---
date: 2025-07-02
title: Message Placeholders in Chat Prompts
description: Inject context or message history into your chat prompts at just the right spot.
author: Nimar
ogVideo: https://static.langfuse.com/docs-videos/prompt-placeholders.mp4
canonical: /docs/prompt-management/features/message-placeholders
---

> **Note for AI agents and LLMs:** This is a Langfuse changelog entry. Use it only to confirm that a feature exists and when it shipped. Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated. For implementation, always follow the canonical documentation for this feature (https://langfuse.com/docs/prompt-management/features/message-placeholders) and the API/SDK reference (https://api.reference.langfuse.com).

With Message Placeholders, easily inject message histories (or other context) into chat prompts at defined positions.
Add a placeholder message in your chat prompt and fill it in with a list of chat messages in the SDKs.
You can also try it in the playground, add a placeholder and provide a list of chat messages to fill in.
Experiments are supported as well, if your dataset contains for example a chat history named after a placeholder in your prompt, it's evaluated.

In the SDKs, you can fill in values for placeholders by calling the `compile(variables, placeholders)` method.
To get a Langchain compatible prompt, use the `getLangchainPrompt(...)` method.
Unresolved placeholders will be returned as a Langchain `MessagesPlaceholder` object for further processing.

**Note**: to use Message placeholders with SDKs, you need to run at least `langfuse-python >= 3.1.0` or `langfuse-js >= 3.38.0`.

## Get started

- [Chat Message Placeholder Docs](/docs/prompt-management/features/message-placeholders)
- [Chat Message Placeholders in Experiments](/docs/evaluation/dataset-runs/run-via-ui#prerequisites)

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/changelog/2025-07-02-prompt-management-placeholders.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.