The community member is trying to use the llama_packs-dense_x_retrieval package from LlamaHub and is unsure if it is a ready-to-use package or a template to build upon. They are interested in adding storage context for a vector store index, but are unsure if they should contribute it to the package or add it locally.
In the comments, another community member suggests that the package can be customized locally and provides a link to an example. Another community member encountered an error when parsing the text to a list of strings and is unsure about the purpose of this parsing. The original author of the package suggests that the parsing code may be prone to errors, but it worked well in their testing with OpenAI. The community members discuss the impact of using the output for the proposition directly instead of parsing it to a list of strings.
Hi, I'm trying to use https://llamahub.ai/l/llama_packs-dense_x_retrieval?from=llama_packs I wonder the llama_packs is a ready to use package, or is it more like a template that we can build on? For example I like to add storage context for vector store index, but not sure if I should contribute it to the llama_pack or just add the code locally.
hi @Logan M , sorry for bothering. I just try the dense_x_retrieval llama pack. I got an error where parsing the text to list[str] is not correct. I'm not sure the purpose of parsing the response to a list[str] instead of a str. Could you elaborate a bit? The parsing code seems prone to errors.
