Core Concepts

Basic Usage

from langchain.llms import OpenAI
from langchain.chains import LLMChain
from langchain.prompts import PromptTemplate

# Simple LLM call
llm = OpenAI(temperature=0.7)
response = llm("What is the capital of France?")

# Chain with prompt template
prompt = PromptTemplate(
    input_variables=["product"],
    template="What is a good name for a company that makes {product}?"
)
chain = LLMChain(llm=llm, prompt=prompt)
result = chain.run("colorful socks")

# Agent with tools
from langchain.agents import load_tools, initialize_agent

tools = load_tools(["serpapi", "llm-math"], llm=llm)
agent = initialize_agent(tools, llm, agent="zero-shot-react-description")
agent.run("What is the weather in NYC?")

Common Chains

Best Practices

• Use prompt templates for consistency
• Add memory for conversational apps
• Use vector stores for document QA
• Implement error handling for API calls