Skip to main content
Embed text and generate completions using OpenAI models. See the API reference for all parameters. 
pip install 'geneva[udf-text-openai]'
OpenAI UDFs make API calls that incur per-token costs. Each row processed results in one or more API requests billed to your account. Review OpenAI pricing before running on large tables.
Set the OPENAI_API_KEY environment variable before calling any factory function below. The key is read at UDF creation time and serialized with the UDF — no cluster-level env_vars configuration is needed.

​
Embeddings

Compare models by adding multiple embedding columns at once: 
from geneva.udfs import openai_embedding_udf

table.add_columns({
    # Default model — fast, 1536 dimensions
    "embedding_small": openai_embedding_udf(
        column="body",
        model="text-embedding-3-small",
    ),
    # Higher-quality model — 3072 dimensions
    "embedding_large": openai_embedding_udf(
        column="body",
        model="text-embedding-3-large",
    ),
    # Same large model, truncated to 256 dimensions for storage efficiency
    "embedding_large_256": openai_embedding_udf(
        column="body",
        model="text-embedding-3-large",
        output_dimensionality=256,
    ),
})

​
Generation

Generate text from OpenAI chat completion models. Supports both text and binary (image) input columns. See the API reference for all parameters. Add a summary and an image caption in one call, using different models: 
from geneva.udfs import openai_udf

table.add_columns({
    # Fast model for bulk text summarization
    "summary": openai_udf(
        column="body",
        prompt="Summarize this document in 3 bullet points",
        model="gpt-5-mini",
    ),
    # More capable model for nuanced image captions
    "caption": openai_udf(
        column="image",
        prompt="Provide a 1 sentence description of the scene",
        model="gpt-5",
        mime_type="image/jpeg",
    ),
})