Видео

Most concise explanation - thank you

Thank you, Clemens, very helpful! Keep them coming :)

can we use this to compare a resume to a qualification?

Hello. I want to use Chatgbt4 Turbo vision for my application however I am not sure about the charges I am paying the way of calculation is very confusing to me. Does anyone know for sure what is paid on Azure open ai for using the Chatgbt 4 Turbo vision model, is it just spent tokens or something extra,host? Thank you

Is it only supported for round robin only ?

Thanks for this video. May i know what is the user hit limt for 240k token. (Per second or per minute)

you still use openai embedding, not azure openai embedding service right?

🎯 Key Takeaways for quick navigation: 00:13 📚 Embeddings in Azure OpenAI Service: Embeddings are tools used to measure the relatedness of two strings, such as words, sentences, or documents. They are versatile and can be used for semantic search, clustering, recommendations, anomaly detection, diversity measurement, and classification. 01:22 📦 Supported Embedding Models: In Azure OpenAI Service, the primary model for embeddings is the "text-embeddings" model, introduced by OpenAI. It's powerful and cost-effective for various use cases. 02:02 🔑 Getting Started with Embeddings: To use embeddings in Azure OpenAI Service, you need to authenticate, set up the API base, and initialize your embeddings model. You should also adjust the "chunk size" to 1 for single embedding calculations. 05:05 🧩 Comparing Text with Embeddings: You can compare the similarity between two pieces of text by calculating the cosine similarity between their embeddings. This allows you to measure relatedness between strings. 09:27 🎥 Building a Recommendation System: Embeddings can be used to create recommendation systems. By comparing the embeddings of items, you can recommend similar items to users based on their preferences. 13:28 🌎 Visualizing Embeddings: Embeddings can be visualized in a multidimensional space, revealing clusters that represent relatedness. This can help gain insights into the relationships between various entities, like cities in different regions. Made with HARPA AI

loved this video, just so clean and easily understandable. Earned yourself a sub. Waiting for other videos to drop.

I have searched and watched many videos, but the more I search the more confused I get. I hope you can point me to some information that will save my sanity. I think my idea is very basic, and a very common use case, but I cannot find examples or implementations of it. I have a text document of about 50 pages, which can be bigger and can be smaller. I want to give users the ability to "chat" with the document. I would prefer that the data does not go into the public realm. I would prefer to build a tool for this using c# without Azure services. Is this possible? It must be, so please save my sanity! :)

Thanks Clemens. This was a great video. Ideas for next video: compare embeddings for top 3 ranking articles on the topic of 'dental implants risks'. Google has a patent that looks for similarity of articles. They use embedding models as well. It would be interesting to see how similar the top articles are.

I would like to see a similar video, but classify files from the filenames in an input folder, and put them into a different folders subfolders where the name of the subfolders is the classification list to sort them into. (ex. AI, AI LLMs, AI Art, AI Tools, Health, FPGA, Crypto, etc) I'll use this to classify videos I've downloaded, into categories that I'll watch later by category. = A similar thing would be to classify screenshots from videos I watch into a similar categories of subfolders like above example, but the text to classify would have to come from OCR of the Images. Love your Channel.

very helpful and concise. Looking forward to more content :-)