langchain-architecture

name	langchain-architecture
description	Design LLM applications using LangChain and LangGraph frameworks with agents, memory, tool integration, state management, and production deployment patterns. Covers LangChain 0.1+ and LangGraph APIs. Use when this capability is needed.
metadata	{"author":"bugrabilge"}

LangChain Architecture

Master the LangChain framework for building sophisticated LLM applications with agents, chains, memory, and tool integration.

Do not use this skill when

• The task is unrelated to langchain architecture
• You need a different domain or tool outside this scope

Instructions

• Clarify goals, constraints, and required inputs.
• Apply relevant best practices and validate outcomes.
• Provide actionable steps and verification.
• If detailed examples are required, open resources/implementation-playbook.md.

Use this skill when

• Building autonomous AI agents with tool access
• Implementing complex multi-step LLM workflows
• Managing conversation memory and state
• Integrating LLMs with external data sources and APIs
• Creating modular, reusable LLM application components
• Implementing document processing pipelines
• Building production-grade LLM applications

Core Concepts

1. Agents

Autonomous systems that use LLMs to decide which actions to take.

Agent Types:

• ReAct: Reasoning + Acting in interleaved manner
• OpenAI Functions: Leverages function calling API
• Structured Chat: Handles multi-input tools
• Conversational: Optimized for chat interfaces
• Self-Ask with Search: Decomposes complex queries

2. Chains

Sequences of calls to LLMs or other utilities.

Chain Types:

• LLMChain: Basic prompt + LLM combination
• SequentialChain: Multiple chains in sequence
• RouterChain: Routes inputs to specialized chains
• TransformChain: Data transformations between steps
• MapReduceChain: Parallel processing with aggregation

3. Memory

Systems for maintaining context across interactions.

Memory Types:

• ConversationBufferMemory: Stores all messages
• ConversationSummaryMemory: Summarizes older messages
• ConversationBufferWindowMemory: Keeps last N messages
• EntityMemory: Tracks information about entities
• VectorStoreMemory: Semantic similarity retrieval

4. Document Processing

Loading, transforming, and storing documents for retrieval.

Components:

• Document Loaders: Load from various sources
• Text Splitters: Chunk documents intelligently
• Vector Stores: Store and retrieve embeddings
• Retrievers: Fetch relevant documents
• Indexes: Organize documents for efficient access

5. Callbacks

Hooks for logging, monitoring, and debugging.

Use Cases:

• Request/response logging
• Token usage tracking
• Latency monitoring
• Error handling
• Custom metrics collection

Quick Start

from langchain.agents import AgentType, initialize_agent, load_tools
from langchain.llms import OpenAI
from langchain.memory import ConversationBufferMemory

# Initialize LLM
llm = OpenAI(temperature=0)

# Load tools
tools = load_tools(["serpapi", "llm-math"], llm=llm)

# Add memory
memory = ConversationBufferMemory(memory_key="chat_history")

# Create agent
agent = initialize_agent(
    tools,
    llm,
    agent=AgentType.CONVERSATIONAL_REACT_DESCRIPTION,
    memory=memory,
    verbose=True
)

# Run agent
result = agent.run("What's the weather in SF? Then calculate 25 * 4")

Architecture Patterns

Pattern 1: RAG with LangChain

from langchain.chains import RetrievalQA
from langchain.document_loaders import TextLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import Chroma
from langchain.embeddings import OpenAIEmbeddings

# Load and process documents
loader = TextLoader('documents.txt')
documents = loader.load()

text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
texts = text_splitter.split_documents(documents)

# Create vector store
embeddings = OpenAIEmbeddings()
vectorstore = Chroma.from_documents(texts, embeddings)

# Create retrieval chain
qa_chain = RetrievalQA.from_chain_type(
    llm=llm,
    chain_type="stuff",
    retriever=vectorstore.as_retriever(),
    return_source_documents=True
)

# Query
result = qa_chain({"query": "What is the main topic?"})

Pattern 2: Custom Agent with Tools

from langchain.agents import Tool, AgentExecutor
from langchain.agents.react.base import ReActDocstoreAgent
from langchain.tools import tool

@tool
def search_database(query: str) -> str:
    """Search internal database for information."""
    # Your database search logic
    return f"Results for: {query}"

