@Logan M Extracting metadata from documents takes ~ 10 sec per document if I am using private openai. Is there a way to speed up the process? I have 76000 documents? I have business documents downloaded from confluence and would like to use llama_index to have the most accurate answers.
@Vimwork1 There's not really a way to speed it up right now 😅 Since most metadata extractors depend on calling the LLM to generate text
Which extractors are you using? I've been thinking of implementing more extractors that rely on faster local models -- right now, only the entity extractor runs locally (and if you have CUDA, it's very fast)
