Skip to main content

End-to-end observability with built-in security guardrails.

Project description

llm-traceguard

llm-traceguard is an open-source Python library that provides Open Telemetry integration with Large Language Models (LLMs). It is designed to facilitate tracing and safeguarding applications that leverage LLMs, ensuring better monitoring and reliability.

Features

  • Easy integration with Open Telemetry for LLM applications.
  • Real-time tracing and monitoring of LLM-based systems.
  • Enhanced safeguards and insights for your LLM applications.

Installation

To install llm-traceguard, simply use pip:

pip install llm-traceguard

Usage 🚀

Here's a basic example of how to use llm-traceguard in your project:

import llm_traceguard

llm_traceguard.instrument()

Requirements 📋

  • Python 3.8 or higher
  • opentelemetry-api
  • opentelemetry-sdk

Contributing 👐

Contributions are welcome! For major changes, please open an issue first to discuss what you would like to change. Please make sure to update tests as appropriate.

License 📄

llm-traceguard is licensed under the Apache-2.0 License. See LICENSE for more details.

Contact 📧

For support or any questions, feel free to contact us at support@whylabs.ai.

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

opengenaitelemetry-0.0.1.dev0.tar.gz (10.1 kB view details)

Uploaded Source

Built Distribution

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

opengenaitelemetry-0.0.1.dev0-py3-none-any.whl (11.5 kB view details)

Uploaded Python 3

File details

Details for the file opengenaitelemetry-0.0.1.dev0.tar.gz.

File metadata

  • Download URL: opengenaitelemetry-0.0.1.dev0.tar.gz
  • Upload date:
  • Size: 10.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.4.0 CPython/3.9.7 Darwin/23.1.0

File hashes

Hashes for opengenaitelemetry-0.0.1.dev0.tar.gz
Algorithm Hash digest
SHA256 5b9c73b1d8d18b96ee5b770669ec5f15e830a13beb9e98ed3da0f5a68c63e94f
MD5 102da5a70429101e7b612d12e0052c0b
BLAKE2b-256 17058bbba13c64f35cd8b9ce0a2517d83d661209db159c032b1a92799fcb163b

See more details on using hashes here.

File details

Details for the file opengenaitelemetry-0.0.1.dev0-py3-none-any.whl.

File metadata

File hashes

Hashes for opengenaitelemetry-0.0.1.dev0-py3-none-any.whl
Algorithm Hash digest
SHA256 06ab6eb0c66efa9ce30cf9f7c4088a74b640313bd1080f1bdbb755194a41a774
MD5 27dde4070a50ed9afb22a39ad5e35193
BLAKE2b-256 0f7a53819aea4f37fcb71ffd1c8584714e6ca74109c41af13b82a34f47280fe7

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