run-llama/llama_index · error · ValueError
Query bundle must be provided.
Error message
Query bundle must be provided.
What it means
Error "Query bundle must be provided." thrown in run-llama/llama_index.
Source
Thrown at llama-index-core/llama_index/core/postprocessor/llm_rerank.py:118
) -> List[NodeWithScore]:
raw_choices, relevances = self._parse_choice_select_answer_fn(
raw_response, len(nodes_batch)
)
choice_idxs = [int(choice) - 1 for choice in raw_choices]
choice_nodes = [nodes_batch[idx] for idx in choice_idxs]
relevances = relevances or [1.0 for _ in choice_nodes]
return [
NodeWithScore(node=node, score=relevance)
for node, relevance in zip(choice_nodes, relevances)
]
def _postprocess_nodes(
self,
nodes: List[NodeWithScore],
query_bundle: Optional[QueryBundle] = None,
) -> List[NodeWithScore]:
if query_bundle is None:
raise ValueError("Query bundle must be provided.")
if len(nodes) == 0:
return []
initial_results: List[NodeWithScore] = []
for nodes_batch in self._get_node_batches(nodes):
# call each batch independently
raw_response = self.llm.predict(
self.choice_select_prompt,
**self._get_predict_kwargs(nodes_batch, query_bundle.query_str),
)
initial_results.extend(self._parse_raw_response(raw_response, nodes_batch))
return sorted(initial_results, key=lambda x: x.score or 0.0, reverse=True)[
: self.top_n
]
async def _apostprocess_nodes(
self,View on GitHub (pinned to afd0fef371)
Solutions
- Pass a query_bundle when calling the LLMRerank postprocessor.
- Ensure the query bundle is forwarded through the query engine pipeline.
When it happens
Trigger: Thrown at llama-index-core/llama_index/core/postprocessor/llm_rerank.py:118 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/6308c5f4c19bbdd5.
Report an issue: GitHub.