Fix variable name inconsistency in SQL agent tutorial (#1552)

Fixes DOC-471

Author: lnhsingh

src/oss/langgraph/sql-agent.mdx

@@ -169,7 +169,7 @@ Use the `SQLDatabase` wrapper available in the `langchain_community` package to
 ```python
 from langchain_community.agent_toolkits import SQLDatabaseToolkit
 
-toolkit = SQLDatabaseToolkit(db=db, llm=llm)
+toolkit = SQLDatabaseToolkit(db=db, llm=model)
 
 tools = toolkit.get_tools()
 
@@ -304,7 +304,7 @@ def list_tables(state: MessagesState):
 def call_get_schema(state: MessagesState):
     # Note that LangChain enforces that all models accept `tool_choice="any"`
     # as well as `tool_choice=<string name of tool>`.
-    llm_with_tools = llm.bind_tools([get_schema_tool], tool_choice="any")
+    llm_with_tools = model.bind_tools([get_schema_tool], tool_choice="any")
     response = llm_with_tools.invoke(state["messages"])
 
     return {"messages": [response]}
@@ -335,7 +335,7 @@ def generate_query(state: MessagesState):
     }
     # We do not force a tool call here, to allow the model to
     # respond naturally when it obtains the solution.
-    llm_with_tools = llm.bind_tools([run_query_tool])
+    llm_with_tools = model.bind_tools([run_query_tool])
     response = llm_with_tools.invoke([system_message] + state["messages"])
 
     return {"messages": [response]}
@@ -369,7 +369,7 @@ def check_query(state: MessagesState):
     # Generate an artificial user message to check
     tool_call = state["messages"][-1].tool_calls[0]
     user_message = {"role": "user", "content": tool_call["args"]["query"]}
-    llm_with_tools = llm.bind_tools([run_query_tool], tool_choice="any")
+    llm_with_tools = model.bind_tools([run_query_tool], tool_choice="any")
     response = llm_with_tools.invoke([system_message, user_message])
     response.id = state["messages"][-1].id
 
@@ -407,7 +407,7 @@ async function listTables(state: typeof MessagesAnnotation.State) {
 
 // Example: force a model to create a tool call
 async function callGetSchema(state: typeof MessagesAnnotation.State) {
-  const llmWithTools = llm.bindTools([getSchemaTool], {
+  const llmWithTools = model.bindTools([getSchemaTool], {
     tool_choice: "any",
   });
   const response = await llmWithTools.invoke(state.messages);
@@ -435,7 +435,7 @@ async function generateQuery(state: typeof MessagesAnnotation.State) {
   const systemMessage = new SystemMessage(generateQuerySystemPrompt);
   // We do not force a tool call here, to allow the model to
   // respond naturally when it obtains the solution.
-  const llmWithTools = llm.bindTools([queryTool]);
+  const llmWithTools = model.bindTools([queryTool]);
   const response = await llmWithTools.invoke([systemMessage, ...state.messages]);
 
   return { messages: [response] };
@@ -469,7 +469,7 @@ async function checkQuery(state: typeof MessagesAnnotation.State) {
   }
   const toolCall = lastMessage.tool_calls[0];
   const userMessage = new HumanMessage(toolCall.args.query);
-  const llmWithTools = llm.bindTools([queryTool], {
+  const llmWithTools = model.bindTools([queryTool], {
     tool_choice: "any",
   });
   const response = await llmWithTools.invoke([systemMessage, userMessage]);