default_headers={"X-Krixai-Key": "kx-live-..."}
)

# All LangChain chains now route through Krixai automatically
response = llm.invoke("Summarize this legal document...")

LlamaIndex Integration

from llama_index.llms.openai import OpenAI

llm = OpenAI(
    model="gpt-4o",
    api_key="sk-...",
    api_base="https://api.krixaisecurity.com/v1",
    default_headers={"X-Krixai-Key": "kx-live-..."}
)

FastAPI Middleware

If you prefer to run Krixai as middleware on your own server rather than proxying outbound requests:

from krixai import KrixaiMiddleware
from fastapi import FastAPI

app = FastAPI()
app.add_middleware(KrixaiMiddleware, api_key="kx-live-...")

# All requests to your AI endpoints are now automatically scanned

⌘I