# Observability

* **LangSmith**
    
    * A developer tool/platform for managing and debugging LLM (Large Language Model) applications.
        
    * Helps with **tracing, monitoring, and evaluation** of prompts and responses.
        
* **LangFuse**
    
    * An open-source observability and analytics platform for LLM applications.
        
    * Provides **monitoring, logging, and user feedback integration**.
        

**Key Difference Example:**

* *LangSmith* → Often used for **prompt debugging and evaluation**.
    
* *LangFuse* → Often used for **observability and logging** across the lifecycle.
    

---

## Implementation Notes

### LangSmith Environment Setup

Add the following to `.env` file:

```plaintext
LANGSMITH_TRACING=true
LANGSMITH_ENDPOINT=https://api.smith.langchain.com
LANGSMITH_API_KEY=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
LANGSMITH_PROJECT=calender-ai-project
```

### Installation Command

Run:

```bash
npm install @langchain/langgraph @langchain/core
```

---

## LangFuse Setup

### Self-Hosting with Docker Compose

* Official deployment guide: [LangFuse Docker Compose Deployment](https://langfuse.com/self-hosting/deployment/docker-compose)
    
* Provides steps to set up **LangFuse locally or on a server** using Docker Compose.
    

### Integration with LangChain

* Official integration guide: [LangFuse x LangChain](https://langfuse.com/integrations/frameworks/langchain)
    
* Explains how to integrate **LangFuse observability** directly into LangChain apps.
    

## Comparison

| Feature | LangSmith | LangFuse |
| --- | --- | --- |
| Setup | Easy, quick | Harder (needs Docker, DB setup) |
| Cost | Costly | Nearly free (self-hosted option) |
| Purpose | Debugging, tracing, evaluation | Monitoring, observability, logging |
| Flexibility | Limited by platform pricing model | Fully open-source, customizable |