Find answers from the community

Updated 2 months ago

Does anyone know how llama index uses

Does anyone know how llama index uses UnstructeedReader’s elements to do RAG? i.e how are table and image elements treated? any pointers to code i can read would be fine too
L
V
4 comments
right now there isn't really too much special handling

a) the unstructured loader code is here
https://github.com/run-llama/llama-hub/blob/ec27ff1056d85e84197499eab67892031db50f7c/llama_hub/file/unstructured/base.py#L51

b) there is some special handling for tables in the unstructured element node parser
https://github.com/run-llama/llama_index/blob/16f444ce760c89d8cc86cfe2cfc7b9e0cd45ce29/llama_index/node_parser/relational/unstructured_element.py#L98

In general, any contributions to either would definitely be welcome 🙂
Add a reply
Sign up and join the conversation on Discord