feat: enhance security by adding security_tier parameter and improving secure memory handling
This commit introduces the security_tier parameter to all SecureChatCompletion calls, allowing users to specify security levels (standard, high, maximum). It also refactors secure memory management in SecureCompletionClient.py to use secure_bytearray instead of secure_bytes, improves memory protection by aligning addresses to page boundaries, and enhances the secure memory locking mechanism. The README.md has been updated to document the new security_tier parameter and include missing import statements.
This commit is contained in:
parent
2fae7d1d24
commit
5641a746b7
4 changed files with 509 additions and 127 deletions
|
|
@ -30,6 +30,7 @@ async def main():
|
|||
messages=[
|
||||
{"role": "user", "content": "Hello! How are you today?"}
|
||||
],
|
||||
security_tier="standard", #optional: standard, high or maximum
|
||||
temperature=0.7
|
||||
)
|
||||
|
||||
|
|
@ -156,6 +157,7 @@ async def main():
|
|||
{"role": "system", "content": "You are a helpful assistant."},
|
||||
{"role": "user", "content": "What is the capital of France?"}
|
||||
],
|
||||
security_tier="standard", #optional: standard, high or maximum
|
||||
temperature=0.7
|
||||
)
|
||||
|
||||
|
|
@ -167,6 +169,7 @@ asyncio.run(main())
|
|||
### With Tools
|
||||
|
||||
```python
|
||||
|
||||
import asyncio
|
||||
from nomyo import SecureChatCompletion
|
||||
|
||||
|
|
@ -194,6 +197,7 @@ async def main():
|
|||
}
|
||||
}
|
||||
],
|
||||
security_tier="standard", #optional: standard, high or maximum
|
||||
temperature=0.7
|
||||
)
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue