> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-export-1767976498-81c8aa9.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Manage prompts programmatically

You can use the LangSmith Python and TypeScript SDK to manage prompts programmatically.

<Note>
  Previously this functionality lived in the `langchainhub` package which is now deprecated. All functionality going forward will live in the `langsmith` package.
</Note>

## Install packages

In Python, you can directly use the LangSmith SDK (*recommended, full functionality*) or you can use through the LangChain package (limited to pushing and pulling prompts).

In TypeScript, you must use the LangChain npm package for pulling prompts (it also allows pushing). For all other functionality, use the LangSmith package.

<CodeGroup>
  ```bash pip theme={null}
  pip install -U langsmith # version >= 0.1.99
  ```

  ```bash uv theme={null}
  uv add langsmith  # version >= 0.1.99
  ```

  ```bash TypeScript theme={null}
  yarn add langsmith langchain // langsmith version >= 0.1.99 and langchain version >= 0.2.14
  ```
</CodeGroup>

## Configure environment variables

If you already have `LANGSMITH_API_KEY` set to your current workspace's api key from LangSmith, you can skip this step.

Otherwise, get an API key for your workspace by navigating to `Settings > API Keys > Create API Key` in LangSmith.

Set your environment variable.

```bash theme={null}
export LANGSMITH_API_KEY="lsv2_..."
```

<Note>
  What we refer to as "prompts" used to be called "repos", so any references to "repo" in the code are referring to a prompt.
</Note>

## Push a prompt

To create a new prompt or update an existing prompt, you can use the `push prompt` method.

<CodeGroup>
  ```python Python theme={null}
  from langsmith import Client
  from langchain_core.prompts import ChatPromptTemplate

  client = Client()
  prompt = ChatPromptTemplate.from_template("tell me a joke about {topic}")
  url = client.push_prompt("joke-generator", object=prompt)
  # url is a link to the prompt in the UI
  print(url)
  ```

  ```python LangChain (Python) theme={null}
  from langchain_classic import hub as prompts
  from langchain_core.prompts import ChatPromptTemplate

  prompt = ChatPromptTemplate.from_template("tell me a joke about {topic}")
  url = prompts.push("joke-generator", prompt)
  # url is a link to the prompt in the UI
  print(url)
  ```

  ```typescript TypeScript theme={null}
  import * as hub from "langchain/hub";
  import { ChatPromptTemplate } from "@langchain/core/prompts";

  const prompt = ChatPromptTemplate.fromTemplate("tell me a joke about {topic}");
  const url = hub.push("joke-generator", {
    object: prompt,
  });
  // url is a link to the prompt in the UI
  console.log(url);
  ```
</CodeGroup>

You can also push a prompt as a RunnableSequence of a prompt and a model. This is useful for storing the model configuration you want to use with this prompt. The provider must be supported by the LangSmith playground. (see settings here: [Supported Providers](https://langsmith.com/playground))

<CodeGroup>
  ```python Python theme={null}
  from langsmith import Client
  from langchain_core.prompts import ChatPromptTemplate
  from langchain_openai import ChatOpenAI

  client = Client()
  model = ChatOpenAI(model="gpt-4o-mini")
  prompt = ChatPromptTemplate.from_template("tell me a joke about {topic}")
  chain = prompt | model
  client.push_prompt("joke-generator-with-model", object=chain)
  ```

  ```python LangChain (Python) theme={null}
  from langchain_classic import hub as prompts
  from langchain_core.prompts import ChatPromptTemplate
  from langchain_openai import ChatOpenAI

  model = ChatOpenAI(model="gpt-4o-mini")
  prompt = ChatPromptTemplate.from_template("tell me a joke about {topic}")
  chain = prompt | model
  url = prompts.push("joke-generator-with-model", chain)
  # url is a link to the prompt in the UI
  print(url)
  ```

  ```typescript TypeScript theme={null}
  import * as hub from "langchain/hub";
  import { ChatPromptTemplate } from "@langchain/core/prompts";
  import { ChatOpenAI } from "@langchain/openai";

  const model = new ChatOpenAI({ model: "gpt-4o-mini" });
  const prompt = ChatPromptTemplate.fromTemplate("tell me a joke about {topic}");
  const chain = prompt.pipe(model);
  await hub.push("joke-generator-with-model", {
    object: chain,
  });
  ```
</CodeGroup>

## Pull a prompt

To pull a prompt, you can use the `pull prompt` method, which returns a the prompt as a langchain `PromptTemplate`.

To pull a **private prompt** you do not need to specify the owner handle (though you can, if you have one set).

To pull a **public prompt** from the LangChain Hub, you need to specify the handle of the prompt's author.

