---
title: How to configure retries and timeouts when fetching prompts?
seoTitle: "Retries and Timeouts When Fetching Prompts"
description: Learn how to adjust retry attempts and timeout settings when fetching prompts using the Langfuse Python and JavaScript/TypeScript SDKs.
tags: [prompt-management]
---

# How to configure retries and timeouts when fetching prompts?

By default, the Langfuse SDKs retry failed prompt-fetch operations twice and apply a 20-second timeout. You can override both settings if you need stricter (or more lenient) parameters.

<LangTabs items={["Python SDK", "JS/TS SDK"]}>
<Tab>

```python
# Number of retries when fetching prompts from the server. Default is 2.
prompt = langfuse.get_prompt("movie-critic", max_retries=3)

# Timeout per call to the Langfuse API in seconds. Default is 20.
prompt = langfuse.get_prompt("movie-critic", fetch_timeout_seconds=3)
```

</Tab>

<Tab>

```ts
// Number of retries when fetching prompts from the server. Default is 2.
const promptWithMaxRetries = await langfuse.getPrompt(
  "movie-critic",
  undefined,
  {
    maxRetries: 5,
  }
);

// Timeout per call to the Langfuse API in milliseconds. Default is 10 seconds.
const promptWithFetchTimeout = await langfuse.getPrompt(
  "movie-critic",
  undefined,
  {
    fetchTimeoutMs: 5000,
  }
);
```

</Tab>

</LangTabs>

The examples above demonstrate how to fine-tune reliability parameters for prompt retrieval. Adjust the values to balance resilience and latency according to your application’s requirements.

<!-- 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/faq/all/error-handling-and-timeouts.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>.