[PR #4211] [MERGED] Add methodology section to multi-turn online evaluators page #4198

Closed
opened 2026-06-05 19:13:07 -04:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/docs/pull/4211
Author: @langsmith-fleet[bot]
Created: 5/29/2026
Status: Merged
Merged: 6/2/2026
Merged by: @fjmorris

Base: mainHead: docs/add-methodology-online-evaluations-multi-turn


📝 Commits (4)

  • 388b234 Add methodology section to multi-turn online evaluators page
  • f56ec1a Modified online-evaluations-multi-turn.mdx, explained how all_messages variable is calculated.
  • c61937d Merge remote-tracking branch 'origin/main' into docs/add-methodology-online-evaluations-multi-turn
  • ad3795f Merge remote-tracking branch 'origin/main' into docs/add-methodology-online-evaluations-multi-turn

📊 Changes

1 file changed (+15 additions, -3 deletions)

View changed files

📝 src/langsmith/online-evaluations-multi-turn.mdx (+15 -3)

📄 Description

Fixes DOC-1183

Summary

  • Adds a "How it works" section before the Prerequisites section on the multi-turn online evaluators page
  • Explains the end-to-end evaluation lifecycle: trace ingestion, idle time detection, message assembly, LLM-as-a-judge evaluation, and feedback recording
  • Addresses a request from #docs-plz to document the methodology at https://docs.langchain.com/langsmith/online-evaluations-multi-turn#prerequisites

Links

Verification

Not run; docs-only copy change.

Reviewers

Requested review from: @katmayb, @fjmorris


🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/langchain-ai/docs/pull/4211 **Author:** [@langsmith-fleet[bot]](https://github.com/apps/langsmith-fleet) **Created:** 5/29/2026 **Status:** ✅ Merged **Merged:** 6/2/2026 **Merged by:** [@fjmorris](https://github.com/fjmorris) **Base:** `main` ← **Head:** `docs/add-methodology-online-evaluations-multi-turn` --- ### 📝 Commits (4) - [`388b234`](https://github.com/langchain-ai/docs/commit/388b234652217b6a751709b932bf878a366bcb6f) Add methodology section to multi-turn online evaluators page - [`f56ec1a`](https://github.com/langchain-ai/docs/commit/f56ec1ac5f6d80b7aafe6bd9680ac20187ac75db) Modified online-evaluations-multi-turn.mdx, explained how all_messages variable is calculated. - [`c61937d`](https://github.com/langchain-ai/docs/commit/c61937dbb2a71df7ba3993c1debca26a914e57da) Merge remote-tracking branch 'origin/main' into docs/add-methodology-online-evaluations-multi-turn - [`ad3795f`](https://github.com/langchain-ai/docs/commit/ad3795f2ec2fa5897bb5cc6734421ac7f5b52b3a) Merge remote-tracking branch 'origin/main' into docs/add-methodology-online-evaluations-multi-turn ### 📊 Changes **1 file changed** (+15 additions, -3 deletions) <details> <summary>View changed files</summary> 📝 `src/langsmith/online-evaluations-multi-turn.mdx` (+15 -3) </details> ### 📄 Description Fixes DOC-1183 ## Summary - Adds a "How it works" section before the Prerequisites section on the multi-turn online evaluators page - Explains the end-to-end evaluation lifecycle: trace ingestion, idle time detection, message assembly, LLM-as-a-judge evaluation, and feedback recording - Addresses a request from #docs-plz to document the methodology at https://docs.langchain.com/langsmith/online-evaluations-multi-turn#prerequisites ## Links - Linear: https://linear.app/langchain/issue/DOC-1183/add-methodology-explanation-to-online-evaluations-multi-turn - Slack: https://langchain.slack.com/archives/C09G1T60QV9/p1780072374303589 ## Verification Not run; docs-only copy change. ## Reviewers Requested review from: @katmayb, @fjmorris --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-06-05 19:13:07 -04:00
yindo closed this issue 2026-06-05 19:13:07 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/docs#4198