--- id: langsmith version: "0.10.18" license: MIT license_treatment: permissive maintenance: active --- # langsmith — Client library to connect to the LangSmith Observability and Evaluation Platform. License: permissive · Maintenance: active · Popularity: top 1,000 on PyPI ## Install pip install langsmith uv add langsmith poetry add langsmith ## Description # LangSmith Client SDK [![Release Notes](https://img.shields.io/github/release/langchain-ai/langsmith-sdk?logo=python)](https://github.com/langchain-ai/langsmith-sdk/releases) [![Python Downloads](https://img.shields.io/pypi/dm/langsmith)](https://pypi.org/project/langsmith/) This package contains the Python client for interacting with the [LangSmith platform](https://smith.langchain.com/). To install: ```bash pip install -U langsmith export LANGSMITH_TRACING=true export LANGSMITH_API_KEY=ls_... ``` Then trace: ```python import openai from langsmith.wrappers import wrap_openai from langsmith import traceable # Auto-trace LLM calls in-context client = wrap_openai(openai.Client()) @traceable # Auto-trace this function def pipeline(user_input: str): result = client.chat.completions.create( messages=[{"role": "user", "content": user_input}], model="gpt-3.5-turbo" ) return result.choices[0].message.content pipeline("Hello, world!") ``` See the resulting nested trace [🌐 here](https://smith.langchain.com/public/b37ca9b1-60cd-4a2a-817e-3c4e4443fdc0/r). LangSmith helps you and your team develop and evaluate language models and intelligent agents.... ## AI interpretation — verify before relying LangSmith is a Python client SDK for the LangSmith observability and evaluation platform, enabling you to trace, debug, and evaluate language model applications with automatic instrumentation and benchmark evaluation capabilities. Verdict: Actively maintained, permissively licensed, and dependency-light for its scope. Zero known vulnerabilities and top-1000 popularity tier make it a safe choice for teams adopting LangSmith observability. The 14 runtime dependencies are standard (httpx, pydantic, requests) and well-vetted. [View on SkillFed](https://skillfed.io/packages/langsmith) · [View on PyPI](https://pypi.org/project/langsmith/)