langchain-components

Name: langchain-components
Author: krzysztofsurdy

23installs1forks

How to install langchain-components?

krzysztofsurdy/code-virtuoso/langchain-components

$npx -y skills add krzysztofsurdy/code-virtuoso --skill langchain-components

Installs into the current project.

Summary

Comprehensive reference for the LangChain ecosystem including LangChain, LangGraph, and Deep Agents for Python 3.10+. Use when the user asks to build AI agents, implement RAG pipelines, configure chat models, create tool-calling agents, set up retrieval chains, manage conversatio

Files · 1

View on GitHub

SKILL.md

1	# LangChain Components
2
3	Complete reference for the LangChain ecosystem — models, agents, tools, retrieval, memory, middleware, streaming, multi-agent orchestration, LangGraph workflows, Deep Agents, and provider integrations for Python 3.10+.
4
5	## Component Index
6
7	### Models & Output
8	- Models — Chat models, tool calling, multimodal inputs, caching, rate limiting, custom models [reference](references/models.md)
9	- Messages — Message types (Human, AI, System, Tool), message operations, serialization, OpenAI format conversion [reference](references/messages.md)
10
11	### Agents
12	- Agents — create_agent, tools, structured output, guardrails, human-in-the-loop, context engineering [reference](references/agents.md)
13	- Multi-Agent — Subagents, handoffs, skills, router, custom workflows, pattern selection [reference](references/multi-agent.md)
14
15	### Tools & MCP
16	- Tools — Tool creation (@tool decorator, ToolNode), InjectedState, MCP integration, error handling [reference](references/tools.md)
17
18	### Retrieval & RAG
19	- Retrieval — Document loaders, text splitters, embeddings, vector stores, agentic RAG, semantic search [reference](references/retrieval.md)
20
21	### Memory
22	- Memory — Short-term (checkpointers, message trimming, summarization), long-term (store abstraction, namespaces) [reference](references/memory.md)
23
24	### Middleware & Streaming
25	- Middleware — 16 built-in middleware, custom middleware (decorator, class, wrap-style), execution order [reference](references/middleware.md)
26	- Streaming — Stream modes (updates, messages, custom), token streaming, useStream React hook [reference](references/streaming.md)
27
28	### Runtime & Architecture
29	- Runtime — Dependency injection, context schemas, ToolRuntime, component architecture (5 layers) [reference](references/runtime.md)
30
31	### Testing & Deployment
32	- Testing — Unit testing (GenericFakeChatModel), integration testing (AgentEvals), LangSmith observability [reference](references/testing.md)
33
34	### LangGraph
35	- LangGraph Core — Graph API, Functional API, workflows vs agents, state management, quickstart [reference](references/langgraph-core.md)
36	- LangGraph State — Memory, persistence, durable execution, interrupts, checkpointers [reference](references/langgraph-state.md)
37	- LangGraph Advanced — Subgraphs, time-travel, streaming, Graph API usage, Functional API usage [reference](references/langgraph-advanced.md)
38
39	### Deep Agents
40	- Deep Agents — Harness framework, models, subagents, skills, sandboxes, human-in-the-loop, long-term memory [reference](references/deep-agents.md)
41
42	### Integrations
43	- Integrations — Chat models, document loaders, retrievers, embeddings, vector stores, tools, stores, splitters [reference](references/integrations.md)
44	- Providers — OpenAI, Anthropic, Google, AWS, Ollama setup and configuration [reference](references/providers.md)
45
46	## Quick Patterns
47
48	### Create an Agent with Tools
49
50	```python
51	from langchain.chat_models import init_chat_model
52	from langgraph.prebuilt import create_agent
53
54	model = init_chat_model("anthropic:claude-sonnet-4-20250514")
55
56	def get_weather(city: str) -> str:
57	"""Get weather for a city."""
58	return f"Sunny, 72F in {city}"
59
60	agent = create_agent(model, [get_weather])
61	response = agent.invoke(
62	{"messages": [{"role": "user", "content": "What's the weather in SF?"}]}
63	)
64	```
65
66	### Structured Output
67
68	```python
69	from pydantic import BaseModel
70
71	class SearchQuery(BaseModel):
72	query: str
73	year: int
74
75	structured_model = model.with_structured_output(SearchQuery)
76	result = structured_model.invoke("Who won the World Cup in 2022?")
77	```
78
79	### RAG with Retrieval
80
81	```python
82	from langchain_community.document_loaders import WebBaseLoader
83	from langchain_text_splitters import RecursiveCharacterTextSplitter
84	from langchain_openai import OpenAIEmbeddings
85	from langchain_core.vectorstores import InMemoryVectorStore
86
87	docs = WebBaseLoader("https://example.com").load()
88	chunks = RecursiveCharacterTextSplitter(chunk_size=1000).split_documents(docs)
89	vector_store = InMemoryVectorStore.from_documents(chunks, OpenAIEmbeddings())
90	retriever_tool = vector_store.as_retriever()
91	```
92
93	### Multi-Agent Handoffs
94
95	```python
96	from langgraph.prebuilt import create_agent
97
98	billing_agent = create_agent(model, [lookup_billing], name="billing")
99	tech_agent = create_agent(model, [check_status], name="tech_support")
100	supervis

