Add support for Int8 embeddings

[pabvald]

It would be great to have support for embeddings compressed to Int8 as per HuggingFace: Embedding Quantization.

Potential implementation would be to:

• Define an embedder (<:AbstractEmbedder for get_embeddings) and the corresponding finder (<:AbstractSimilarityFinder for find_similar). Both would have the vectors with necessary min_values and max_values fields to hold the effective range for each embedding dimension (eg, length(min_values)=length(max_values)=D)
• Define methods for these types
• The conversion to Int8 could be done post hoc (after build_index) via a utility function and then the resulting finder with the range to allow converting to Int8 (to be provided to the airag)
• It should implement the two-stage pass with rescore_multiplier=4 (first on Int8 embeddings, then with Float x Int8)

Original issue from PromptingTools.jl: svilupp/PromptingTools.jl#118

[pabvald]

LinLogQuantization.jl implements both linear and logarithmic quantization. In order to avoid unnecessary deps, we can get the necessary functions from linquantarrays.jl, leaving out:

• the support for 24-bit integers
• syntactic sugar, e.g. LinQuant8Array, LinQuant16Array, LinQuant32Array.