<CodeGroup>
  ```python Python theme={null}
  from langsmith import Client
  from langchain_openai import ChatOpenAI

  client = Client()
  prompt = client.pull_prompt("joke-generator")
  model = ChatOpenAI(model="gpt-4o-mini")
  chain = prompt | model
  chain.invoke({"topic": "cats"})
  ```

  ```python LangChain (Python) theme={null}
  from langchain_classic import hub as prompts
  from langchain_openai import ChatOpenAI

  prompt = prompts.pull("joke-generator")
  model = ChatOpenAI(model="gpt-4o-mini")
  chain = prompt | model
  chain.invoke({"topic": "cats"})
  ```

  ```typescript TypeScript theme={null}
  import * as hub from "langchain/hub";
  import { ChatOpenAI } from "@langchain/openai";

  const prompt = await hub.pull("joke-generator");
  const model = new ChatOpenAI({ model: "gpt-4o-mini" });
  const chain = prompt.pipe(model);
  await chain.invoke({"topic": "cats"});
  ```
</CodeGroup>

Similar to pushing a prompt, you can also pull a prompt as a RunnableSequence of a prompt and a model. Just specify include\_model when pulling the prompt. If the stored prompt includes a model, it will be returned as a RunnableSequence. Make sure you have the proper environment variables set for the model you are using.

<CodeGroup>
  ```python Python theme={null}
  from langsmith import Client

  client = Client()
  chain = client.pull_prompt("joke-generator-with-model", include_model=True)
  chain.invoke({"topic": "cats"})
  ```

  ```python LangChain (Python) theme={null}
  from langchain_classic import hub as prompts

  chain = prompts.pull("joke-generator-with-model", include_model=True)
  chain.invoke({"topic": "cats"})
  ```

  ```typescript TypeScript theme={null}
  import * as hub from "langchain/hub";
  import { Runnable } from "@langchain/core/runnables";

  const chain = await hub.pull<Runnable>("joke-generator-with-model", { includeModel: true });
  await chain.invoke({"topic": "cats"});
  ```
</CodeGroup>

When pulling a prompt, you can also specify a specific commit hash or [commit tag](/langsmith/manage-prompts#commit-tags) to pull a specific version of the prompt.

<CodeGroup>
  ```python Python theme={null}
  prompt = client.pull_prompt("joke-generator:12344e88")
  ```

  ```python LangChain (Python) theme={null}
  prompt = prompts.pull("joke-generator:12344e88")
  ```

  ```typescript TypeScript theme={null}
  const prompt = await hub.pull("joke-generator:12344e88")
  ```
</CodeGroup>

To pull a public prompt from the LangChain Hub, you need to specify the handle of the prompt's author.

<CodeGroup>
  ```python Python theme={null}
  prompt = client.pull_prompt("efriis/my-first-prompt")
  ```

  ```python LangChain (Python) theme={null}
  prompt = prompts.pull("efriis/my-first-prompt")
  ```

  ```typescript TypeScript theme={null}
  const prompt = await hub.pull("efriis/my-first-prompt")
  ```
</CodeGroup>

<Note>
  For pulling prompts, if you are using Node.js or an environment that supports dynamic imports, we recommend using the `langchain/hub/node` entrypoint, as it handles deserialization of models associated with your prompt configuration automatically.

  If you are in a non-Node environment, "includeModel" is not supported for non-OpenAI models and you should use the base `langchain/hub` entrypoint.
</Note>

## Prompt caching

<Note>
  We recommend enabling prompt caching in production environments to reduce latency and API calls. The cache uses a stale-while-revalidate pattern, ensuring your application always gets a fast response while keeping prompts up-to-date in the background.
</Note>

The LangSmith SDK includes built-in in-memory caching for prompts. When enabled, pulled prompts are cached in memory, reducing latency and API calls for frequently used prompts. The cache persists for the lifetime of the client instance.

**Requirements:**

* Python SDK: `langsmith >= 0.6.1`
* TypeScript SDK: `langsmith >= 0.4.5`

### Default behavior

Caching is **disabled by default**. When enabled, the default settings are:

| Setting                    | Default       | Description                                     |
| -------------------------- | ------------- | ----------------------------------------------- |
| `max_size`                 | 100           | Maximum number of prompts to cache              |
| `ttl_seconds`              | 3600 (1 hour) | Time before a cached prompt is considered stale |
| `refresh_interval_seconds` | 60            | How often to check for stale prompts            |

### Enabling the cache

Pass `cache=True` to enable caching with default settings, or pass a `Cache` instance for custom configuration:

