Skip to main content

Observability stack: OpenTelemetry tracing, Langfuse integration, and drift detection

Project description

rag-forge-observability

OpenTelemetry tracing and query drift detection for the RAG-Forge toolkit.

Installation

pip install rag-forge-observability

Usage

from rag_forge_observability.drift import DriftDetector, DriftBaseline

baseline = DriftBaseline(embeddings=[[1.0, 0.0, 0.0]])
detector = DriftDetector(threshold=0.15)
report = detector.analyze(current_embeddings=[[0.9, 0.1, 0.0]], baseline=baseline)
print(f"Drift detected: {report.is_drifting}")

Features

  • OpenTelemetry tracing for all RAG pipeline stages
  • Query drift detection with baseline comparison
  • Centroid-based cosine distance analysis

License

MIT

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

rag_forge_observability-0.1.0.tar.gz (6.2 kB view details)

Uploaded Source

Built Distribution

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

rag_forge_observability-0.1.0-py3-none-any.whl (6.1 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: rag_forge_observability-0.1.0.tar.gz
  • Upload date:
  • Size: 6.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for rag_forge_observability-0.1.0.tar.gz
Algorithm Hash digest
SHA256 06d686661bc2e409481516a567d818017db33bce48cb9ea063aa29a3965e650f
MD5 7d730887a8d7225fc83c8f3cc5c7a475
BLAKE2b-256 69246eda9b8d3346f1518e2c22330ab66ccda1133317b06cc3a1e255b11633df

See more details on using hashes here.

File details

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

File metadata

File hashes

Hashes for rag_forge_observability-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 1bc3a39abb3306d5e39633467aaf49e52effde1c1fc46a576eced8d6058c95c6
MD5 fca57448ef1f87b47bec30d2011f16ce
BLAKE2b-256 ebeefd29030be159881f87f16e160900849328020c4efef801e70d44ed921091

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