rakshak
Python SDK for the Rakshak LLM security guard API.
Install
pip install rakshak
Quick start
import rakshak
client = rakshak.Client(api_key="rsk_...")
# Block malicious input
result = client.guard(user_input)
if result.blocked:
return "I can't help with that."
# Sanitize LLM output (redacts PII, blocks policy violations)
result = client.sanitize(llm_response)
reply = result.safe_text or "[Response blocked]"
# Multi-turn conversation guard
session = client.conversation("user-session-id")
result = session.send(user_message)
if result.flagged:
print("Rising risk score:", result.risk_score)
Async
async_client = rakshak.AsyncClient(api_key="rsk_...")
result = await async_client.guard(user_input)
Release files for rakshak 0.1.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| rakshak-0.1.2.tar.gz | 9.5 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| rakshak-0.1.2-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 22.2 kB
Release files / rakshak-0.1.2.tar.gz
| Download URL | rakshak-0.1.2.tar.gz |
|---|---|
| Size | 9.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d2a6078efb93356f329735fb1b17ca66af512af2e0a4444f744296e52eae335f
|
|
BLAKE2b-256 checksum How to use checksums |
89e8701c4dfab2a7223bfc3a625d494c3124917ebc9ff5711e07d0a41c8b661b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.19
|
Release files / rakshak-0.1.2-py3-none-any.whl
| Download URL | rakshak-0.1.2-py3-none-any.whl |
|---|---|
| Size | 12.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
533daad3ce49c1398fabe41e3a0b1830ef2d413367c23af9e1c4af7082e40f0e
|
|
BLAKE2b-256 checksum How to use checksums |
a70337432ced2efa1ddc89416aa829f5978a957895c54b5a1872d3d2a0851687
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.19
|