run-llama/llama_index · error · ValueError
Invalid mode: {mode}
Error message
Invalid mode: {mode} What it means
Error "Invalid mode: {mode}" thrown in run-llama/llama_index.
Source
Thrown at llama-index-core/llama_index/core/postprocessor/node.py:360
query_str=query_bundle.query_str,
)
raw_pred = cast(str, raw_pred)
mode = self._parse_prediction(raw_pred)
logger.debug(f"> Postprocessor Predicted mode: {mode}")
if self.verbose:
print(f"> Postprocessor Predicted mode: {mode}")
if mode == "next":
all_nodes.update(get_forward_nodes(node, self.num_nodes, self.docstore))
elif mode == "previous":
all_nodes.update(
get_backward_nodes(node, self.num_nodes, self.docstore)
)
elif mode == "none":
pass
else:
raise ValueError(f"Invalid mode: {mode}")
sorted_nodes = sorted(all_nodes.values(), key=lambda x: x.node.node_id)
return list(sorted_nodes)
class LongContextReorder(BaseNodePostprocessor):
"""
Models struggle to access significant details found
in the center of extended contexts. A study
(https://arxiv.org/abs/2307.03172) observed that the best
performance typically arises when crucial data is positioned
at the start or conclusion of the input context. Additionally,
as the input context lengthens, performance drops notably, even
in models designed for long contexts.".
"""
@classmethod
def class_name(cls) -> str:View on GitHub (pinned to afd0fef371)
Solutions
- Use a valid mode for this postprocessor; check the class documentation for allowed values.
- Correct the mode argument.
When it happens
Trigger: Thrown at llama-index-core/llama_index/core/postprocessor/node.py:360 when the library encounters an invalid state.
Common situations: See trigger scenarios.
AI-assisted analysis of run-llama/llama_index@afd0fef371 (2026-08-15).
Data as JSON: /api/errors/a3323f233753634f.
Report an issue: GitHub.