Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.egisai.co/llms.txt

Use this file to discover all available pages before exploring further.

The SDK transparently governs calls made through the official openai Python package. After egisai.init() runs, every supported method on OpenAI / AsyncOpenAI clients is policy-checked, audited, and (where applicable) sanitized before reaching the provider.

​
Supported surface

MethodSyncAsyncStreaming
chat.completions.create✅✅✅
responses.create✅✅✅
Streaming responses are wrapped in a generator that audits the assembled output without materialising it for your code — your existing for chunk in stream: loop continues to work.

​
Minimum version

openai>=1.40 is recommended. Older releases do not expose the modern Chat/Responses API surface the patcher targets.

​
Install

pip install "egisai[openai]"

​
Use

import egisai
import openai

egisai.init(app="customer-support-bot", env="production")

client = openai.OpenAI()
response = client.chat.completions.create(
    model="gpt-4.1",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user",   "content": "Hello!"},
    ],
)
print(response.choices[0].message.content)
The call is intercepted before it leaves your process, evaluated against your active policies, and only then forwarded to OpenAI.

​
Async usage

import asyncio
import egisai
import openai

egisai.init(app="async-bot", env="production")

async def main():
    client = openai.AsyncOpenAI()
    response = await client.chat.completions.create(
        model="gpt-4.1",
        messages=[{"role": "user", "content": "Hello!"}],
    )
    print(response.choices[0].message.content)

asyncio.run(main())

​
Streaming

client = openai.OpenAI()

stream = client.chat.completions.create(
    model="gpt-4.1",
    messages=[{"role": "user", "content": "Tell me a story."}],
    stream=True,
)

for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)

​
Tool calls

When the model returns tool calls, output-side policies (for example tool/ connector restrictions) are evaluated against the structured response. If a tool call is blocked, the verdict is recorded with the offending tool name. 
response = client.chat.completions.create(
    model="gpt-4.1",
    messages=[{"role": "user", "content": "Run the cleanup task."}],
    tools=[
        {
            "type": "function",
            "function": {
                "name": "delete_database",
                "description": "Drop the production database.",
                "parameters": {"type": "object", "properties": {}},
            },
        }
    ],
)

​
When a call is blocked

By default a blocked call raises PermissionError. Switch modes at init if you’d rather receive a refusal-shaped response object: 
egisai.init(..., on_block="stub")
Read Blocking behavior for the full picture.

​
Notes

  • The SDK detects vision parts in messages and ignores image content for text-based PII checks. Text fields elsewhere in the payload are still evaluated.
  • The patcher runs only when the openai package is importable; if you uninstall it, the integration silently disables itself.

​
What’s next

Anthropic

Configuration