LangChain Quickstart: Build an AI App in 10 Minutes

LangChain has a big reputation, but every time I look at tutorials, I get overwhelmed by all the concepts—Chain, Agent, Tool, Memory, Retriever... How are they actually used? Can't we just get something running first before diving into all that?

💡 What You Will Learn

LangChain has a big reputation, but every time I look at tutorials, I get overwhelmed by all the concepts—Chain, Agent, Tool, Memory, Retriever... How are they actually used? Can't we just get somethi

pip install langchain langchain-openai

from langchain_openai import ChatOpenAI
from langchain.schema import HumanMessage

llm = ChatOpenAI(model="gpt-4o")
response = llm.invoke([HumanMessage(content="LangChain")])
print(response.content)

from langchain import LLMChain
from langchain.prompts import PromptTemplate

prompt = PromptTemplate(
    input_variables=["topic"],
    template="{topic}"
)

chain = LLMChain(llm=llm, prompt=prompt)
print(chain.run(""))

from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationChain

memory = ConversationBufferMemory()
conversation = ConversationChain(llm=llm, memory=memory)

print(conversation.predict(input=""))
print(conversation.predict(input=""))  # 

from langchain_community.vectorstores import Chroma
from langchain_openai import OpenAIEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.chains import RetrievalQA

# Load documents
text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=50)
texts = text_splitter.split_text(open(".txt").read())

# Store
docsearch = Chroma.from_texts(texts, OpenAIEmbeddings())

# RAG
qa = RetrievalQA.from_chain_type(llm=llm, retriever=docsearch.as_retriever())
print(qa.invoke(""))

from langchain.agents import Tool, initialize_agent
from langchain.tools import tool

@tool
def calculate(expression: str) -> str:
    """"""
    return str(eval(expression))

tools = [Tool(name="", func=calculate, description="")]

agent = initialize_agent(tools, llm, agent="zero-shot-react-description")
print(agent.run("1234567890"))