Jina AI examples VS videos

- Modern PDFs - if you wanna extract text and images, then the PDFSegmenter used in my example will work. If tables too, might need some additional jiggery-pokery, but definitely doable. I know other ppl using the same framework (Jina) who've accomplished it.

- Exact word search - pretty simple. I've focused on more advanced stuff because color vs colour is same same but different. Also just because it's pretty easy since I'm just using pre-defined building blocks, not manually integrating stuff

- Cross platform frontend - I've seen a lyrics search frontend [0] and I've built stuff in Streamlit before. Jina offers RESTful/gRPC/WebSockets gateways so it can't be too tough

- Lightweight? I mean how lightweight do you want it? C? Bash? Assembly? I've found Python good for text parsing

- Long-term: The notebook I wrote has a few (each of which have their own), but compared to others they're relatively lightweight.

- Gluing code: I've been using pre-existing building blocks, and writing new Executors (i.e. building blocks) is relatively straightforward, and then scaling them up with shards, replicas, etc is just a parameter away.

I'm more into the search side then the PDF stuff. The PDF side I've had experience with through bitter suffering and torment. Not a fun format to work with (unless you're into sado-masochism)

[0] https://github.com/jina-ai/examples/tree/master/multires-lyr...

Semantic Wikipedia Search

I was looking for some projects based on search engines, and building a tool which could search across various types of data, and that's when I came across this GitHub project: https://github.com/jina-ai/jina/blob/master/.github/pages/hello-world.md#-multimodal-document-search. Encouraged by thorough, step by step instructions on how to build a search service that can use diverse modal features to provide accurate results; I ventured through the documents till I came to the latest updated version, here: https://github.com/jina-ai/examples/tree/master/cross-modal-search.

There are already some examples on music search, pdf search and video search that shows some POC of it's capabilities around those use cases. You can discuss your specific use case in detail with Jina community on slack

Thank you so much for the appreciation and sharing your use cases. Checkout examples for chatbot and financial analysis - https://github.com/jina-ai/examples

git clone --depth 1 --filter=blob:none --sparse https://github.com/jina-ai/examples git sparse-checkout set multimodal-search-pdf

Hey all, I am trying to build my home server to have nextcloud to store most of my stuff. I started the journey without any significant knowledge about hosting. So far: * I got a domain name. I moved the nameservers to Cloudflare. * Got to know that ipv4 was being blocked by ISP for port forwarding but ipv6 wasn't. So opened the ports on ipv6 address. Checked the open ports of public ipv6 address and they were showing open. * I installed the Nginx Proxy Manager along with Nextcloud on Docker by following the following tutorial: https://www.youtube.com/watch?v=iFHbzWhKfuU&list=LL&index=2&t=457s The docker file is in here: https://github.com/christianlempa/videos/tree/main/nextcloud-tutorial

I grabbed this guys info and found that he put a more stuff into npms env. I pretty much worked from his compose file, but I ran into a issue with adding networks to the npm... not sure of the exact syntax. been trying all kinds of different ways the past 30 minutes to plug in a network. finally said fuck it and just ran it without a network. gonna try and add them retroactively from portainer.

Which can be found here: https://github.com/christianlempa/videos/tree/main/nginxproxymanager-tutorial