Quickstart
Get your first API call working in 5 minutes.
1
Get your API key
Sign up at ambientmeta.com and copy your API key from the dashboard.
2
Install the SDK
pip install ambientmeta
3
Sanitize some text
from ambientmeta import AmbientMeta client = AmbientMeta(api_key="am_live_your_key_here") # Sanitize text before sending to an LLM result = client.sanitize("Email John Smith at john@acme.com about the project") print(result.sanitized) # "Email [PERSON_1] at [EMAIL_1] about the project" print(result.session_id) # "ses_abc123..."
4
Call your LLM (with safe text)
import openai response = openai.chat.completions.create( model="gpt-4", messages=[{"role": "user", "content": result.sanitized}] ) llm_response = response.choices[0].message.content
5
Rehydrate the response
final = client.rehydrate(llm_response, result.session_id) print(final.text) # Original names and emails restored
That's it! Your LLM never saw the real PII. The original data stayed in your control the entire time.
Using curl
Sanitize
curl -X POST https://api.ambientmeta.com/v1/sanitize \ -H "Authorization: Bearer am_live_xxx" \ -H "Content-Type: application/json" \ -d '{"text": "Email John Smith at john@acme.com about the merger"}'
Response:
{
"sanitized": "Email [PERSON_1] at [EMAIL_1] about the merger",
"session_id": "ses_a1b2c3d4e5f6",
"entities_found": 2,
"processing_ms": 12
}
Rehydrate
curl -X POST https://api.ambientmeta.com/v1/rehydrate \ -H "Authorization: Bearer am_live_xxx" \ -H "Content-Type: application/json" \ -d '{"text": "I will contact [PERSON_1] at [EMAIL_1] tomorrow.", "session_id": "ses_a1b2c3d4e5f6"}'
Next Steps
- Full sanitize API reference
- Create custom patterns for org-specific data
- Use with LangChain
- Python SDK documentation