run-llama / llama-hub

A library of data loaders for LLMs made by the community -- to be used with LlamaIndex and/or LangChain
https://llamahub.ai/
MIT License
3.44k stars 731 forks source link

[Bug]: llm_compiler.ipynb asked about Houston, returns Boston data? #823

Open oaustegard opened 8 months ago

oaustegard commented 8 months ago

Bug Description

llama_hub/llama_packs/agents/llm_compiler/llm_compiler.ipynb

In the RAG, Test Out Queries paragraphs the question asked is "Tell me about the demographics of Houston, and compare that with the demographics of Chicago?"

Yet the data returned is for Chicago and Boston, not Houston, then it proceeds to answer as if the context is actually from the Houston wiki entry

Version

NA

Steps to Reproduce

See https://github.com/run-llama/llama-hub/blob/main/llama_hub/llama_packs/agents/llm_compiler/llm_compiler.ipynb

Relevant Logs/Tracbacks

NA
oaustegard commented 8 months ago

arguably more a problem with VectorStoreIndex than llm_compiler