Data

Tools

Indexes

Applications

Experiments

Repos

An open API service providing repository metadata for many open source software ecosystems.

GitHub topics: context-curation

Daethyra/context-converter

Curate scraped HTML for large language models. Build more robust generative AI applications. Convert HTML to Markdown using Regex, BeautifulSoup4, and filter useless content with Jina Embeddings.

Language: Python - Size: 93.8 KB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 1 - Forks: 0

Related Keywords
ai-assistant 1 asynchronous 1 context-converter 1 context-curation 1 converter 1 curation 1 custom-gpt 1 embeddings 1 html 1 jina 1 llm 1 markdown 1 regex 1 retrieval-augmented-generation 1 similarity-score 1 similarity-threshold 1