Azure OpenAI Integration
KoreShield can proxy Azure OpenAI requests to apply sanitization, detection, and policy enforcement before requests reach your Azure endpoint.
Model Names
In Azure OpenAI, the model field usually maps to your deployment name, not the base model name.
Setup
Get Azure Credentials
Obtain your Azure OpenAI endpoint, API key, and deployment name.
Configure KoreShield
Set up KoreShield proxy to route Azure OpenAI requests.
Update Application
Point your application to the KoreShield proxy endpoint.
Basic Request
const response = await fetch("http://localhost:8000/v1/chat/completions", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
model: "gpt-5-mini",
messages: [{ role: "user", content: "Summarize the ticket backlog." }]
})
});
Streaming
const response = await fetch("http://localhost:8000/v1/chat/completions", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
model: "gpt-5-mini",
stream: true,
messages: [{ role: "user", content: "Write an executive summary." }]
})
});
System Prompts and Multi-Turn
{
"model": "gpt-5-mini",
"messages": [
{"role": "system", "content": "You are a support analyst."},
{"role": "user", "content": "Summarize the backlog."},
{"role": "assistant", "content": "Summary..."},
{"role": "user", "content": "Highlight top risks."}
]
}
Error Handling
403 indicates a blocked request due to policy enforcement429 or 5xx typically indicates provider or rate-limit issues
Security Controls
security:
sensitivity: medium
default_action: block
features:
sanitization: true
detection: true
policy_enforcement: true
Next Steps
Configuration
Configure providers and security settings
JavaScript SDK
See SDK usage examples