Langchain Patterns

# Langchain Patterns

## Skill Profile
*(Select at least one profile to enable specific modules)*
- [ ] **DevOps**
- [x] **Backend**
- [ ] **Frontend**
- [ ] **AI-RAG**
- [ ] **Security Critical**

## Overview
LangChain is a framework for building applications powered by LLMs. It helps manage the complexity of prompt chaining, memory, retrieval, agents, and tool use, making it faster to build AI applications. This skill covers basic setup, structured output, RAG (Retrieval-Augmented Generation), conversational memory, agents with tools, streaming, document loaders, LangSmith integration for production monitoring, and production deployment patterns.

## Why This Matters
LangChain is essential for production AI applications because:
- **Abstraction**: Unified interface for various LLM providers
- **Composability**: Chain components together easily
- **RAG Ready**: Built-in retrieval and vector store integrations
- **Production**: LangSmith for monitoring and debugging
- **Ecosystem**: Extensive library of integrations and tools

## Core Concepts & Rules

### 1. Core Principles
- Follow established patterns and conventions
- Maintain consistency across codebase
- Document decisions and trade-offs

### 2. Implementation Guidelines
- Start with the simplest viable solution
- Iterate based on feedback and requirements
- Test thoroughly before deployment


## Inputs / Outputs / Contracts
#

## Skill Composition
* **Depends on**: None
* **Compatible with**: None
* **Conflicts with**: None
* **Related Skills**: None

## Quick Start
#

## Assumptions
- API keys are available in environment variables
- Vector database is configured and accessible
- Documents are in supported formats (PDF, CSV, text)
- Network connectivity for external services
- Sufficient memory for document processing

## Compatibility
- Node.js 18+
- TypeScript 5.0+
- LangChain 0.1+
- OpenAI API 1.0+
- Anthropic API 1.0+
- Supabase 2.0+
- Redis 6.0+

## Test Scenario Matrix (QA Strategy)

| Type | Focus Area | Required Scenarios / Mocks |
| :--- | :--- | :--- |
| **Unit** | Core Logic | Must cover primary logic and at least 3 edge/error cases. Target minimum 80% coverage |
| **Integration** | DB / API | All external API calls or database connections must be mocked during unit tests |
| **E2E** | User Journey | Critical user flows to test |
| **Performance** | Latency / Load | Benchmark requirements |
| **Security** | Vuln / Auth | SAST/DAST or dependency audit |
| **Frontend** | UX / A11y | Accessibility checklist (WCAG), Performance Budget (Lighthouse score) |


## Technical Guardrails & Security Threat Model

### 1. Security & Privacy (Threat Model)
* **Top Threats**: Injection attacks, authentication bypass, data exposure
- [ ] **Data Handling**: Sanitize all user inputs to prevent Injection attacks. Never log raw PII
- [ ] **Secrets Management**: No hardcoded API keys. Use Env Vars/Secrets Manager
- [ ] **Authorization**: Validate user permissions before state changes

### 2. Performance & Resources
- [ ] **Execution Efficiency**: Consider time complexity for algorithms
- [ ] **Memory Management**: Use streams/pagination for large data
- [ ] **Resource Cleanup**: Close DB connections/file handlers in finally blocks

### 3. Architecture & Scalability
- [ ] **Design Pattern**: Follow SOLID principles, use Dependency Injection
- [ ] **Modularity**: Decouple logic from UI/Frameworks

### 4. Observability & Reliability
- [ ] **Logging Standards**: Structured JSON, include trace IDs `request_id`
- [ ] **Metrics**: Track `error_rate`, `latency`, `queue_depth`
- [ ] **Error Handling**: Standardized error codes, no bare except
- [ ] **Observability Artifacts**:
    - **Log Fields**: timestamp, level, message, request_id
    - **Metrics**: request_count, error_count, response_time
    - **Dashboards/Alerts**: High Error Rate > 5%


## Agent Directives & Error Recovery
*(ข้อกำหนดสำหรับ AI Agent ในการคิดและแก้ปัญหาเมื่อเกิดข้อผิดพลาด)*

- **Thinking Process**: Analyze root cause before fixing. Do not brute-force.
- **Fallback Strategy**: Stop after 3 failed test attempts. Output root cause and ask for human intervention/clarification.
- **Self-Review**: Check against Guardrails & Anti-patterns before finalizing.
- **Output Constraints**: Output ONLY the modified code block. Do not explain unless asked.


## Definition of Done (DoD) Checklist

- [ ] Tests passed + coverage met
- [ ] Lint/Typecheck passed
- [ ] Logging/Metrics/Trace implemented
- [ ] Security checks passed
- [ ] Documentation/Changelog updated
- [ ] Accessibility/Performance requirements met (if frontend)


## Anti-patterns
1. **No Streaming**: Not streaming long responses
2. **Ignoring Token Limits**: Not monitoring context length
3. **No Error Handling**: LLM calls can fail
4. **Hardcoded Prompts**: Not using prompt templates
5. **No Memory**: Stateless conversations
6. **Blocking Operations**: Not using async/await properly

## Reference Links & Examples

* Internal documentation and examples
* Official documentation and best practices
* Community resources and discussions


## Versioning & Changelog

* **Version**: 1.0.0
* **Changelog**:
  - 2026-02-22: Initial version with complete template structure