[Bug]: Chain Of Table, KeyError: "None of [Int64Index([0, 2, 3], dtype='int64')] are in the [index]"

[ivrschool]

Bug Description

chain_of_table /chain_of_table.ipynb

KeyError                                  Traceback (most recent call last)
[<ipython-input-52-07d7650d1fac>](https://localhost:8080/#) in <cell line: 1>()
----> 1 query_engine.query(query)

9 frames
[/usr/local/lib/python3.10/dist-packages/llama_index/query_engine/custom.py](https://localhost:8080/#) in query(self, str_or_query_bundle)
     43             else:
     44                 query_str = str_or_query_bundle
---> 45             raw_response = self.custom_query(query_str)
     46             return (
     47                 Response(raw_response)

[<ipython-input-31-1105bee10f52>](https://localhost:8080/#) in custom_query(self, query_str)
     64             )
     65             raw_args = generate_args_chain.run(question=query_str)
---> 66             args, cur_table = schema_mappings[key].parse_args_and_call_fn(
     67                 cur_table, raw_args
     68             )

[<ipython-input-8-2d944fc15c94>](https://localhost:8080/#) in parse_args_and_call_fn(self, table, args)
     18         """引数を解析し、関数を呼び出す。"""
     19         args = self.parse_args(args)
---> 20         return args, self.fn(table, args)
     21 
     22     def generate_prompt_component(self, **kwargs: Any) -> QueryComponent:

[<ipython-input-19-7a80280de750>](https://localhost:8080/#) in fn(self, table, args)
     20         table = table.copy()
     21         # テーブルから行を選択
---> 22         table = table.loc[args]
     23         return table
     24 

[/usr/local/lib/python3.10/dist-packages/pandas/core/indexing.py](https://localhost:8080/#) in __getitem__(self, key)
   1071 
   1072             maybe_callable = com.apply_if_callable(key, self.obj)
-> 1073             return self._getitem_axis(maybe_callable, axis=axis)
   1074 
   1075     def _is_scalar_access(self, key: tuple):

[/usr/local/lib/python3.10/dist-packages/pandas/core/indexing.py](https://localhost:8080/#) in _getitem_axis(self, key, axis)
   1299                     raise ValueError("Cannot index with multidimensional key")
   1300 
-> 1301                 return self._getitem_iterable(key, axis=axis)
   1302 
   1303             # nested tuple slicing

[/usr/local/lib/python3.10/dist-packages/pandas/core/indexing.py](https://localhost:8080/#) in _getitem_iterable(self, key, axis)
   1237 
   1238         # A collection of keys
-> 1239         keyarr, indexer = self._get_listlike_indexer(key, axis)
   1240         return self.obj._reindex_with_indexers(
   1241             {axis: [keyarr, indexer]}, copy=True, allow_dups=True

[/usr/local/lib/python3.10/dist-packages/pandas/core/indexing.py](https://localhost:8080/#) in _get_listlike_indexer(self, key, axis)
   1430         axis_name = self.obj._get_axis_name(axis)
   1431 
-> 1432         keyarr, indexer = ax._get_indexer_strict(key, axis_name)
   1433 
   1434         return keyarr, indexer

[/usr/local/lib/python3.10/dist-packages/pandas/core/indexes/base.py](https://localhost:8080/#) in _get_indexer_strict(self, key, axis_name)
   6068             keyarr, indexer, new_indexer = self._reindex_non_unique(keyarr)
   6069 
-> 6070         self._raise_if_missing(keyarr, indexer, axis_name)
   6071 
   6072         keyarr = self.take(indexer)

[/usr/local/lib/python3.10/dist-packages/pandas/core/indexes/base.py](https://localhost:8080/#) in _raise_if_missing(self, key, indexer, axis_name)
   6128                 if use_interval_msg:
   6129                     key = list(key)
-> 6130                 raise KeyError(f"None of [{key}] are in the [{axis_name}]")
   6131 
   6132             not_found = list(ensure_index(key)[missing_mask.nonzero()[0]].unique())

KeyError: "None of [Int64Index([0, 2, 3], dtype='int64')] are in the [index]"

The base.py works for some query but some time it gives KeyError. Is there any fix to this yet?

Version

0.9.41

Steps to Reproduce

run: query_engine.query(query)

Relevant Logs/Tracbacks

No response

[tituslhy]

I have a similar error. I was running the code in "chain_of_table.ipynb" using LLaMA2-7bn but I got the error messages below: