LlamaIndex
Log in

Find answers from the community

Updated 2 months ago

I am using titleextractor for extracting

aadeelhasan
·
I am using titleextractor for extracting metadata by passing a document which contains 20 different pdf but i am getting same title for all the PDFs
L
1 comment
LLogan M
the title extractor only runs on the first 5 nodes, and the aggregates a single title 🤔

https://github.com/jerryjliu/llama_index/blob/f8c07e8eeb52cc774d9a6334effcbe4c132daef5/llama_index/node_parser/extractors/metadata_extractors.py#L205

You should probably process each PDF individually
Add a reply
Sign up and join the conversation on Discord