Can i call property graph index extractors directly on a document
Can i call property graph index extractors directly on a document
At a glance
The community member is trying to use the DynamicLLMPathExtractor from the PropertyGraphIndex library, but is having trouble getting it to work as expected. They tried calling the extractor directly on a document, but only got a node with the document text and no additional nodes or relations. The comments suggest that the community member has tried chunking the document into nodes using a SentenceSplitter, and has also tried different extractors and documents, but is still not getting the expected results.
The community members discuss potential reasons for the issue, such as the choice of language model (Haiku vs Sonnet) and the starting entity types provided to the DynamicLLMPath extractor. They suggest that the Haiku model may be struggling and that some tweaking may be required to get the desired results.
Hi, for PropertyGraphIndex's many extractors (WLOG DynamicLLMPathExtractor), can I call them directly on a Document since they are just transforms? I see that that's whats happening under the hood when I insert them but when I call them directly, I'm just getting a node back with the document text and no additional nodes and relations.
Thank you for the clarifications! Very helpful <3! I think I'm just surprised to see that the DynamicLLMPath didn't pick up anything for so many documents that I've been trying.
Haiku right now. I'll try switching to Sonnet to test it. The DynamicLLMPath was also given starting entity types so maybe that is why? Haiku is also worse than Sonnet.
