Add client.embeddings.create() for /v1/embeddings endpoint

[flyworker]

Context

mega-nova-api is adding POST /v1/embeddings (MeganovaAI/mega-nova-api#441). The SDK needs a matching client method.

Requirements

• Create meganova/resources/embeddings.py with EmbeddingsResource
• Add client.embeddings.create() method
• Support parameters: input (str or list[str]), model, encoding_format
• Create Pydantic models in models/embeddings.py:
  • Embedding(index, embedding: list[float], object)
  • EmbeddingResponse(data: list[Embedding], model, usage)
• Wire into main MegaNova client class
• Add example: examples/embeddings.py

Interface

# Match OpenAI SDK pattern:
response = client.embeddings.create(
    input="Hello world",
    model="meganova-ai/embedding-v1"
)
print(response.data[0].embedding[:5])  # [0.123, -0.456, ...]

Depends On

• mega-nova-api#441 (embeddings endpoint implementation)

[flyworker]

📋 Reference Report: AI API Compatibility Best Practices Research (29 items, 7 categories — protocols, gateways, SDKs, cloud platforms, local inference)

Tracking Epic: MeganovaAI/mega-nova-api#447

[flyworker]

Implemented in PR #15