parea-ai/parea-sdk-py
Python SDK for experimenting, testing, evaluating & monitoring LLM-powered applications - Parea AI (YC S23)
Provides automatic client wrapping for OpenAI and Anthropic to capture LLM calls, hierarchical tracing via decorators for mapping function execution flows, and a prompt deployment system with templating support for non-engineer collaboration. Integrates with LangChain, Instructor, DSPy, and LiteLLM, while supporting dataset-driven experiments with built-in evaluation metrics like Levenshtein distance for benchmarking LLM outputs.
No commits in the last 6 months.
Stars
82
Forks
9
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/parea-ai/parea-sdk-py"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Mirascope/lilypad
Open-source versioning, tracing, and annotation tooling.
Supervertaler/Supervertaler-Workbench
Open-source, AI-enhanced CAT tool with multi-LLM support, translation memory, glossary...
crjaensch/PromptoLab
A multi-platform app to serve as a prompts catalog, a LLM playground for running and optimizing...
jeong-se-hun/autotune-skill
Eval-first tuning skill for prompts, docs, skills, and code with guards, holdouts, and stop rules.
MukundaKatta/PromptLab
Prompt experimentation workspace — A/B testing prompt variants with statistical significance testing