Azure RAG plans raise practical cost questions
The planned RAG system would use a public website as its , including PDFs and other fact sheets. The first step would be to extract web pages and save their content as plain text.
The text would then be vectorized so it can be searched by meaning rather than only by exact words. A would create those searchable representations.
and a Foundry model would then be used to retrieve relevant material and generate answers. The main open questions are which Azure services to use, what kinds of costs appear in real projects, and which resources or documents are useful during development.
Key points
- The would come from a public website with PDFs and fact sheets.
- The plan is to extract web content and store it as plain text.
- The stored text would be vectorized for meaning-based search.
- and a Foundry model are being considered for retrieval and answers.
- No real cost figures or results are provided yet.