search

GuGuskyastro / Scientific-conference-title-disambiguation-system-based-on-GPT-and-Wikidata

This project uses langchain to formulate workflows for GPT and pre-creates WeaviateVS to store information for scientific meetings in Wikidata. Use GPT to parse the input text, compare the VS query results, and finally obtain the metadata of the conference extracted by GPT through Wikidata.
0 stars 1 forks source link

Structure the natural language results of GPT (computer readable) #10

Open GuGuskyastro opened 1 year ago

GuGuskyastro commented 1 year ago

The current running result is the natural language output by GPT, which will be difficult to test or display in the web page. The result should be converted into a computer-readable form.

GuGuskyastro commented 1 year ago

https://github.com/GuGuskyastro/Scientific-conference-title-disambiguation-system-based-on-GPT-and-Wikidata/commit/8f55650f7e066a29f99981566ea1d617bd01c9f4 Add a method for structured GPT output. Using generate_result() will directly generate the yaml format result corresponding to the input text.

GuGuskyastro commented 1 year ago

https://github.com/GuGuskyastro/Scientific-conference-title-disambiguation-system-based-on-GPT-and-Wikidata/commit/3f4246f9b35481ee73e7aeb61a15c3f070c25def https://github.com/GuGuskyastro/Scientific-conference-title-disambiguation-system-based-on-GPT-and-Wikidata/commit/60473cd811776c53e8341f90a9eceae1ac32d2c4 Restructured the natural language results of the test output , computer readable.