LangChain 1 cheatsheet

LangChain 1: Prompts and chains

3 common LangChain 1 tasks.

Create a prompt template

Build a reusable prompt with placeholders.

from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_messages([
    ("system", "Translate the user's text into {language}."),
    ("human", "{text}"),
])

Chain a prompt, model and parser

Combine steps with the | operator, then call the chain like any other runnable.

from langchain_core.output_parsers import StrOutputParser

chain = prompt | model | StrOutputParser()
chain.invoke({"language": "French", "text": "Good morning"})

Get structured output

Make the model return data that matches a Pydantic class.

from pydantic import BaseModel

class Movie(BaseModel):
    title: str
    year: int

structured = model.with_structured_output(Movie)
structured.invoke("Tell me about Inception.")