langsmith

Install

langsmith on PyPI

pip install langsmith

uv add langsmith

poetry add langsmith

Package facts

Evidence: langsmith-0.10.18-py3-none-any.whl

Keywords: evaluation, langchain, langsmith, language, llm, nlp, platform, tracing, translation

About langsmith

from the package's own PyPI description — quoted content, verbatim

pip install -U langsmith
export LANGSMITH_TRACING=true
export LANGSMITH_API_KEY=ls_...

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!")

Read as markdown · JSON record · Source repository · Homepage · Docs

AI interpretation — verify before relying

AI-generated interpretation of the package facts above; every digit, version, license, or vulnerability id it cites is grounded in the facts already shown on this page

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.

Low friction: pure Python wheel with 14 well-maintained dependencies (httpx, pydantic, requests, websockets, etc.) and active development—released 2 days ago with 1016 repository stars.

MIT license permits unrestricted use, modification, and distribution in both open-source and commercial projects with minimal obligations.

pip install langsmith
export LANGSMITH_API_KEY=ls_...

from langsmith import traceable

@traceable
def my_function(input_str: str):
    return f"Processed: {input_str}"

my_function("test")

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.

Needs verification

• Whether the 14 runtime dependencies have themselves been audited for security or maintenance status beyond their presence in the fact sheet.
• Performance impact of automatic tracing on production LLM applications at scale.

Similar packages