What are the key differences between index.as_query_engine() vs index.as_chat_engine()? I used my one pager bio as the document and compared these two with a few well known LLMs. I asked a few questions about myself via the one pager. The results are very different between them. The index.as_query_engine() approach did generally well with all these LLMs. However, index.as_chat_engine() has huge hallucination problem. Can someone provide insight about the huge differences?

Can someone point me to an example of querying a PDF document? Thanks.

@Logan M I ran the following statement. It worked on one Windows PC but failed on another Windows PC.

Settings.embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")

On the Windows PC that failed, it has the following error message:

FileNotFoundError: [Errno 2] No such file or directory: 'C:\Users\me\AppData\Local\llama_index\models--BAAI--bge-small-en-v1.5\snapshots\5c38ec7c405ec4b44b94cc5a9bb96e735b38267a\config.json'

In fact, on the AppData\Local directory, there is no llama_index folder. Could you please provide ideas for debugging? Thanks.

To upgrade all Llama-Index packages, do I just do "pip install -U llama-index"? Or I have to upgrade the sub-packages too? Thanks.

Please update the docs on ServiceContext. Thank you.