* [Document Metadata for Higher Accuracy Retrieval](https://betterprogramming.pub/building-production-ready-llm-apps-with-llamaindex-document-metadata-for-higher-accuracy-retrieval-a8ceca641fb5) https://twitter.com/manelferreira_/status/1711788180603896204 https://gpt-index.readthedocs.io/en/stable/module_guides/loading/documents_and_nodes/usage_metadata_extractor.html https://gpt-index.readthedocs.io/en/stable/examples/metadata_extraction/MetadataExtraction_LLMSurvey.html https://gpt-index.readthedocs.io/en/latest/examples/metadata_extraction/PydanticExtractor.html https://docs.llamaindex.ai/en/stable/examples/metadata_extraction/MetadataExtractionSEC.html langchain 的實驗 https://blog.langchain.dev/extraction-benchmarking/ GPT-4 function calling 最好 實體識別 NER, 關係識別 RE, 事件識別 EE paper: https://twitter.com/omarsar0/status/1743661688526639468 ## langchain parallel function calling https://blog.langchain.dev/parallel-function-calling-extraction/ ## llamaindex * MultiDocAutoRetrieverPack * https://twitter.com/llama_index/status/1739307699773518201 ## Awesome LLM JSON List https://github.com/imaurer/awesome-llm-json