@tool
def send_email(recipient: str, content: str) -> str:
    """Send an email to specified recipient."""
    # Email sending logic
    return f"Email sent to {recipient}"

tools = [search_database, send_email]

agent = initialize_agent(
    tools,
    llm,
    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
    verbose=True
)

Pattern 3: Multi-Step Chain

from langchain.chains import LLMChain, SequentialChain
from langchain.prompts import PromptTemplate

# Step 1: Extract key information
extract_prompt = PromptTemplate(
    input_variables=["text"],
    template="Extract key entities from: {text}\n\nEntities:"
)
extract_chain = LLMChain(llm=llm, prompt=extract_prompt, output_key="entities")

# Step 2: Analyze entities
analyze_prompt = PromptTemplate(
    input_variables=["entities"],
    template="Analyze these entities: {entities}\n\nAnalysis:"
)
analyze_chain = LLMChain(llm=llm, prompt=analyze_prompt, output_key="analysis")

# Step 3: Generate summary
summary_prompt = PromptTemplate(
    input_variables=["entities", "analysis"],
    template="Summarize:\nEntities: {entities}\nAnalysis: {analysis}\n\nSummary:"
)
summary_chain = LLMChain(llm=llm, prompt=summary_prompt, output_key="summary")

# Combine into sequential chain
overall_chain = SequentialChain(
    chains=[extract_chain, analyze_chain, summary_chain],
    input_variables=["text"],
    output_variables=["entities", "analysis", "summary"],
    verbose=True
)

Memory Management Best Practices

Choosing the Right Memory Type

# For short conversations (< 10 messages)
from langchain.memory import ConversationBufferMemory
memory = ConversationBufferMemory()

# For long conversations (summarize old messages)
from langchain.memory import ConversationSummaryMemory
memory = ConversationSummaryMemory(llm=llm)

# For sliding window (last N messages)
from langchain.memory import ConversationBufferWindowMemory
memory = ConversationBufferWindowMemory(k=5)

# For entity tracking
from langchain.memory import ConversationEntityMemory
memory = ConversationEntityMemory(llm=llm)

# For semantic retrieval of relevant history
from langchain.memory import VectorStoreRetrieverMemory
memory = VectorStoreRetrieverMemory(retriever=retriever)

Callback System

Custom Callback Handler

from langchain.callbacks.base import BaseCallbackHandler

class CustomCallbackHandler(BaseCallbackHandler):
    def on_llm_start(self, serialized, prompts, **kwargs):
        print(f"LLM started with prompts: {prompts}")

    def on_llm_end(self, response, **kwargs):
        print(f"LLM ended with response: {response}")

    def on_llm_error(self, error, **kwargs):
        print(f"LLM error: {error}")

    def on_chain_start(self, serialized, inputs, **kwargs):
        print(f"Chain started with inputs: {inputs}")

    def on_agent_action(self, action, **kwargs):
        print(f"Agent taking action: {action}")

# Use callback
agent.run("query", callbacks=[CustomCallbackHandler()])

Testing Strategies

import pytest
from unittest.mock import Mock

def test_agent_tool_selection():
    # Mock LLM to return specific tool selection
    mock_llm = Mock()
    mock_llm.predict.return_value = "Action: search_database\nAction Input: test query"

    agent = initialize_agent(tools, mock_llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION)

    result = agent.run("test query")

    # Verify correct tool was selected
    assert "search_database" in str(mock_llm.predict.call_args)

def test_memory_persistence():
    memory = ConversationBufferMemory()

    memory.save_context({"input": "Hi"}, {"output": "Hello!"})

    assert "Hi" in memory.load_memory_variables({})['history']
    assert "Hello!" in memory.load_memory_variables({})['history']

Performance Optimization

1. Caching

from langchain.cache import InMemoryCache
import langchain

langchain.llm_cache = InMemoryCache()

2. Batch Processing

# Process multiple documents in parallel
from langchain.document_loaders import DirectoryLoader
from concurrent.futures import ThreadPoolExecutor

loader = DirectoryLoader('./docs')
docs = loader.load()

def process_doc(doc):
    return text_splitter.split_documents([doc])

with ThreadPoolExecutor(max_workers=4) as executor:
    split_docs = list(executor.map(process_doc, docs))

3. Streaming Responses

from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler

llm = OpenAI(streaming=True, callbacks=[StreamingStdOutCallbackHandler()])

