Skip to main content

Privacy middleware for DSPy and LLM pipelines. Redact and reconstruct PII locally using regex, spaCy, and LLM hybrid detection.

Project description

de-spii

de-spii logo

Privacy middleware for DSPy and LLM pipelines.

De-spii is a Python package for detecting and redacting Personally Identifiable Information (PII) from user prompts before they are sent to cloud-based LLMs. It ensures privacy by stripping sensitive data locally, forwarding redacted queries upstream, and then reconstructing the original content from placeholders after the response.


Roadmap

  • Initial release with regex + spaCy + LLM hybrid redaction
  • DSPy + LangChain pipeline integration demos
  • Add pluggable detector registry
  • PyPI release
  • Docker image with preloaded spaCy models

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

despii-0.1.0.tar.gz (1.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

despii-0.1.0-py3-none-any.whl (2.4 kB view details)

Uploaded Python 3

File details

Details for the file despii-0.1.0.tar.gz.

File metadata

  • Download URL: despii-0.1.0.tar.gz
  • Upload date:
  • Size: 1.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.11

File hashes

Hashes for despii-0.1.0.tar.gz
Algorithm Hash digest
SHA256 58bf56388638246a3d2a9a81da6cf39fc163bc4b7fb63a4b12c2368224d09d0b
MD5 44c3e1f3592d5fb9393ce29539a4c9d4
BLAKE2b-256 93cbb4535cabfae5a9c92e605126cd383f50a42701dd5538c3159dfc57fc28c7

See more details on using hashes here.

File details

Details for the file despii-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: despii-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 2.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.11

File hashes

Hashes for despii-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6f5bed62c37b7bef10f5fc3e5eebecf59f13be52cd4bc0651b9693ffc847e94e
MD5 a735c21b9b9ff44e33b1646317dea447
BLAKE2b-256 2d56ed6e1bbe96f23813f4252304a0473268771f04acdc859d8dff63bb1ae5c6

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page