Movatterモバイル変換


[0]ホーム

URL:


Skip to main content
OurBuilding Ambient Agents with LangGraph course is now available on LangChain Academy!
Open In ColabOpen on GitHub

Build a simple LLM application with chat models and prompt templates

In this quickstart we'll show you how to build a simple LLM application with LangChain. This application will translate text from English into another language. This is a relatively simple LLM application - it's just a single LLM call plus some prompting. Still, this is a great way to get started with LangChain - a lot of features can be built with just some prompting and an LLM call!

After reading this tutorial, you'll have a high level overview of:

Let's dive in!

Setup

Jupyter Notebook

This and other tutorials are perhaps most conveniently run in aJupyter notebooks. Going through guides in an interactive environment is a great way to better understand them. Seehere for instructions on how to install.

Installation

To install LangChain run:

  • Pip
  • Conda
pip install langchain

For more details, see ourInstallation guide.

LangSmith

Many of the applications you build with LangChain will contain multiple steps with multiple invocations of LLM calls.As these applications get more and more complex, it becomes crucial to be able to inspect what exactly is going on inside your chain or agent.The best way to do this is withLangSmith.

After you sign up at the link above, make sure to set your environment variables to start logging traces:

export LANGSMITH_TRACING="true"
export LANGSMITH_API_KEY="..."
export LANGSMITH_PROJECT="default" # or any other project name

Or, if in a notebook, you can set them with:

import getpass
import os

try:
# load environment variables from .env file (requires `python-dotenv`)
from dotenvimport load_dotenv

load_dotenv()
except ImportError:
pass

os.environ["LANGSMITH_TRACING"]="true"
if"LANGSMITH_API_KEY"notin os.environ:
os.environ["LANGSMITH_API_KEY"]= getpass.getpass(
prompt="Enter your LangSmith API key (optional): "
)
if"LANGSMITH_PROJECT"notin os.environ:
os.environ["LANGSMITH_PROJECT"]= getpass.getpass(
prompt='Enter your LangSmith Project Name (default = "default"): '
)
ifnot os.environ.get("LANGSMITH_PROJECT"):
os.environ["LANGSMITH_PROJECT"]="default"

Using Language Models

First up, let's learn how to use a language model by itself. LangChain supports many different language models that you can use interchangeably. For details on getting started with a specific model, refer tosupported integrations.

pip install -qU "langchain[google-genai]"
import getpass
import os

ifnot os.environ.get("GOOGLE_API_KEY"):
os.environ["GOOGLE_API_KEY"]= getpass.getpass("Enter API key for Google Gemini: ")

from langchain.chat_modelsimport init_chat_model

model= init_chat_model("gemini-2.0-flash", model_provider="google_genai")

Let's first use the model directly.ChatModels are instances of LangChainRunnables, which means they expose a standard interface for interacting with them. To simply call the model, we can pass in a list ofmessages to the.invoke method.

from langchain_core.messagesimport HumanMessage, SystemMessage

messages=[
SystemMessage("Translate the following from English into Italian"),
HumanMessage("hi!"),
]

model.invoke(messages)
AIMessage(content='Ciao!', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 3, 'prompt_tokens': 20, 'total_tokens': 23, 'completion_tokens_details': {'accepted_prediction_tokens': 0, 'audio_tokens': 0, 'reasoning_tokens': 0, 'rejected_prediction_tokens': 0}, 'prompt_tokens_details': {'audio_tokens': 0, 'cached_tokens': 0}}, 'model_name': 'gpt-4o-mini-2024-07-18', 'system_fingerprint': 'fp_0705bf87c0', 'finish_reason': 'stop', 'logprobs': None}, id='run-32654a56-627c-40e1-a141-ad9350bbfd3e-0', usage_metadata={'input_tokens': 20, 'output_tokens': 3, 'total_tokens': 23, 'input_token_details': {'audio': 0, 'cache_read': 0}, 'output_token_details': {'audio': 0, 'reasoning': 0}})
tip

If we've enabled LangSmith, we can see that this run is logged to LangSmith, and can see theLangSmith trace. The LangSmith trace reportstoken usage information, latency,standard model parameters (such as temperature), and other information.

Note that ChatModels receivemessage objects as input and generate message objects as output. In addition to text content, message objects convey conversationalroles and hold important data, such astool calls and token usage counts.

LangChain also supports chat model inputs via strings orOpenAI format. The following are equivalent:

model.invoke("Hello")

model.invoke([{"role":"user","content":"Hello"}])

model.invoke([HumanMessage("Hello")])

Streaming

Because chat models areRunnables, they expose a standard interface that includes async and streaming modes of invocation. This allows us to stream individual tokens from a chat model:

for tokenin model.stream(messages):
print(token.content, end="|")
|C|iao|!||

You can find more details on streaming chat model outputs inthis guide.

Prompt Templates

Right now we are passing a list of messages directly into the language model. Where does this list of messages come from? Usually, it is constructed from a combination of user input and application logic. This application logic usually takes the raw user input and transforms it into a list of messages ready to pass to the language model. Common transformations include adding a system message or formatting a template with the user input.

Prompt templates are a concept in LangChain designed to assist with this transformation. They take in raw user input and return data (a prompt) that is ready to pass into a language model.

Let's create a prompt template here. It will take in two user variables:

  • language: The language to translate text into
  • text: The text to translate
from langchain_core.promptsimport ChatPromptTemplate

system_template="Translate the following from English into {language}"

prompt_template= ChatPromptTemplate.from_messages(
[("system", system_template),("user","{text}")]
)
API Reference:ChatPromptTemplate

Note thatChatPromptTemplate supports multiplemessage roles in a single template. We format thelanguage parameter into the system message, and the usertext into a user message.

The input to this prompt template is a dictionary. We can play around with this prompt template by itself to see what it does by itself

prompt= prompt_template.invoke({"language":"Italian","text":"hi!"})

prompt
ChatPromptValue(messages=[SystemMessage(content='Translate the following from English into Italian', additional_kwargs={}, response_metadata={}), HumanMessage(content='hi!', additional_kwargs={}, response_metadata={})])

We can see that it returns aChatPromptValue that consists of two messages. If we want to access the messages directly we do:

prompt.to_messages()
[SystemMessage(content='Translate the following from English into Italian', additional_kwargs={}, response_metadata={}),
HumanMessage(content='hi!', additional_kwargs={}, response_metadata={})]

Finally, we can invoke the chat model on the formatted prompt:

response= model.invoke(prompt)
print(response.content)
Ciao!
tip

Messagecontent can contain both text andcontent blocks with additional structure. Seethis guide for more information.

If we take a look at theLangSmith trace, we can see exactly what prompt the chat model receives, along withtoken usage information, latency,standard model parameters (such as temperature), and other information.

Conclusion

That's it! In this tutorial you've learned how to create your first simple LLM application. You've learned how to work with language models, how to create a prompt template, and how to get great observability into applications you create with LangSmith.

This just scratches the surface of what you will want to learn to become a proficient AI Engineer. Luckily - we've got a lot of other resources!

For further reading on the core concepts of LangChain, we've got detailedConceptual Guides.

If you have more specific questions on these concepts, check out the following sections of the how-to guides:

And the LangSmith docs:


[8]ページ先頭

©2009-2025 Movatter.jp