Neuro-symbolic guardrails for LLMs: rules + repair loops + (optional) SMT.
Project description
🧠 neurosym
Neuro-symbolic guardrails for LLMs — validate and repair outputs from Gemini, Ollama, or OpenAI using symbolic rules (regex, JSON Schema, Python predicates, SMT/Z3).
🚀 Quickstart
pip install -e ".[dev]"
export GEMINI_API_KEY="your_key"
python -m neurosym.examples.01_pii_redaction
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
neurosym_ai-0.1.1.tar.gz
(26.6 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file neurosym_ai-0.1.1.tar.gz.
File metadata
- Download URL: neurosym_ai-0.1.1.tar.gz
- Upload date:
- Size: 26.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
39ad3bb6a65656e479094d36ee8747ee88e83b51660299db667860c39e822f08
|
|
| MD5 |
b1b2e459849572f2f3063bcf396c7515
|
|
| BLAKE2b-256 |
44d3a12e64519fda7b723613385ece017707faa18dd62d9372f0087a2bbc3843
|
File details
Details for the file neurosym_ai-0.1.1-py3-none-any.whl.
File metadata
- Download URL: neurosym_ai-0.1.1-py3-none-any.whl
- Upload date:
- Size: 36.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
cbc16cf6f3da794ed43bb2907e0f879beb1744508caff3169577c0a8344b39ef
|
|
| MD5 |
1cfecd847fb8262689818b0286ad01d0
|
|
| BLAKE2b-256 |
4c81e058bbdf20f270bf3de8b1c7842b147048dfc3846e6cbef68f1bbd879e86
|