<CodeGroup>
  ```python Python theme={null}
  from langsmith import Client, Cache

  # Enable with default settings
  client = Client(cache=True)

  # Or configure custom cache settings
  my_cache = Cache(
      max_size=100,
      ttl_seconds=3600,
  )
  client = Client(cache=my_cache)

  # First pull - fetches from API and caches
  prompt = client.pull_prompt("joke-generator")

  # Subsequent pulls - returns cached version instantly
  prompt = client.pull_prompt("joke-generator")

  # Check cache metrics
  print(f"Cache hits: {client.cache.metrics.hits}")
  print(f"Cache misses: {client.cache.metrics.misses}")
  print(f"Hit rate: {client.cache.metrics.hit_rate:.1%}")
  ```

  ```typescript TypeScript theme={null}
  import { Client, Cache } from "langsmith";

  // Enable with default settings
  const client = new Client({ cache: true });

  // Or configure custom cache settings
  const myCache = new Cache({
    maxSize: 100,
    ttlSeconds: 3600,
  });
  const client2 = new Client({ cache: myCache });

  // First pull - fetches from API and caches
  const prompt = await client.pullPrompt("joke-generator");

  // Subsequent pulls - returns cached version instantly
  const prompt2 = await client.pullPrompt("joke-generator");

  // Check cache metrics
  console.log(`Cache hits: ${client.cache?.metrics.hits}`);
  console.log(`Cache misses: ${client.cache?.metrics.misses}`);
  console.log(`Hit rate: ${(client.cache?.hitRate ?? 0 * 100).toFixed(1)}%`);
  ```
</CodeGroup>

### Skipping the cache

To bypass the cache and fetch a fresh prompt from the API, use the `skip_cache` parameter:

<CodeGroup>
  ```python Python theme={null}
  # Force a fresh fetch, ignoring any cached version
  prompt = client.pull_prompt("joke-generator", skip_cache=True)
  ```

  ```typescript TypeScript theme={null}
  // Force a fresh fetch, ignoring any cached version
  const prompt = await client.pullPrompt("joke-generator", { skipCache: true });
  ```
</CodeGroup>

This is useful when you need to ensure you have the latest version of a prompt, such as after making changes in the LangSmith UI.

### Offline mode

For environments with limited or no network connectivity, you can pre-populate the cache and use it offline. Set `ttl_seconds` to `None` (Python) or `null` (TypeScript) to prevent cache entries from expiring.

**Step 1: Export your prompts to a cache file (while online)**

<CodeGroup>
  ```python Python theme={null}
  from langsmith import Client, Cache

  # Create client with caching enabled
  client = Client(cache=True)

  # Pull the prompts you need
  client.pull_prompt("prompt-1")
  client.pull_prompt("prompt-2")
  client.pull_prompt("prompt-3")

  # Export cache to a file
  client.cache.dump("prompts_cache.json")
  client.cleanup()
  ```

  ```typescript TypeScript theme={null}
  import { Client } from "langsmith";

  // Create client with caching enabled
  const client = new Client({ cache: true });

  // Pull the prompts you need
  await client.pullPrompt("prompt-1");
  await client.pullPrompt("prompt-2");
  await client.pullPrompt("prompt-3");

  // Export cache to a file
  client.cache?.dump("prompts_cache.json");
  client.cleanup();
  ```
</CodeGroup>

**Step 2: Load the cache file in your offline environment**

<CodeGroup>
  ```python Python theme={null}
  from langsmith import Client, Cache

  # Create cache with infinite TTL (never expire)
  my_cache = Cache(ttl_seconds=None)
  my_cache.load("prompts_cache.json")

  client = Client(cache=my_cache)

  # Uses cached version without any API calls
  prompt = client.pull_prompt("prompt-1")
  ```

  ```typescript TypeScript theme={null}
  import { Client, Cache } from "langsmith";

  // Create cache with infinite TTL (never expire)
  const myCache = new Cache({ ttlSeconds: null });
  myCache.load("prompts_cache.json");

  const client = new Client({ cache: myCache });

  // Uses cached version without any API calls
  const prompt = await client.pullPrompt("prompt-1");
  ```
</CodeGroup>

### Cleanup

When you're done using the client, call `cleanup()` to stop the background refresh task:

<CodeGroup>
  ```python Python theme={null}
  client.cleanup()
  ```

  ```typescript TypeScript theme={null}
  client.cleanup();
  ```
</CodeGroup>

## Use a prompt without LangChain

If you want to store your prompts in LangSmith but use them directly with a model provider's API, you can use our conversion methods. These convert your prompt into the payload required for the OpenAI or Anthropic API.

