Usability improvements for samples work

[jonsequitur]

This issue collects small features and usability improvements intended to make planned sample notebooks more concise and easier to use.

Intelligent app development issues

• Display input forms in the cell output #3194
• Automatically deserialize as TabularDataResource when application/table-schema+json MIME type is shared #3211
• Add support for vector type in DAtaView Extension colombod/dotnet-interactive-extension-lab#38
• API for token count for specific models (related PRs : add token counter #3223, Add project for cook book utilities #3217)
• API to truncate text using token count (with optional overlapping) (related PRs : Add project for cook book utilities #3217)
• API to split long text using token count (with optional overlapping) (related PRs : Add project for cook book utilities #3217)
• Linq extensions for slicing and chunking (related PRs : Add project for cook book utilities #3217)
• Search utilities over collections using similarity scores (like cosine similarity) (related PRs : Add project for cook book utilities #3217)
• Generate JsonSchema from methods for GPT Function calls (see GPT Function Call #3243)
• Automate function calls from GPT function results (see GPT Function Call #3243)
• Access to json documents is a lot of code, need some indexer and / or xpath selection (see GPT Function Call #3243)
• GPT Function does not respect argument schema, array of strings are completed as single string and enum values are ignored
• Azure OpenAI SDK FunctionDefinition and FunctionCall are hard to use as they partial deserialize the json paylaod and leave the rest as plain strings (FunctionDefinition.Parameters and FunctionCall.Arguments are not usable objects but binary paylaod or string)
• Ability to sample at random from collections (related PRs support for collection shuffle #3294 )
• simplify calculations like centroids (related Prs support to calculate centroids from list of vectors #3298 )

Data preparation issues

• create float[] column types in dataframe (needed for data prep)

Ecosystem issues

• Support for easy scraping of wikipedia (maybe using this https://github.com/CXuesong/WikiClientLibrary/tree/6be126af214b60367637a804863b7d7f46f649fe)
• pdf parsing / extraction
• arxiv search