# langchain-ai/langsmith-cookbook

Repository: https://github.com/langchain-ai/langsmith-cookbook
Canonical: https://ross.abutalabs.com/products/langsmith-cookbook
Homepage: https://langsmith-cookbook.vercel.app
Language: Jupyter Notebook
License Family: other
Archived: true
Last push: 2025-11-20T20:47:57+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 53, release rhythm 35, longevity 80
- inputs: {"age_days": 1128, "days_push": 286, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1036, forks 185 (observed 2026-08-28T04:03:19.247272+00:00)

## What it is
A collection of practical Jupyter notebook recipes and examples for using LangSmith to debug, trace, evaluate, and improve LLM applications. It complements the official LangSmith documentation with real-world patterns for tracing, feedback collection, and dataset management.

## Use cases
- learn how to trace LLM applications with LangSmith
- add tracing to non-LangChain Python code
- collect user feedback on LLM runs in a Next.js app
- evaluate and test LLM outputs with datasets
- log runs via the LangSmith REST API
- manage prompts with the LangChain Hub
- debug nested tool calls in LLM agents

## When to choose
- you use LangSmith and want practical, example-driven guidance beyond the docs
- you need copy-paste notebooks for tracing, evaluation, or feedback workflows
- you want real-world recipes for LLM observability

## When to avoid
- you want the LangSmith SDK or product itself rather than examples
- you need a production observability tool, not tutorials
- you don't use LangChain/LangSmith tooling

## Facets
- artifact type: learning-resource
- maturity: active
- function: monitoring, tracing, testing, llm-inference, developer-tools
- domain: large-language-models, artificial-intelligence, developer-tools, tutorials, monitoring
- platform: python, jvm-scripting
- tags: langsmith, langchain, llm-observability, llm-evaluation, cookbook, jupyter-notebooks, prompt-engineering, nodejs

## Member repositories
- langchain-ai/langsmith-cookbook (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:19.247272+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:04:41.251834+00:00, confidence not recorded.
  - readme: https://github.com/langchain-ai/langsmith-cookbook (fetched 2026-08-28T04:03:19.247272+00:00, sha 11a6af6cca35)
  - homepage: https://langsmith-cookbook.vercel.app (fetched 2026-08-29T13:05:41.799028+00:00, sha 7c5f8dc7e2a0)
- Data as of 2026-08-30T08:39:29.467469+00:00.