以编程方式管理提示

您可以使用 LangSmith Python 和 TypeScript SDK 以编程方式管理提示。

注意

以前此功能存在于 langchainhub 包中，现已弃用。未来所有功能都将存在于 langsmith 包中。

安装包

在 Python 中，您可以直接使用 LangSmith SDK（推荐，功能完整），或者通过 LangChain 包使用（仅限于推送和拉取提示）。

在 TypeScript 中，您必须使用 LangChain npm 包来拉取提示（它也允许推送）。对于所有其他功能，请使用 LangSmith 包。

Python

pip install -U langsmith 
# version >= 0.1.99

LangChain (Python)

pip install -U langchain langsmith 
# langsmith version >= 0.1.99 and langchain >= 0.2.13

TypeScript

yarn add langsmith langchain 
// langsmith version >= 0.1.99 and langchain version >= 0.2.14

配置环境变量

如果您已经将 LANGSMITH_API_KEY 设置为 LangSmith 中当前工作区的 API 密钥，则可以跳过此步骤。

否则，通过导航到 LangSmith 中的 设置 > API 密钥 > 创建 API 密钥 获取您工作区的 API 密钥。

设置您的环境变量。

export LANGSMITH_API_KEY="lsv2_..."

术语

我们所说的“提示”以前被称为“仓库”，因此代码中对“仓库”的任何引用都指的是提示。

推送提示

要创建新提示或更新现有提示，您可以使用 push prompt 方法。

Python

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)

LangChain (Python)

from langchain 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

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);

您还可以将提示作为提示和模型的 RunnableSequence 推送。这对于存储您希望与此提示一起使用的模型配置很有用。提供商必须受 LangSmith Playground 支持。（在此处查看设置：支持的提供商）

Python

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)

LangChain (Python)

from langchain 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

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
});

拉取提示

要拉取提示，您可以使用 pull prompt 方法，它将提示作为 langchain PromptTemplate 返回。

要拉取私有提示，您无需指定所有者句柄（尽管如果您已设置，也可以指定）。

要从 LangChain Hub 拉取公共提示，您需要指定提示作者的句柄。

Python

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"})

LangChain (Python)

from langchain 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

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"});

与推送提示类似，您还可以将提示作为提示和模型的 RunnableSequence 拉取。只需在拉取提示时指定 include_model 即可。如果存储的提示包含模型，它将作为 RunnableSequence 返回。请确保您为正在使用的模型设置了正确的环境变量。

Python

from langsmith import Client

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

LangChain (Python)

from langchain import hub as prompts
chain = prompts.pull("joke-generator-with-model", include_model=True)
chain.invoke({"topic": "cats"})

TypeScript

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"});

拉取提示时，您还可以指定特定的提交哈希或提示标签来拉取特定版本的提示。

Python

prompt = client.pull_prompt("joke-generator:12344e88")

LangChain (Python)

prompt = prompts.pull("joke-generator:12344e88")

TypeScript

const prompt = await hub.pull("joke-generator:12344e88")

要从 LangChain Hub 拉取公共提示，您需要指定提示作者的句柄。

Python

prompt = client.pull_prompt("efriis/my-first-prompt")

LangChain (Python)

prompt = prompts.pull("efriis/my-first-prompt")

TypeScript

const prompt = await hub.pull("efriis/my-first-prompt")

JavaScript 用户重要提示

对于拉取提示，如果您使用的是 Node.js 或支持动态导入的环境，我们建议使用 langchain/hub/node 入口点，因为它会自动处理与您的提示配置关联的模型的反序列化。

如果您处于非 Node 环境中，则“includeModel”不支持非 OpenAI 模型，您应该使用基本的 langchain/hub 入口点。

不使用 LangChain 的提示

如果您想将提示存储在 LangSmith 中，但直接与模型提供商的 API 一起使用它们，您可以使用我们的转换方法。这些方法将您的提示转换为 OpenAI 或 Anthropic API 所需的负载。

这些转换方法依赖于 LangChain 集成包中的逻辑，除了您选择的官方 SDK 之外，您还需要安装相应的包作为依赖项。以下是一些示例：

OpenAI

Python

pip install -U langchain_openai

TypeScript

yarn add @langchain/openai @langchain/core 
// @langchain/openai version >= 0.3.2

Python

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

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,
});

Anthropic

Python

pip install -U langchain_anthropic

TypeScript

yarn add @langchain/anthropic @langchain/core 
// @langchain/anthropic version >= 0.3.3

Python

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

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-3-haiku-20240307",
system,
messages,
max_tokens: 1024,
stream: false,
});

列出、删除和点赞提示

您还可以使用 list prompts、delete prompt、like prompt 和 unlike prompt 方法列出、删除和点赞/取消点赞提示。有关这些方法的详细文档，请参阅 LangSmith SDK 客户端。

Python

# 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

// 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");