Did you know @CohereAI open-sourced 94 million vectors of Wikipedia embeddings from 10 languages? And @weaviate_io hosted 10 million of them to search for free?
With a few lines of code using @langchain you can retrieve them. But we face one issue, let's solve 🧵↓
NotebookLM is great, but what if I want to use my voice and add visuals from the PDF?
🚀Introducing Personalized Explainers — drop a PDF, and receive an explainer in your own voice that includes visuals, and images from the document.
This video is entirely AI-generated. 🔊
With this modified code, you can now upload documents in multiple formats (.pdf, .txt, .docx, .pptx, .jpg, .png, .eml, .html) and semantically search in 100+ languages supported by @CohereAI. Embeddings saved @qdrant_engine. Flask-backend uses @langchain. Code open-sourced.🧵👇
Let's build a @langchain agent in under 30 minutes that can access the internet, chat with a PDF, and help us understand code. All without a single line of code using @FlowiseAI and @bubble.
This agent will have access to 3 tools and a memory as shown. Tools explained in 🧵👇
An attempt to solve the LLM challenge by @karpathy
Built an LLM-based app using @langchain to go from a YouTube link to a nicely written markdown article. (still a work in progress)
Building Apps using Cursor + other AI tools
(something that's working for me lately)
Step 1/
- Generate UI - @v0
- Generate DB schema - Postgres .new by @supabase
- Index API Docs and any other docs based on the framework to build with ( could ask o-1 for help )
Deploy a PrivateGPT chat-with-documents app in less than 15 mins. PrivateGPT's focus on no-data leaks makes it ideal for enterprises and organizations. Built on @langchain, this app utilizes @huggingface embeddings and GPT4ALL for RetrievalQA. 🧵↴
What?! The Bolt .new repository is open-source!
How did I miss that part of the announcement?
This will be fun to learn from. Great work @stackblitz!
Repo link for your bookmarks ↓
Prob: There are too many AI papers to read (and a bit difficult to understand)
Sol: A PDF2Video explainer. Drop a PDF and get a well-explained video incl. text, images, equations, figures, etc. Uses @langchain, @UnstructuredIO, @DeepgramAI
1/ Attention is all you need:🔈🔊