People who liked this also viewed

6 picks

Type

langchain-components

23installs1forks

View on GitHub

How to install langchain-components?

krzysztofsurdy/code-virtuoso/langchain-components

$npx -y skills add krzysztofsurdy/code-virtuoso --skill langchain-components

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# LangChain Components
2
3	Complete reference for the LangChain ecosystem — models, agents, tools, retrieval, memory, middleware, streaming, multi-agent orchestration, LangGraph workflows, Deep Agents, and provider integrations for Python 3.10+.
4
5	## Component Index
6
7	### Models & Output
8	- Models — Chat models, tool calling, multimodal inputs, caching, rate limiting, custom models [reference](references/models.md)
9	- Messages — Message types (Human, AI, System, Tool), message operations, serialization, OpenAI format conversion [reference](references/messages.md)
10
11	### Agents
12	- Agents — create_agent, tools, structured output, guardrails, human-in-the-loop, context engineering [reference](references/agents.md)
13	- Multi-Agent — Subagents, handoffs, skills, router, custom workflows, pattern selection [reference](references/multi-agent.md)
14
15	### Tools & MCP
16	- Tools — Tool creation (@tool decorator, ToolNode), InjectedState, MCP integration, error handling [reference](references/tools.md)
17
18	### Retrieval & RAG
19	- Retrieval — Document loaders, text splitters, embeddings, vector stores, agentic RAG, semantic search [reference](references/retrieval.md)
20
21	### Memory
22	- Memory — Short-term (checkpointers, message trimming, summarization), long-term (store abstraction, namespaces) [reference](references/memory.md)
23
24	### Middleware & Streaming
25	- Middleware — 16 built-in middleware, custom middleware (decorator, class, wrap-style), execution order [reference](references/middleware.md)
26	- Streaming — Stream modes (updates, messages, custom), token streaming, useStream React hook [reference](references/streaming.md)
27
28	### Runtime & Architecture
29	- Runtime — Dependency injection, context schemas, ToolRuntime, component architecture (5 layers) [reference](references/runtime.md)
30
31	### Testing & Deployment
32	- Testing — Unit testing (GenericFakeChatModel), integration testing (AgentEvals), LangSmith observability [reference](references/testing.md)
33
34	### LangGraph
35	- LangGraph Core — Graph API, Functional API, workflows vs agents, state management, quickstart [reference](references/langgraph-core.md)
36	- LangGraph State — Memory, persistence, durable execution, interrupts, checkpointers [reference](references/langgraph-state.md)
37	- LangGraph Advanced — Subgraphs, time-travel, streaming, Graph API usage, Functional API usage [reference](references/langgraph-advanced.md)
38
39	### Deep Agents
40	- Deep Agents — Harness framework, models, subagents, skills, sandboxes, human-in-the-loop, long-term memory [reference](references/deep-agents.md)
41
42	### Integrations
43	- Integrations — Chat models, document loaders, retrievers, embeddings, vector stores, tools, stores, splitters [reference](references/integrations.md)
44	- Providers — OpenAI, Anthropic, Google, AWS, Ollama setup and configuration [reference](references/providers.md)
45
46	## Quick Patterns
47
48	### Create an Agent with Tools
49
50	```python
51	from langchain.chat_models import init_chat_model
52	from langgraph.prebuilt import create_agent
53
54	model = init_chat_model("anthropic:claude-sonnet-4-20250514")
55
56	def get_weather(city: str) -> str:
57	"""Get weather for a city."""
58	return f"Sunny, 72F in {city}"
59
60	agent = create_agent(model, [get_weather])
61	response = agent.invoke(
62	{"messages": [{"role": "user", "content": "What's the weather in SF?"}]}
63	)
64	```
65
66	### Structured Output
67
68	```python
69	from pydantic import BaseModel
70
71	class SearchQuery(BaseModel):
72	query: str
73	year: int
74
75	structured_model = model.with_structured_output(SearchQuery)
76	result = structured_model.invoke("Who won the World Cup in 2022?")
77	```
78
79	### RAG with Retrieval
80
81	```python
82	from langchain_community.document_loaders import WebBaseLoader
83	from langchain_text_splitters import RecursiveCharacterTextSplitter
84	from langchain_openai import OpenAIEmbeddings
85	from langchain_core.vectorstores import InMemoryVectorStore
86
87	docs = WebBaseLoader("https://example.com").load()
88	chunks = RecursiveCharacterTextSplitter(chunk_size=1000).split_documents(docs)
89	vector_store = InMemoryVectorStore.from_documents(chunks, OpenAIEmbeddings())
90	retriever_tool = vector_store.as_retriever()
91	```
92
93	### Multi-Agent Handoffs
94
95	```python
96	from langgraph.prebuilt import create_agent
97
98	billing_agent = create_agent(model, [lookup_billing], name="billing")
99	tech_agent = create_agent(model, [check_status], name="tech_support")
100	supervis

People who liked this also viewed

6 picks

Type