We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
{ "id": "0", "label": "Person", "properties": "{'name': 'Duke Leto Atreides'}" }
{ "id": "0", "label": "Person", "properties": {'name': 'Duke Leto Atreides'} }
neo4j_graphrag/experimental/components/entity_relation_extractor.py
Have to remove double quotes from LLMEntityRelationExtractor.extract_for_chunk when some LLM model is not able to generate nested JSON ojbect:
llm_result.content = llm_result.content.replace('''"{''', "{").replace('''}"''', "}")
The text was updated successfully, but these errors were encountered:
Hi @thimoonxy ,
Thanks for bringing this issue to us. This is part of a broader problem, when the LLM is not able to generate JSON in the format we expect.
We're planning to improve this behavior.
Unfortunaly for now, there is not so much you can do except trying to implement your own EntityRelationExtractor component.
EntityRelationExtractor
Sorry, something went wrong.
No branches or pull requests
Backgroud
LLM outputs
Expected output
Locate src file
neo4j_graphrag/experimental/components/entity_relation_extractor.py
Try to fix
Have to remove double quotes from LLMEntityRelationExtractor.extract_for_chunk
when some LLM model is not able to generate nested JSON ojbect:
Any other proper ways to fix this ?
The text was updated successfully, but these errors were encountered: