tool-calling-agent update; README

recipes/use_cases/agents/langchain/README.md

@@ -16,7 +16,7 @@ AgentExecutor is the runtime for an agent. AgentExecutor calls the agent, execut
 
 Our first notebook, `tool-calling-agent`, shows how to build a [tool calling agent](https://python.langchain.com/docs/modules/agents/agent_types/tool_calling/) with AgentExecutor and Llama 3.
 
-This shows how to build an agent that uses web search and retrieval tools.
+This shows how to build an agent that uses web search, text2image, image2text, and text2speech tools.
 
 --- 
 
@@ -29,9 +29,9 @@ LangGraph can be used to build agents with a few pieces:
 - **Memory:** Persist information (graph state) across these steps
 - **Tool use:** Modify state at any step
 
-Our second notebook, `langgraph-agent`, shows how to build a Llama 3 powered agent that uses web search and retrieval tool in LangGraph.
+Our second notebook, `langgraph-agent`, shows an alternative way to AgentExecutor to build a Llama 3 powered agent in LangGraph. 
 
-It discusses some of the trade-offs between AgentExecutor and LangGraph.
+It discusses some of the trade-offs between AgentExecutor and LangGraph. 
 
 --- 
 

recipes/use_cases/agents/langchain/langgraph-agent.ipynb

@@ -140,17 +140,6 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "a697495d-c6ad-4baf-9e76-b1b1ac4ca745",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "os.environ[\"REPLICATE_API_TOKEN\"] = \"r8_agHIJ9gWsfUbCKgtdOWlnIdcTFFed3x1PNIbV\""
-   ]
-  },
-  {
-   "cell_type": "code",
    "execution_count": 16,
    "id": "586093b9-115c-47d6-840a-9c0d09522af1",
    "metadata": {},