Skip to main content

Examples

Explore practical code examples to get the most out of the Nebul inference-api.

Streaming Responses​

Stream tokens as they're generated for real-time output:

python
1234567891011121314151617
from openai import OpenAI


client = OpenAI(
    api_key="sk-your-api-key-here",
    base_url="https://api.inference.nebul.io/v1"
)


stream = client.chat.completions.create(
    model="openai/gpt-oss-120b",
    messages=[{"role": "user", "content": "Write a haiku about AI."}],
    stream=True
)


for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
print()

Text Embeddings​

Generate vector embeddings for semantic search, similarity matching, and RAG applications.

python
12345678910111213
from openai import OpenAI


client = OpenAI(
    api_key="sk-your-api-key-here",
    base_url="https://api.inference.nebul.io/v1"
)


response = client.embeddings.create(
    model="sentence-transformers/all-MiniLM-L6-v2",
    input="Privacy is fundamental to maintaining trust in AI systems."
)


print(response.data[0].embedding)

Batch Embeddings​

Embed multiple texts in a single request for efficiency:

python
1234567891011121314151617181920
from openai import OpenAI


client = OpenAI(
    api_key="sk-your-api-key-here",
    base_url="https://api.inference.nebul.io/v1"
)


texts = [
    "First document to embed",
    "Second document to embed",
    "Third document to embed"
]


response = client.embeddings.create(
    model="sentence-transformers/all-MiniLM-L6-v2",
    input=texts
)


for i, data in enumerate(response.data):
    print(f"Text {i+1}: {len(data.embedding)} dimensions")

Vision - Image Analysis​

Analyze images by providing them as base64-encoded strings or image URLs.

Using Image URL​

python
1234567891011121314151617181920212223242526
from openai import OpenAI


client = OpenAI(
    api_key="sk-your-api-key-here",
    base_url="https://api.inference.nebul.io/v1"
)


response = client.chat.completions.create(
    model="Qwen/Qwen3-VL-235B-A22B-Thinking",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://fastly.picsum.photos/id/669/200/200.jpg?hmac=lAa_bMRK0BRBCTEvl1acVqTfEDrXQc0yNwi683-13cE"
                    }
                }
            ]
        }
    ]
)


print(response.choices[0].message.content)

Using Base64-Encoded Image​

python
12345678910111213141516171819202122232425262728293031
from openai import OpenAI
import base64


client = OpenAI(
    api_key="sk-your-api-key-here",
    base_url="https://api.inference.nebul.io/v1"
)


# Read and encode image
with open("image.jpg", "rb") as image_file:
    base64_image = base64.b64encode(image_file.read()).decode('utf-8')


response = client.chat.completions.create(
    model="Qwen/Qwen3-VL-235B-A22B-Thinking",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe this image in detail."},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": f"data:image/jpeg;base64,{base64_image}"
                    }
                }
            ]
        }
    ]
)


print(response.choices[0].message.content)

Function Calling & Tools​

Enable models to call external functions and APIs. See Function Calling & Tools for the complete guide.

python
123456789101112131415161718192021222324252627282930313233343536373839404142
from openai import OpenAI


client = OpenAI(
    api_key="sk-your-api-key-here",
    base_url="https://api.inference.nebul.io/v1"
)


tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the current weather for a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city and country, e.g. London, UK"
                    },
                    "unit": {
                        "type": "string",
                        "enum": ["celsius", "fahrenheit"],
                        "description": "Temperature unit"
                    }
                },
                "required": ["location"]
            }
        }
    }
]


response = client.chat.completions.create(
    model="Qwen/Qwen3-VL-235B-A22B-Thinking",
    messages=[
        {"role": "user", "content": "What's the weather in Paris?"}
    ],
    tools=tools,
    tool_choice="auto"
)


print(response.choices[0].message.tool_calls)
Last updated on