Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Tiny corpora +
CacheType.memory
crashed withValueError: Columns must be same length as key
(and follow-on dtype issues).This PR hardens three spots:
build_noun_graph._extract_edges
edges
column intosource/target
viapd.DataFrame
, padding bad rows and dropping NaNs leading to no broadcast error.graph_to_dataframes
list
so the single-column assignment can’t broadcast-fail.prune_graph
astype(str)
onsource/target
before merges to avoidfloat64 vs object
mismatch.Related Issues
Closes #1983
Proposed Changes
graphrag/index/operations/build_noun_graph/build_noun_graph.py
graphrag/index/operations/graph_to_dataframes.py
graphrag/index/operations/prune_graph.py
tests/unit/indexing/graph/test_small_corpus_bug.py
Checklist
input/tiny.txt
) withIndexingMethod.Fast
&CacheType.memory
.Additional Notes
These fixes touch only the small-corpus edge-cases - normal pipelines are unaffected.
Heads-up: the prompt files have been altered, can be discarded. Shout if you’d
like them dropped or squashed.