Muennighoff/sgpt
SGPT: GPT Sentence Embeddings for Semantic Search
This project helps developers enhance search functionality within their applications by transforming text into meaningful numerical representations called sentence embeddings. It takes raw text inputs and processes them into embeddings, which can then be used to find semantically similar documents, even if they don't share keywords. A machine learning engineer or data scientist working on search systems would use this to improve relevance and performance.
873 stars. No commits in the last 6 months.
Use this if you are a developer or data scientist building search or recommendation engines and need to efficiently find text that is conceptually similar to a query, even with different wording.
Not ideal if you are looking for a ready-to-use search engine or a simple keyword-matching tool, as this requires integration into a larger system.
Stars
873
Forks
52
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 17, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/Muennighoff/sgpt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Azure-Samples/azure-ai-document-processing-samples
A collection of samples demonstrating techniques for processing documents with Azure AI...
artitw/text2text
Text2Text Language Modeling Toolkit
aiplanethub/beyondllm
Build, evaluate and observe LLM apps
build-on-aws/langchain-embeddings
This repository demonstrates the construction of a state-of-the-art multimodal search engine,...
qianniuspace/llm_notebooks
AI 应用示例合集