WWW::Gemini

Raku package for connecting with Google's Gemini. It is based on the Web API described in Gemini's API documentation.

The design and implementation of the package closely follows those of "WWW::PaLM", [AAp1], and "WWW::OpenAI", [AAp2].

Installation

From Zef ecosystem:

zef install WWW::Gemini

From GitHub:

zef install https://github.com/antononcube/Raku-WWW-Gemini

Usage examples

Show models:

use WWW::Gemini;

gemini-models()

Show text generation:

.say for gemini-generate-content('what is the population in Brazil?', format => 'values');

Using a synonym function:

.say for gemini-generation('Who wrote the book "Dune"?');

Embeddings

Show text embeddings:

use Data::TypeSystem;

my @vecs = gemini-embed-content(["say something nice!",
                            "shout something bad!",
                            "where is the best coffee made?"],
        format => 'values');

say "Shape: ", deduce-type(@vecs);
.say for @vecs;

Counting tokens

Here we show how to find the number of tokens in a text:

my $text = q:to/END/;
AI has made surprising successes but cannot solve all scientific problems due to computational irreducibility.
END

gemini-count-tokens($text, format => 'values');

Vision

If the function gemini-completion is given a list of images, textual results corresponding to those images is returned. The argument "images" is a list of image URLs, image file names, or image Base64 representations. (Any combination of those element types.)

Here is an example with this image:

my $fname = $*CWD ~ '/resources/ThreeHunters.jpg';
my @images = [$fname,];
say gemini-generation("Give concise descriptions of the images.", :@images, format => 'values');

When a file name is given to the argument "images" of gemini-completion then the function encode-image of "Image::Markup::Utilities", [AAp4], is applied to it.

Default models

Default models can be specified with the operating system environmental variables:

• GEMINI_DEFAULT_MODEL

• GEMINI_DEFAULT_IMAGE_GENERATION_MODEL

• GEMINI_DEFAULT_EMBEDDING_MODEL

Command Line Interface

Maker suite access

The package provides a Command Line Interface (CLI) script:

gemini-prompt --help

Remark: When the authorization key argument "auth-key" is specified set to "Whatever" then gemini-prompt attempts to use one of the env variables GEMINI_API_KEY or PALM_API_KEY.

Mermaid diagram

The following flowchart corresponds to the steps in the package function gemini-prompt:

TODO

• TODO Implementation

  • DONE Function calling support

  • TODO Image generation

  • TODO Image editing

  • TODO Audio generation

  • TODO Live AI support

• TODO Documentation

  • DONE Core functionalities

  • DONE Function calling / tool workflow notebook

  • TODO Image generation

  • TODO Comparison of OpenAI vs Google image generation

  • TODO Thinking model(s) demo

References

Articles

[AA1] Anton Antonov, "Workflows with LLM functions", (2023), RakuForPredictions at WordPress.

[AA2] Anton Antonov, "Number guessing games: Gemini vs ChatGPT" (2023), RakuForPredictions at WordPress.

[ZG1] Zoubin Ghahramani, "Introducing Gemini 2", (2023), Google Official Blog on AI.

Packages, platforms

[AAp1] Anton Antonov, WWW::PaLM Raku package, (2023-2024), GitHub/antononcube.

[AAp2] Anton Antonov, WWW::OpenAI Raku package, (2023-2024), GitHub/antononcube.

[AAp3] Anton Antonov, LLM::Functions Raku package, (2023-2024), GitHub/antononcube.

[AAp4] Anton Antonov, Image::Markup::Utilities Raku package, (2023-2024), GitHub/antononcube.

[AAp5] Anton Antonov, ML::FindTextualAnswer Raku package, (2023-2024), GitHub/antononcube.