Update README.md

README.md

@@ -69,13 +69,10 @@ This formatting is also available via our vLLM server which we process the funct
 from openai import OpenAI
 
 client = OpenAI(base_url="http://localhost:8000/v1", api_key="functionary")
-
-client.chat.completions.create(
-    model="path/to/functionary/model/",
-    messages=[{"role": "user",
+messages = [{"role": "user",
             "content": "What is the weather for Istanbul?"}
-    ],
-    tools=[{
+    ]
+tools = [{
             "type": "function",
             "function": {
                 "name": "get_current_weather",
@@ -91,7 +88,15 @@ client.chat.completions.create(
                     "required": ["location"]
                 }
             }
-        }],
+        }]
+
+# to let the model generate the reasoning first, then the tool uses add type reasoning; without reasoning tool, the model will not output the reasoning
+tools.append({"type": "reasoning"})
+
+client.chat.completions.create(
+    model="path/to/functionary/model/",
+    messages=messages,
+    tools=tools,
     tool_choice="auto"
 )
 ```
@@ -101,7 +106,8 @@ will yield:
 ```
 <|start_header_id|>system<|end_header_id|>
 
-Environment: ipython
+Reasoning Mode: On
+
 
 Cutting Knowledge Date: December 2023
 
@@ -109,7 +115,7 @@ Cutting Knowledge Date: December 2023
 You have access to the following functions:
 
 Use the function 'get_current_weather' to 'Get the current weather'
-{"name": "get_current_weather", "description": "Get the current weather", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city and state, e.g. San Francisco, CA"}},"required": ["location"]}}
+{"name": "get_current_weather", "description": "Get the current weather", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city and state, e.g. San Francisco, CA"}}, "required": ["location"]}}
 
 
 Think very carefully before calling functions.
@@ -136,7 +142,6 @@ Reminder:
 What is the weather for Istanbul?
 ```
 
-A more detailed example is provided [here](https://github.com/MeetKai/functionary/blob/main/tests/prompt_test_v3-llama3.1.txt).
 
 ## Run the model