Text2Table

Text-to-table structuring

Key features

  • Web and PDF scraping - extraction of text and tables from web pages and PDF resources for future analysis by LLMs;

  • Tables construction - building table from text according to response;

  • Merging tables - an intelligent combination of several tables into a single one;

API endpoints

/text2table - converts unstructured text into a structured table format. Simply provide the table column names and receive a tailored table formed from the input text. /text_preprocessing - the pre-processing endpoint is designed to prepare your text data for the /text2table transformation. It is required when dealing with large texts that exceed the 3900 token limit of the text2table model.​/web2text - the Web2Text API serves as an alternative to the text_preprocessing endpoint, but instead extracting text directly from a web page. /pdf2text - route for preprocessing PDF files. It gets text from specified pages of the provided file and splits the text into chunks if needed to prevent truncation at the /text2table request.

Last updated