skills.rest
Orchestra-Research
Orchestra-ResearchOFFICIAL
Explore all skills by this author →
GitHub

langchain

Build LLM applications with agents, chains, RAG pipelines, and vector store retrieval.

13.0k|930|Updated Nov 3, 2025
Search Tags:#react#langchain#rag#tool calling#agents#vector stores#llm applications
One-click install
npx skills add https://github.com/Orchestra-Research/AI-research-SKILLs --skill langchain-orchestra-research
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: langchain
Source: https://github.com/Orchestra-Research/AI-research-SKILLs/tree/main/14-agents/langchain
Command: npx skills add https://github.com/Orchestra-Research/AI-research-SKILLs --skill langchain-orchestra-research

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 from scratch. This Skill provides the LangChain framework patterns to assemble agents, chains, and RAG systems with swappable providers like OpenAI, Anthropic, and Google. ## Core Features & Use Cases - ReAct Agents with Tool Calling: Create agents that reason and invoke custom tools, with parallel execution, streaming, and error handling in under 10 lines of code. - RAG Pipelines: Load documents, split text, embed into vector stores (Chroma, Pinecone, FAISS), and build QA chains with source citations and conversational memory. - Provider Abstraction & Observability: Swap between OpenAI, Anthropic, and Google models with identical code, and trace every run with LangSmith. - Use Case: Build a documentation chatbot that loads your product docs into a Chroma vector store, retrieves relevant chunks per question, and answers with cited sources while remembering conversation history. ## Quick Start Use the langchain skill to create a ReAct agent with a calculator and web search tool powered by Claude.

Frequently Asked Questions about langchain

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

FAQPage Schema
How do I create a ReAct agent with tool calling in LangChain?▼

Use create_agent with a chat model, a list of tool functions, and a system prompt. LangChain handles the reasoning loop, tool invocation, and parallel execution of independent tool calls automatically.

How to build a RAG pipeline with LangChain and Chroma?▼

Load documents with a document loader, split them with RecursiveCharacterTextSplitter, embed into a Chroma vector store, then connect a retriever to a RetrievalQA chain. The chain returns answers with source documents for citation.

LangChain vs LangGraph: which should I use for agents?▼

LangChain suits quick agents and RAG with high-level abstractions and minimal code. LangGraph fits complex stateful workflows with cycles, fine-grained control, and multi-agent systems requiring full orchestration.

Does LangChain support multiple LLM providers like OpenAI and Anthropic?▼

Yes, LangChain abstracts providers through packages like langchain-openai, langchain-anthropic, and langchain-google-genai. You can swap models by changing the chat model class while keeping the rest of your code unchanged.

Why does my LangChain agent fail or loop indefinitely?▼

Common causes include vague tool descriptions, too many tools, and missing iteration limits. Set max_iterations on AgentExecutor, add error handling inside tools, and enable verbose mode or LangSmith tracing to inspect reasoning steps.

What chunk size should I use for LangChain text splitting?▼

Use 512-1024 tokens for general Q&A with 10-20% overlap between chunks. RecursiveCharacterTextSplitter with separators for paragraphs, lines, and spaces is recommended for general text.

Related Skills

Explore More Software Engineering Skills→
sathishssj3sathishssj3
2

embedding-pipeline-builder

Builds document embedding pipelines with chunking, vector indexing, and semantic retrieval.

Community
Advanced
KappTech88KappTech88

langsmith-observability

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

Community
Advanced
davila7davila7
30.5k

langsmith-observability

Trace, evaluate, and monitor LLM applications using the LangSmith Python SDK.

Community
Advanced
tivon-xtivon-x

langgraph-fundamentals

Develop agentic workflows with LangGraph using state, nodes, and edges.

Community
Intermediate