skills.rest
listentomi
listentomiCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

langchain

Build LLM applications with agents, chains, RAG pipelines, and multi-provider model support.

Updated Aug 28, 2026
Search Tags:#langchain#llm#rag#tool calling#agents#chatbots#vector stores
One-click install
npx skills add https://github.com/listentomi/Orcajack --skill langchain-listentomi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: langchain
Source: https://github.com/listentomi/Orcajack/tree/main/skills/science/agents-langchain
Command: npx skills add https://github.com/listentomi/Orcajack --skill langchain-listentomi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires langchain, langchain-core, langchain-openai, langchain-anthropic, and includes references (resource) components.

What problem does it solve? Building LLM-powered applications requires wiring together model providers, tools, memory, and retrieval pipelines, which involves significant boilerplate and provider-specific code. This Skill provides guidance and code patterns for using LangChain to assemble agents, chains, and RAG systems with swappable LLM providers. ## Core Features & Use Cases - Agent Creation: Build ReAct and tool-calling agents with create_agent, custom tools, parallel tool execution, and streaming output. - RAG Pipelines: Load documents from web, PDF, GitHub, or CSV, split them into chunks, embed them into vector stores like Chroma, Pinecone, or FAISS, and run retrieval QA chains with conversation memory. - Provider Flexibility: Swap between OpenAI, Anthropic, and Google models with a single line change, plus structured output via Pydantic schemas and LangSmith tracing for observability. - Use Case: Build a chatbot that answers questions about your documentation by loading web pages, indexing them in Chroma, and running a conversational retrieval chain that remembers prior turns. ## Quick Start Ask the AI to create a LangChain agent with a weather tool and a web search tool using the Anthropic Claude model, then run it on a sample question.

Frequently Asked Questions about langchain

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a LangChain agent with tools?▼

Use create_agent with a chat model, a list of tool functions, and a system prompt. Each tool is a Python function with a docstring describing its purpose, and the agent decides when to call them using the ReAct reasoning pattern.

How to build a RAG pipeline with LangChain?▼

Load documents with a document loader, split them with RecursiveCharacterTextSplitter, embed them into a vector store like Chroma, then connect a retriever to a RetrievalQA chain. The chain fetches relevant chunks and passes them to the LLM for grounded answers.

LangChain vs LangGraph: which should I use?▼

LangChain suits quick agents and RAG with high-level abstractions and under ten lines of setup code. LangGraph fits complex stateful workflows, cyclic graphs, multi-agent systems, and cases needing fine-grained control or human-in-the-loop steps.

Can I switch LLM providers in LangChain?▼

Yes, LangChain provides a unified chat model interface across providers. Swap ChatOpenAI, ChatAnthropic, or ChatGoogleGenerativeAI by changing one initialization line while keeping the rest of your chains and agents unchanged.

Does LangChain support conversation memory?▼

Yes, ConversationBufferMemory stores chat history and can be attached to a ConversationChain or ConversationalRetrievalChain. This lets the application reference earlier turns, such as remembering a user's name across messages.

Why is my LangChain agent slow?▼

Agent latency comes from ReAct reasoning loops, typically three to five seconds per tool call, plus LLM response time. Enable streaming for better perceived performance and use LangSmith tracing to identify slow steps in the execution chain.

Related Skills

Explore More Software Engineering Skills→
myaiartist360-makermyaiartist360-maker

summarize

Summarize web content, local files, and video transcripts via LLM extraction.

Community
Intermediate
KappTech88KappTech88

langsmith-observability

Diagnose LLM behavior across tracing, evaluation, and monitoring workflows in LangSmith.

Community
Advanced
yonatangrossyonatangross
217

testing-llm

Mock LLM responses and evaluate outputs with DeepEval and RAGAS.

Community
Advanced
qcmuuqcmuu

haystack

Build RAG search pipelines with retrievers, rerankers, and generators.

Community
Intermediate