Resources

• references/agents.md: Deep dive on agent architectures
• references/memory.md: Memory system patterns
• references/chains.md: Chain composition strategies
• references/document-processing.md: Document loading and indexing
• references/callbacks.md: Monitoring and observability
• assets/agent-template.py: Production-ready agent template
• assets/memory-config.yaml: Memory configuration examples
• assets/chain-example.py: Complex chain examples

Common Pitfalls

1. Memory Overflow: Not managing conversation history length
2. Tool Selection Errors: Poor tool descriptions confuse agents
3. Context Window Exceeded: Exceeding LLM token limits
4. No Error Handling: Not catching and handling agent failures
5. Inefficient Retrieval: Not optimizing vector store queries

Production Checklist

• Implement proper error handling
• Add request/response logging
• Monitor token usage and costs
• Set timeout limits for agent execution
• Implement rate limiting
• Add input validation
• Test with edge cases
• Set up observability (callbacks)
• Implement fallback strategies
• Version control prompts and configurations

---

LangGraph State Management

State Graph Pattern

from langgraph.graph import StateGraph, MessagesState, START, END
from langgraph.prebuilt import create_react_agent
from langchain_anthropic import ChatAnthropic

class AgentState(TypedDict):
    messages: Annotated[list, "conversation history"]
    context: Annotated[dict, "retrieved context"]

builder = StateGraph(MessagesState)
builder.add_node("node1", node1_func)
builder.add_node("node2", node2_func)
builder.add_edge(START, "node1")
builder.add_conditional_edges("node1", router, {"a": "node2", "b": END})
builder.add_edge("node2", END)
agent = builder.compile(checkpointer=checkpointer)

Multi-Agent Orchestration with LangGraph

• Use Command[Literal["agent1", "agent2", END]] for routing between agents
• Supervisor agent decides next agent based on context and task requirements
• Track progress through shared state across agent nodes

Recommended Model & Embeddings

Purpose	Model	Notes
Primary LLM	Claude Sonnet 4.5	Best balance of quality and speed
Embeddings	Voyage AI voyage-3-large	Officially recommended for Claude
Code embeddings	voyage-code-3	Optimized for code search
Domain-specific	voyage-finance-2, voyage-law-2	Specialized domains

Advanced RAG with LangChain

HyDE (Hypothetical Document Embeddings)

Generate a hypothetical answer to the query, embed that, and use it for retrieval. Improves recall for abstract queries.

RAG Fusion

Generate multiple query perspectives, retrieve for each, then merge results using Reciprocal Rank Fusion.

Reranking Pipeline

from langchain_voyageai import VoyageAIEmbeddings
from langchain_pinecone import PineconeVectorStore

embeddings = VoyageAIEmbeddings(model="voyage-3-large")
vectorstore = PineconeVectorStore(index=index, embedding=embeddings)

# Retrieve with hybrid search, then rerank
base_retriever = vectorstore.as_retriever(
    search_type="hybrid",
    search_kwargs={"k": 20, "alpha": 0.5}
)

Production Deployment with FastAPI

from fastapi import FastAPI
from fastapi.responses import StreamingResponse

@app.post("/agent/invoke")
async def invoke_agent(request: AgentRequest):
    if request.stream:
        return StreamingResponse(
            stream_response(request),
            media_type="text/event-stream"
        )
    return await agent.ainvoke({"messages": [...]})

Async Patterns

Always use async methods in production for better concurrency:

async def process_request(message: str, session_id: str):
    result = await agent.ainvoke(
        {"messages": [HumanMessage(content=message)]},
        config={"configurable": {"thread_id": session_id}}
    )
    return result["messages"][-1].content

Monitoring & Observability

Tool	Purpose
LangSmith	Trace all agent executions, debug chains
Prometheus	Track requests, latency, error rates
Structured logging	Use structlog for consistent logs
Health checks	Validate LLM, tools, memory, and external services

LangGraph Best Practices

1. Always use async: ainvoke, astream, aget_relevant_documents
2. Handle errors gracefully: Try/except with fallbacks and retries
3. Monitor everything: Trace, log, and collect metrics on all operations
4. Optimize costs: Cache responses, set token limits, compress memory
5. Secure secrets: Environment variables, never hardcode API keys
6. Version control state: Use checkpointers for reproducibility
7. Test with evaluation suites: Use LangSmith evaluation framework

---

Source: bugrabilge/bilge-development-kit — distributed by TomeVault.