diff --git a/_posts/2024-05-04-RAG.md b/_posts/2024-05-04-RAG.md
index fd83d287..aee30c06 100644
--- a/_posts/2024-05-04-RAG.md
+++ b/_posts/2024-05-04-RAG.md
@@ -91,11 +91,60 @@ Introduction to Retrieval-Augmented Generation (RAG)
 ---
 ## Frameworks
 
-### [Langchain](https://github.com/langchain-ai/langchain)
-LangChain is a framework for developing applications powered by large language models (LLMs).
+### [LangChain](https://github.com/langchain-ai/langchain)
+LangChain is a framework for developing applications powered by large language models (LLMs).<br>
+![](https://js.langchain.com/assets/images/langchain_stack_feb_2024-101939844004a99c1b676723fc0ee5e9.webp)
 
+---
+### [LangGraph](https://langchain-ai.github.io/langgraph/)
+**[Introduction to LangGraph](https://langchain-ai.github.io/langgraph/tutorials/introduction/)**<br>
+![](https://github.com/rkuo2000/AI-course/blob/main/images/LangGraph_intro.png?raw=true)<br>
+
+```
+import json
+from langchain_anthropic import ChatAnthropic
+from langchain_community.tools.tavily_search import TavilySearchResults
+from langgraph.checkpoint.sqlite import SqliteSaver
+from langgraph.graph import END, MessageGraph
+from langgraph.prebuilt.tool_node import ToolNode
+
+# Define the function that determines whether to continue or not
+def should_continue(messages):
+    last_message = messages[-1]
+    # If there is no function call, then we finish
+    if not last_message.tool_calls:
+        return END
+    else:
+        return "action"
+
+# Define a new graph
+workflow = MessageGraph()
+
+tools = [TavilySearchResults(max_results=1)]
+
+model = ChatAnthropic(model="claude-3-haiku-20240307").bind_tools(tools)
+
+workflow.add_node("agent", model)
+workflow.add_node("action", ToolNode(tools))
+workflow.set_entry_point("agent")
+
+# Conditional agent -> action OR agent -> END
+workflow.add_conditional_edges(
+    "agent",
+    should_continue,
+)
+
+# Always transition `action` -> `agent`
+workflow.add_edge("action", "agent")
+memory = SqliteSaver.from_conn_string(":memory:") # Here we only save in-memory
+
+# Setting the interrupt means that any time an action is called, the machine will stop
+app = workflow.compile(checkpointer=memory, interrupt_before=["action"])
+```
+
+---
 ### [LlamaIndex](https://github.com/run-llama/llama_index)
-LlamaIndex (GPT Index) is a data framework for your LLM application.
+LlamaIndex (GPT Index) is a data framework for your LLM application.<br>
 **Kaggle:** [https://www.kaggle.com/code/rkuo2000/llm-llamaindex](https://www.kaggle.com/code/rkuo2000/llm-llamaindex)<br>
 
 ---