Knowledgator Docs
GitHubDiscord
  • 🛎️Welcome
  • ⚙️Models
    • 🧮Comprehend-it
      • Comprehend_it-base
      • Comprehend_it-multilingual-t5-base
    • 🦎UTC
  • 👷Frameworks
    • 💧LiqFit
      • Quick Start
      • Benchmarks
      • API Reference
        • Collators
          • NLICollator
          • Creating custom collator
        • Datasets
          • NLIDataset
        • Losses
          • Focal Loss
          • Binary Cross Entropy
          • Cross Entropy Loss
        • Modeling
          • LiqFitBackbone
          • LiqFitModel
        • Downstream Heads
          • LiqFitHead
          • LabelClassificationHead
          • ClassClassificationHead
          • ClassificationHead
        • Pooling
          • GlobalMaxPooling1D
          • GlobalAbsAvgPooling1D
          • GlobalAbsMaxPooling1D
          • GlobalRMSPooling1D
          • GlobalSumPooling1D
          • GlobalAvgPooling1D
          • FirstTokenPooling1D
        • Models
          • Deberta
          • T5
        • Pipelines
          • ZeroShotClassificationPipeline
  • 📚Datasets
    • Biotech news dataset
  • 👩‍🔧Support
  • API Reference
    • Comprehend-it API
    • Entity extraction
      • /fast
      • /deterministic
      • /advanced
    • Token searcher
    • Web2Meaning
    • Web2Meaning2
    • Relation extraction
    • Text2Table
      • /web2text
      • /text_preprocessing
      • /text2table
      • /merge_tables
Powered by GitBook
On this page
  1. API Reference

Text2Table

PreviousRelation extractionNext/web2text

Last updated 1 year ago

Text-to-table structuring

Fast and accurate structuring of information from any text to table format. You are just required to put column names and text itself, and the tool will return to you a structured table according to your request. The API can automate the manual work of dealing with unstructured text and help you build required databases in minutes instead of hours or even days of human work.

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

​ - converts unstructured text into a structured table format. Simply provide the table column names and receive a tailored table formed from the input text. - 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 model.​ - the Web2Text API serves as an alternative to the endpoint, but instead extracting text directly from a web page. - 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 request.

/text2table
/text_preprocessing
text2table
/web2text
text_preprocessing
/pdf2text
/text2table