SubQuestinQueryEngine returning KeyError

[Shwetha-Ricoh]

query_engine = SubQuestionQueryEngine.from_defaults(
query_engine_tools=query_engine_tools, response_synthesizer=response_synthesizer,
service_context=service_context,question_gen=question_gen,
) . I am trying to use SubQuestionQueryEngine using LLAMA 2 model and it throws .local/lib/python3.10/site-packages/llama_index/core/query_engine/sub_question_query_engine.py", line 234, in _aquery_subq
query_engine = self._query_engines[sub_q.tool_name]
KeyError: 'uber_10k' error , I tried using LLMQuestionGenerator with custom service context passed into it and played with number of maximum tokens but nothing helped to resolve the issue . So, if anyone could help me with this issue would be great.

[dosubot[bot]]

The KeyError: 'uber_10k' error indicates that the SubQuestionQueryEngine cannot find a query engine named uber_10k in its _query_engines dictionary. This usually means that the tool uber_10k is either not registered or not correctly initialized in the query_engine_tools sequence you're passing to SubQuestionQueryEngine. Here's how you can address this issue:

1. Verify Tool Registration: Make sure the uber_10k tool is correctly included in the query_engine_tools with the right name attribute.
2. Check Tool Initialization: Ensure that the query engine for uber_10k is properly initialized and included when creating the SubQuestionQueryEngine.
3. Consistency in Configuration: If the tool's name or initialization logic has changed, ensure these changes are applied consistently across your application.

If uber_10k is intended for use, confirming its registration and initialization should solve the problem. If it's not meant to be used, ensure no sub-questions are generated that require this tool. This might involve adjusting the LLMQuestionGenerator or its configuration to avoid generating sub-questions targeting uber_10k.

Details

Sources

• [Bug]: SubQuestionQueryEngine raises an error at line: query_engine = self._query_engines[sub_q.tool_name] KeyError:
• [Bug]: Static Value from Example Showing up in Sub Question Query Engine without using Example Data
• SubQuestionQueryEngine raises an error at line: query_engine = self._query_engines[sub_q.tool_name] KeyError: ''
• llama-index-core/llama_index/core/query_engine/sub_question_query_engine.py
• llama-index-core/llama_index/core/question_gen/prompts.py
• llama-index-legacy/llama_index/legacy/question_gen/prompts.py
• llama-index-core/llama_index/core/query_engine/init.py
• llama-index-legacy/llama_index/legacy/query_engine/sub_question_query_engine.py
• llama-index-core/llama_index/core/langchain_helpers/agents/tools.py

About Dosu
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosu.