Clelia Astra Bertelli

as-cle-bert

https://www.cleliasportfolio.xyz

AI & ML interests

Recent Activity

posted an update 1 day ago

Let's pipe some 𝗱𝗮𝘁𝗮 𝗳𝗿𝗼𝗺 𝘁𝗵𝗲 𝘄𝗲𝗯 into our vector database, shall we?🤠 With 𝐢𝐧𝐠𝐞𝐬𝐭-𝐚𝐧𝐲𝐭𝐡𝐢𝐧𝐠 𝐯𝟏.𝟑.𝟎 (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!🕸️ You can do it thanks to 𝗰𝗿𝗮𝘄𝗹𝗲𝗲 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 𝗕𝗲𝗮𝘂𝘁𝗶𝗳𝘂𝗹𝗦𝗼𝘂𝗽, 𝗣𝗱𝗳𝗜𝘁𝗗𝗼𝘄𝗻 and 𝗣𝘆𝗠𝘂𝗣𝗱𝗳 to scrape HTML files, convert them to PDF and extract the text - hassle-free!😸 Check the attached code snippet if you're curious of knowing how to get started🎬 PS: Don't tell anybody, but this release also has another gem... It supports OpenAI models for agentic chunking, following the new releases of Chonkie🦛✨ If you don't want to miss out on the new features, leave us a little star on GitHub ➡️ https://github.com/AstraBert/ingest-anything And join our discord community! ➡️ https://discord.gg/kDqHNjks

posted an update 10 days ago

Hey there, 𝗶𝗻𝗴𝗲𝘀𝘁-𝗮𝗻𝘆𝘁𝗵𝗶𝗻𝗴 𝘃𝟭.𝟬.𝟬 just dropped with major changes: ✅ Embeddings: now works with Sentence Transformers, Jina AI, Cohere, OpenAI, and Model2Vec All powered via 𝗖𝗵𝗼𝗻𝗸𝗶𝗲’𝘀 𝗔𝘂𝘁𝗼𝗘𝗺𝗯𝗲𝗱𝗱𝗶𝗻𝗴𝘀. No more local-only limitations 🙌 ✅ Vector DBs: now supports 𝗮𝗹𝗹 𝗟𝗹𝗮𝗺𝗮𝗜𝗻𝗱𝗲𝘅-𝗰𝗼𝗺𝗽𝗮𝘁𝗶𝗯𝗹𝗲 𝗯𝗮𝗰𝗸𝗲𝗻𝗱𝘀 Think: Qdrant, Pinecone, Weaviate, Milvus, etc. No more bottlenecks🔓 ✅ File parsing: now plugs into any 𝗟𝗹𝗮𝗺𝗮𝗜𝗻𝗱𝗲𝘅-𝗰𝗼𝗺𝗽𝗮𝘁𝗶𝗯𝗹𝗲 𝗱𝗮𝘁𝗮 𝗹𝗼𝗮𝗱𝗲𝗿 Using LlamaParse, Docling or your own setup? You’re covered. Curious of knowing more? Try it out! 👉 https://github.com/AstraBert/ingest-anything

posted an update 11 days ago

One of the biggest challenges I've been facing since I started developing [𝐏𝐝𝐟𝐈𝐭𝐃𝐨𝐰𝐧](https://github.com/AstraBert/PdfItDown) was handling correctly the conversion of files like Excel sheets and CSVs: table conversion was bad and messy, almost unusable for downstream tasks🫣 That's why today I'm excited to introduce 𝐫𝐞𝐚𝐝𝐞𝐫𝐬, the new feature of PdfItDown v1.4.0!🎉 With 𝘳𝘦𝘢𝘥𝘦𝘳𝘴, you can choose among three (for now👀) flavors of text extraction and conversion to PDF: - 𝗗𝗼𝗰𝗹𝗶𝗻𝗴, which does a fantastic work with presentations, spreadsheets and word documents🦆 - 𝗟𝗹𝗮𝗺𝗮𝗣𝗮𝗿𝘀𝗲 by LlamaIndex, suitable for more complex and articulated documents, with mixture of texts, images and tables🦙 - 𝗠𝗮𝗿𝗸𝗜𝘁𝗗𝗼𝘄𝗻 by Microsoft, not the best at handling highly structured documents, by extremly flexible in terms of input file format (it can even convert XML, JSON and ZIP files!)✒️ You can use this new feature in your python scripts (check the attached code snippet!😉) and in the command line interface as well!🐍 Have fun and don't forget to star the repo on GitHub ➡️ https://github.com/AstraBert/PdfItDown

View all activity

Organizations

Posts 47

Post

2374

Let's pipe some 𝗱𝗮𝘁𝗮 𝗳𝗿𝗼𝗺 𝘁𝗵𝗲 𝘄𝗲𝗯 into our vector database, shall we?🤠

With 𝐢𝐧𝐠𝐞𝐬𝐭-𝐚𝐧𝐲𝐭𝐡𝐢𝐧𝐠 𝐯𝟏.𝟑.𝟎 (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!🕸️

You can do it thanks to 𝗰𝗿𝗮𝘄𝗹𝗲𝗲 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 𝗕𝗲𝗮𝘂𝘁𝗶𝗳𝘂𝗹𝗦𝗼𝘂𝗽, 𝗣𝗱𝗳𝗜𝘁𝗗𝗼𝘄𝗻 and 𝗣𝘆𝗠𝘂𝗣𝗱𝗳 to scrape HTML files, convert them to PDF and extract the text - hassle-free!😸

Check the attached code snippet if you're curious of knowing how to get started🎬

PS: Don't tell anybody, but this release also has another gem... It supports OpenAI models for agentic chunking, following the new releases of Chonkie🦛✨

If you don't want to miss out on the new features, leave us a little star on GitHub ➡️ https://github.com/AstraBert/ingest-anything
And join our discord community! ➡️ https://discord.gg/kDqHNjks

View all Posts