Notebooks
N
Nebius Function Calling 1

Function Calling 1

tool-callingnebius-token-factory-cookbook
alph-notebooks/nebius-token-factory-cookbook / function_calling_1.ipynb

Function Calling in Nebius Token Factory

Open In Colab

Pre requisites

1 - Setup

1.1 - If running on Google Colab

Add NEBIUS_API_KEY to Secrets as follows

1.2 - If running locally

Create an .env file with NEBIUS_API_KEY as follows

NEBIUS_API_KEY=your_api_key_goes_here

2 - Install Dependencies

[1]
NOT running on Colab
[2]

3 - Load Configuration

[3]
✅ NEBIUS_API_KEY found

4 - Pick a Model

We will pick a model that supports function calling.

  1. Go to models tab in tokenfactory.nebius.com
  2. Select text to text models
  3. Select function calling filter
  4. Copy the model name. For example openai/gpt-oss-20b

See screenshot here:

Recomended models:

  • Qwen3 family
    • openai/gpt-oss-20b
    • Qwen/Qwen3-235B-A22B
  • Deepseek family
    • deepseek-ai/DeepSeek-R1-0528
  • Llama
    • meta-llama/Llama-3.3-70B-Instruct

5 - Define Function Call

Here we will use pydantic to define the schema

[4]

6 - Tool calling

[5]
CPU times: user 490 ms, sys: 65.7 ms, total: 555 ms
Wall time: 612 ms
[6]
The weather in San Francisco is 72 degrees fahrenheit. It is sunny, with highs in the 80's.
[7]
[{'role': 'user',
,  'content': 'Can you tell me what the temperature will be in San Francisco?'},
, {'role': 'assistant',
,  'tool_calls': [ChatCompletionMessageToolCall(id='chatcmpl-tool-0c160206cdea4ca6b10cc37e4b592ad7', function=Function(arguments='{"city": "San Francisco", "unit": "celsius"}', name='get_current_weather'), type='function')]},
, {'role': 'tool',
,  'content': "The weather in San Francisco is 72 degrees fahrenheit. It is sunny, with highs in the 80's.",
,  'tool_call_id': 'chatcmpl-tool-0c160206cdea4ca6b10cc37e4b592ad7',
,  'name': 'get_current_weather'}]