diff --git a/src/ragas/testset/transforms/default.py b/src/ragas/testset/transforms/default.py index 3c5f3da46..5a2454f31 100644 --- a/src/ragas/testset/transforms/default.py +++ b/src/ragas/testset/transforms/default.py @@ -74,13 +74,13 @@ def filter_docs(node): def filter_chunks(node): return node.type == NodeType.CHUNK - bin_ranges = [(0, 100), (101, 500), (501, 100000)] + bin_ranges = [(0, 100), (101, 500), (501, float("inf"))] result = count_doc_length_bins(documents, bin_ranges) result = {k: v / len(documents) for k, v in result.items()} transforms = [] - if result["501-100000"] >= 0.25: + if result["501-inf"] >= 0.25: headline_extractor = HeadlinesExtractor( llm=llm, filter_nodes=lambda node: filter_doc_with_num_tokens(node) )