Ask a question in plain language about a data frame, using a table question-answering model (such as TAPAS) via the Hugging Face Inference Providers API. The data frame is converted to the string-cell format the API expects; all values are coerced to character.
Usage
hf_table_question_answer(
query,
table,
model = hf_default_model("table_question_answer"),
token = NULL,
endpoint_url = NULL,
...
)Arguments
- query
Character vector of question(s) to ask about the table.
- table
A data frame to query.
- model
Character string. Model ID from the Hugging Face Hub. Append `":provider"` to select an inference provider. Default: "google/tapas-base-finetuned-wtq".
- token
Character string or NULL. API token for authentication.
- endpoint_url
Character string or NULL. A custom Inference Endpoint URL.
- ...
Additional arguments (currently unused).
Value
A tibble with columns: query, answer, aggregator, cells (a list-column of the source cells the answer was drawn from).
Examples
if (FALSE) { # \dontrun{
sales <- data.frame(
product = c("Widgets", "Gadgets", "Gizmos"),
revenue = c(120, 80, 50)
)
hf_table_question_answer("Which product had the highest revenue?", sales)
hf_table_question_answer("What is the total revenue?", sales)
} # }