These conversion methods rely on logic from within LangChain integration packages, and you will need to install the appropriate package as a dependency in addition to your official SDK of choice. Here are some examples:

### OpenAI

<CodeGroup>
  ```bash Python theme={null}
  pip install -U langchain_openai
  ```

  ```bash TypeScript theme={null}
  yarn add @langchain/openai @langchain/core // @langchain/openai version >= 0.3.2
  ```
</CodeGroup>

<CodeGroup>
  ```python Python theme={null}
  from openai import OpenAI
  from langsmith.client import Client, convert_prompt_to_openai_format

  # langsmith client
  client = Client()
  # openai client
  oai_client = OpenAI()

  # pull prompt and invoke to populate the variables
  prompt = client.pull_prompt("joke-generator")
  prompt_value = prompt.invoke({"topic": "cats"})
  openai_payload = convert_prompt_to_openai_format(prompt_value)
  openai_response = oai_client.chat.completions.create(**openai_payload)
  ```

  ```typescript TypeScript theme={null}
  import * as hub from "langchain/hub";
  import { convertPromptToOpenAI } from "@langchain/openai";
  import OpenAI from "openai";

  const prompt = await hub.pull("jacob/joke-generator");
  const formattedPrompt = await prompt.invoke({
    topic: "cats",
  });
  const { messages } = convertPromptToOpenAI(formattedPrompt);

  const openAIClient = new OpenAI();
  const openAIResponse = await openAIClient.chat.completions.create({
    model: "gpt-4o-mini",
    messages,
  });
  ```
</CodeGroup>

### Anthropic

<CodeGroup>
  ```bash Python theme={null}
  pip install -U langchain_anthropic
  ```

  ```bash TypeScript theme={null}
  yarn add @langchain/anthropic @langchain/core // @langchain/anthropic version >= 0.3.3
  ```
</CodeGroup>

<CodeGroup>
  ```python Python theme={null}
  from anthropic import Anthropic
  from langsmith.client import Client, convert_prompt_to_anthropic_format

  # langsmith client
  client = Client()
  # anthropic client
  anthropic_client = Anthropic()

  # pull prompt and invoke to populate the variables
  prompt = client.pull_prompt("joke-generator")
  prompt_value = prompt.invoke({"topic": "cats"})
  anthropic_payload = convert_prompt_to_anthropic_format(prompt_value)
  anthropic_response = anthropic_client.messages.create(**anthropic_payload)
  ```

  ```typescript TypeScript theme={null}
  import * as hub from "langchain/hub";
  import { convertPromptToAnthropic } from "@langchain/anthropic";
  import Anthropic from "@anthropic-ai/sdk";

  const prompt = await hub.pull("jacob/joke-generator");
  const formattedPrompt = await prompt.invoke({
    topic: "cats",
  });
  const { messages, system } = convertPromptToAnthropic(formattedPrompt);

  const anthropicClient = new Anthropic();
  const anthropicResponse = await anthropicClient.messages.create({
    model: "claude-haiku-4-5-20251001",
    system,
    messages,
    max_tokens: 1024,
    stream: false,
  });
  ```
</CodeGroup>

## List, delete, and like prompts

You can also list, delete, and like/unlike prompts using the `list prompts`, `delete prompt`, `like prompt` and `unlike prompt` methods. See the [LangSmith SDK client](https://github.com/langchain-ai/langsmith-sdk) for extensive documentation on these methods.

<CodeGroup>
  ```python Python theme={null}
  # List all prompts in my workspace
  prompts = client.list_prompts()

  # List my private prompts that include "joke"
  prompts = client.list_prompts(query="joke", is_public=False)

  # Delete a prompt
  client.delete_prompt("joke-generator")

  # Like a prompt
  client.like_prompt("efriis/my-first-prompt")

  # Unlike a prompt
  client.unlike_prompt("efriis/my-first-prompt")
  ```

  ```typescript TypeScript theme={null}
  // List all prompts in my workspace
  import Client from "langsmith";

  const client = new Client({ apiKey: "lsv2_..." });
  const prompts = client.listPrompts();

  for await (const prompt of prompts) {
    console.log(prompt);
  }

  // List my private prompts that include "joke"
  const private_joke_prompts = client.listPrompts({ query: "joke", isPublic: false});

  // Delete a prompt
  client.deletePrompt("joke-generator");

  // Like a prompt
  client.likePrompt("efriis/my-first-prompt");

  // Unlike a prompt
  client.unlikePrompt("efriis/my-first-prompt");
  ```
</CodeGroup>

***

<Callout icon="pen-to-square" iconType="regular">
  [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/langsmith/manage-prompts-programmatically.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
</Callout>

<Tip icon="terminal" iconType="regular">
  [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
</Tip>