docs: Move multiple playground messages guide

docs/evaluation/how_to_guides/index.md

@@ -30,7 +30,6 @@ Evaluate and improve your application before deploying it.
 - [Run an evaluation from the UI](./how_to_guides/run_evaluation_from_prompt_playground)
 - [Run an evaluation via the REST API](./how_to_guides/run_evals_api_only)
 - [Run an evaluation with multimodal content](./how_to_guides/evaluate_with_attachments)
-- [Set up a multi-turn evaluation](./how_to_guides/multiturn_evaluation)
 
 ### Define an evaluator
 

docs/prompt_engineering/how_to_guides/index.md

@@ -16,12 +16,13 @@ Organize and manage prompts in LangSmith to streamline your LLM development work
 
 Quickly iterate on prompts and models in the LangSmith Playground.
 
-- [Run an evaluation in the Playground](/evaluation?mode=ui)
+- [Run an evaluation in the playground](/evaluation?mode=ui)
 - [Include multimodal content in a prompt](./how_to_guides/multimodal_content)
 - [Manage prompt settings](./how_to_guides/managing_model_configurations)
 - [Iterate on your prompts with the Prompt Canvas](./how_to_guides/prompt_canvas)
 - [Run the playground against a custom LangServe model server](./how_to_guides/custom_endpoint)
 - [Run the playground against an OpenAI-compliant model provider/proxy](./how_to_guides/custom_openai_compliant_model)
+- [Use multiple messages in the playground](./how_to_guides/multiturn_evaluation)
 
 ## Few shot prompting
 

docs/evaluation/how_to_guides/multiturn_evaluation.mdx → docs/prompt_engineering/how_to_guides/multiple_messages.mdx

@@ -1,10 +1,7 @@
-# How to set up a multi-turn evaluation
+# How to use multiple messages in the playground
 
-LangSmith makes it easy to evaluate multi-turn conversations in the playground. This allows you to evaluate how changing your system prompt,
-the tools available to the model, or the output schema affects a conversation with multiple messages.
-
-This how-to guide walks you through the various ways you can set up the playground for multi-turn evaluation, which will allow you to
-test different tool configurations and system prompts to see how they impact your system.
+This how-to guide walks you through the various ways you can set up the playground for multi-turn conversations, which will allow you to
+test different tool configurations and system prompts against longer threads of messages.
 
 ![](./static/multiturn_diagram.png)
 
@@ -22,7 +19,7 @@ You can then edit the system prompt, tweak the tools and/or output schema and ob
 Before starting, make sure you have [set up your dataset](../../evaluation/how_to_guides/manage_datasets_in_application). Since you want to evaluate
 multi-turn conversations, make sure there is a key in your inputs that contains a list of messages.
 
-Once you have created your dataset, head to the playground and [load your dataset](/evaluation/how_to_guides/manage_datasets_in_application#from-the-prompt-playground) to evaluate.
+Once you have created your dataset, head to the playground and [load your dataset](../../evaluation/how_to_guides/manage_datasets_in_application#from-the-prompt-playground) to evaluate.
 
 Then, add a messages list variable to your prompt, making sure to name it the same as the key in your inputs that contains the list of messages:
 
@@ -48,6 +45,6 @@ of the `Messages List` variable, allowing you to reuse this prompt across variou
 ## Next Steps
 
 Now that you know how to set up your multi-turn evaluation, you can either manually 
-inspect and judge the outputs, or you can [add evaluators](../how_to_guides#define-an-evaluator) to get repeatable, quantitative results.
+inspect and judge the outputs, or you can [add evaluators](../../evaluation/how_to_guides#define-an-evaluator) to classify results.
 
 You can also read [these how-to guides](../../prompt_engineering/how_to_guides#playground) to learn more about how to use the playground to run evaluations.

vercel.json

@@ -179,6 +179,10 @@
       "source": "/evaluation/how_to_guides/use_langchain_off_the_shelf_evaluators",
       "destination": "/evaluation/how_to_guides/prebuilt_evaluators"
     },
+    {
+      "source": "/evaluation/how_to_guides/multiturn_evaluation",
+      "destination": "/prompt_engineering/how_to_guides/multiple_messages"
+    },
     {
       "source": "/old/tracing/faq/querying_traces",
       "destination": "/observability/how_to_guides/export_traces"