LangChain

Browse articles on LangChain — tutorials, guides, and in-depth comparisons.

41 articles 3 comparisons → Browse all topics

LangChain is the most widely used Python framework for building LLM-powered applications. Its modular abstractions — chains, retrievers, agents, and memory — let you compose complex AI workflows without reinventing common patterns.

LangChain Ecosystem

Tool	Role	When to use
LangChain	Core framework, chains, agents	Connecting LLMs to data and tools
LangGraph	Stateful multi-agent workflows	Complex agent orchestration
LangSmith	Observability, eval, monitoring	Debugging and testing in production
LlamaIndex	Data indexing, RAG patterns	Document-heavy applications
LangServe	Serve chains as REST API	Deploying chains as microservices

Quick Start — RAG Pipeline

from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_community.vectorstores import PGVector
from langchain.chains import RetrievalQA

# Embedding model
embeddings = OpenAIEmbeddings(model="text-embedding-3-small")

# Vector store (PostgreSQL + pgvector)
vectorstore = PGVector(
    connection_string="postgresql://user:pass@localhost/db",
    embedding_function=embeddings,
    collection_name="docs",
)

# RAG chain
qa_chain = RetrievalQA.from_chain_type(
    llm=ChatOpenAI(model="gpt-4o"),
    retriever=vectorstore.as_retriever(search_kwargs={"k": 5}),
)

answer = qa_chain.invoke("What is LangGraph used for?")

LCEL — LangChain Expression Language

from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI
from langchain_core.output_parsers import StrOutputParser

# Compose chains with | operator
chain = (
    ChatPromptTemplate.from_template("Summarize: {text}")
    | ChatOpenAI(model="gpt-4o")
    | StrOutputParser()
)

result = chain.invoke({"text": "Your document here..."})

Learning Path

LCEL basics — prompt templates, model invocation, output parsers
Retrieval chains — document loaders, text splitters, vector stores
Agents — tool definitions, ReAct agent, tool calling
LangGraph — stateful workflows, human-in-the-loop, multi-agent
LangSmith — tracing, evaluation datasets, CI/CD testing
Production — streaming, async, caching, error handling

Showing 31–41 of 41 articles · Page 2 of 2