yaminivibha/LLM_InformationRetrieval
extracting "structured" information that is embedded in natural language text on the web using iterative set expansion, spanBERT, and openAI API
This project helps you find specific pieces of factual information embedded in natural language text across various webpages. You provide an example of the information you're looking for, and it returns a list of similar factual statements. It's designed for anyone needing to systematically extract structured data, such as personal affiliations or employment, from unstructured web content.
No commits in the last 6 months.
Use this if you need to extract specific types of relationships, like who attended which school or who works for which company, from a large number of web pages.
Not ideal if you need to extract highly nuanced information, require extremely high precision, or work with text that is not publicly accessible on the web.
Stars
17
Forks
3
Language
Python
License
—
Category
Last pushed
May 22, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/yaminivibha/LLM_InformationRetrieval"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
google/langextract
A Python library for extracting structured information from unstructured text using LLMs with...
Extralit/extralit
Fast and accurate systemic data extraction with LLM assistance
Keyvanhardani/german-ocr
German-OCR is specifically trained to extract text from German documents including invoices,...
oidlabs-com/Lexoid
Multimodal document parser for high quality data understanding and extraction
xingbow/SciDaEx
Structured data extraction from research literature