Hugging Face's logo
Clelia Astra Bertelli's picture
12 13 135

Clelia Astra Bertelli

as-cle-bert
Sanshi444's profile picture Illusionrealistic's profile picture lakshay007's profile picture
ยท
https://www.clelia.dev

AI & ML interests

Biology + Artificial Intelligence = โค๏ธ | AI for sustainable development, sustainable development for AI | Researching on Machine Learning Enhancement | I love automation for everyday things | Blogger | Open Source

Recent Activity

liked a model about 1 month ago
facebook/dinov2-small
posted an update 6 months ago
Let's pipe some ๐—ฑ๐—ฎ๐˜๐—ฎ ๐—ณ๐—ฟ๐—ผ๐—บ ๐˜๐—ต๐—ฒ ๐˜„๐—ฒ๐—ฏ into our vector database, shall we?๐Ÿค  With ๐ข๐ง๐ ๐ž๐ฌ๐ญ-๐š๐ง๐ฒ๐ญ๐ก๐ข๐ง๐  ๐ฏ๐Ÿ.๐Ÿ‘.๐ŸŽ (https://github.com/AstraBert/ingest-anything) you can now scrape content simply starting from URLs, extract the text from it, chunk it and put it into your favorite LlamaIndex-compatible database!๐Ÿ•ธ๏ธ You can do it thanks to ๐—ฐ๐—ฟ๐—ฎ๐˜„๐—น๐—ฒ๐—ฒ by Apify, an open-source crawling library for python and javascript that handles all the data flow from the web: ingest-anything then combines it with ๐—•๐—ฒ๐—ฎ๐˜‚๐˜๐—ถ๐—ณ๐˜‚๐—น๐—ฆ๐—ผ๐˜‚๐—ฝ, ๐—ฃ๐—ฑ๐—ณ๐—œ๐˜๐——๐—ผ๐˜„๐—ป and ๐—ฃ๐˜†๐— ๐˜‚๐—ฃ๐—ฑ๐—ณ to scrape HTML files, convert them to PDF and extract the text - hassle-free!๐Ÿ˜ธ Check the attached code snippet if you're curious of knowing how to get started๐ŸŽฌ PS: Don't tell anybody, but this release also has another gem... It supports OpenAI models for agentic chunking, following the new releases of Chonkie๐Ÿฆ›โœจ If you don't want to miss out on the new features, leave us a little star on GitHub โžก๏ธ https://github.com/AstraBert/ingest-anything And join our discord community! โžก๏ธ https://discord.gg/kDqHNjks
posted an update 7 months ago
Hey there, ๐—ถ๐—ป๐—ด๐—ฒ๐˜€๐˜-๐—ฎ๐—ป๐˜†๐˜๐—ต๐—ถ๐—ป๐—ด ๐˜ƒ๐Ÿญ.๐Ÿฌ.๐Ÿฌ just dropped with major changes: โœ… Embeddings: now works with Sentence Transformers, Jina AI, Cohere, OpenAI, and Model2Vec All powered via ๐—–๐—ต๐—ผ๐—ป๐—ธ๐—ถ๐—ฒโ€™๐˜€ ๐—”๐˜‚๐˜๐—ผ๐—˜๐—บ๐—ฏ๐—ฒ๐—ฑ๐—ฑ๐—ถ๐—ป๐—ด๐˜€. No more local-only limitations ๐Ÿ™Œ โœ… Vector DBs: now supports ๐—ฎ๐—น๐—น ๐—Ÿ๐—น๐—ฎ๐—บ๐—ฎ๐—œ๐—ป๐—ฑ๐—ฒ๐˜…-๐—ฐ๐—ผ๐—บ๐—ฝ๐—ฎ๐˜๐—ถ๐—ฏ๐—น๐—ฒ ๐—ฏ๐—ฎ๐—ฐ๐—ธ๐—ฒ๐—ป๐—ฑ๐˜€ Think: Qdrant, Pinecone, Weaviate, Milvus, etc. No more bottlenecks๐Ÿ”“ โœ… File parsing: now plugs into any ๐—Ÿ๐—น๐—ฎ๐—บ๐—ฎ๐—œ๐—ป๐—ฑ๐—ฒ๐˜…-๐—ฐ๐—ผ๐—บ๐—ฝ๐—ฎ๐˜๐—ถ๐—ฏ๐—น๐—ฒ ๐—ฑ๐—ฎ๐˜๐—ฎ ๐—น๐—ผ๐—ฎ๐—ฑ๐—ฒ๐—ฟ Using LlamaParse, Docling or your own setup? Youโ€™re covered. Curious of knowing more? Try it out! ๐Ÿ‘‰ https://github.com/AstraBert/ingest-anything
View all activity

Organizations

Social Post Explorers's profile picture Hugging Face Discord Community's profile picture GreenFit AI's profile picture