opendcai/dataflow-webui/text2multihopqa-generator

Text2MultiHopQAGenerator Operator Reference

Text2MultiHopQAGenerator reads one text column, generates up to num_q multi-hop QA pairs per input row, stores the per-row QA list in output_key, stores metadata in output_meta_key, then filters out rows whose generated QA list is empty.

See examples/good.md for a valid pipeline pattern and examples/bad.md for common failure cases.

1. Import

from dataflow.operators.core_text import Text2MultiHopQAGenerator

2. Constructor

Text2MultiHopQAGenerator(
    llm_serving=llm,
    seed=0,
    lang="en",
    prompt_template=None,
    num_q=5,
)

3. run() Signature

op.run(
    storage=self.storage.step(),
    input_key="cleaned_chunk",
    output_key="QA_pairs",
    output_meta_key="QA_metadata",
)

Return Value

The method returns [output_key].

4. Actual Runtime Logic

The source code behavior is:

1. Read the DataFrame from storage.
2. Validate that input_key exists.
3. Validate that output_key does not already exist.
4. Read all texts from dataframe[input_key].tolist().
5. Generate one example record per input row via process_batch(...).
6. Truncate each row's qa_pairs list to at most num_q.
7. Write QA lists to output_key and metadata dicts to output_meta_key.
8. Drop rows whose output_key is not a non-empty list.
9. Write the filtered DataFrame back to storage.
10. Return [output_key].

Important consequences:

• The operator does not expand one row into multiple rows.
• The final row count is less than or equal to the input row count.
• Rows with empty generated QA lists are removed entirely.

5. Text Filtering Rules

Inside ExampleConstructor, a text can fail before QA generation if:

• it is not a string,
• its length is less than 100,
• its length is greater than 200000,
• it fails the basic sentence-count or special-character quality checks.

When that happens, the row gets an empty qa_pairs list first, and is then filtered out by run().

6. Important Constraints

1. input_key must exist, otherwise run() raises ValueError.
2. output_key must not already exist, otherwise run() raises ValueError.