A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 03:30 UTC
Documentation update tool_calling: mapping back to function from response (#20373)
cronoik-inceptionai committed
Jul 2, 2025 at 16:55 UTC
b95877509b86653caafe31da9c6aa480233725c0
1 file changed
+1
-1
docs/features/tool_calling.md
+1
-1
@@ -53,7 +53,7 @@ Next, make a request to the model that should result in it using the available t
53
tool_call = response.choices[0].message.tool_calls[0].function
54
print(f"Function called: {tool_call.name}")
55
print(f"Arguments: {tool_call.arguments}")
56
- print(f"Result: {get_weather(**json.loads(tool_call.arguments))}")
56
+ print(f"Result: {tool_functions[tool_call.name](**json.loads(tool_call.arguments))}")
57
```
58
59
Example output: