README-work
WWW::MistralAI
In brief
This Raku package provides access to the machine learning service MistralAI, [MAI1]. For more details of the MistralAI's API usage see the documentation, [MAI2].
Remark: To use the MistralAI API one has to register and obtain authorization key.
Remark: This Raku package is much "less ambitious" than the official Python package, [MAIp1], developed by MistralAI's team. Gradually, over time, I expect to add features to the Raku package that correspond to features of [MAIp1].
This package is very similar to the packages "WWW::OpenAI", [AAp1], and "WWW::PaLM", [AAp2].
Installation
Package installations from both sources use zef installer (which should be bundled with the "standard" Rakudo installation file.)
To install the package from Zef ecosystem use the shell command:
zef install WWW::MistralAI
To install the package from the GitHub repository use the shell command:
zef install https://github.com/antononcube/Raku-WWW-MistralAI.git
Usage examples
Remark: When the authorization key, auth-key
, is specified to be Whatever
then the functions mistralai-*
attempt to use the env variable MISTRAL_API_KEY
.
Universal "front-end"
The package has an universal "front-end" function mistral-playground
for the
different functionalities provided by MistralAI.
Here is a simple call for a "chat completion":
use WWW::MistralAI;
mistralai-playground('Where is Roger Rabbit?', max-tokens => 64);
Another one using Bulgarian:
mistralai-playground('Колко групи могат да се намерят в този облак от точки.', max-tokens => 64);
Remark: The function mistralai-completion
can be used instead in the examples above.
Models
The current MistralAI models can be found with the function mistralai-models
:
mistralai-models
Code generation
There are two types of completions : text and chat. Let us illustrate the differences of their usage by Raku code generation. Here is a text completion:
mistralai-completion(
'generate Raku code for making a loop over a list',
max-tokens => 120,
format => 'values');
Here is a chat completion:
mistralai-completion(
'generate Raku code for making a loop over a list',
max-tokens => 120,
format => 'values');
Embeddings
Embeddings can be obtained with the function mistralai-embeddings
. Here is an example of finding the embedding vectors
for each of the elements of an array of strings:
my @queries = [
'make a classifier with the method RandomForeset over the data dfTitanic',
'show precision and accuracy',
'plot True Positive Rate vs Positive Predictive Value',
'what is a good meat and potatoes recipe'
];
my $embs = mistralai-embeddings(@queries, format => 'values', method => 'tiny');
$embs.elems;
Here we show:
That the result is an array of four vectors each with length 1536
The distributions of the values of each vector
use Data::Reshapers;
use Data::Summarizers;
say "\$embs.elems : { $embs.elems }";
say "\$embs>>.elems : { $embs>>.elems }";
records-summary($embs.kv.Hash.&transpose);
Here we find the corresponding dot products and (cross-)tabulate them:
use Data::Reshapers;
use Data::Summarizers;
my @ct = (^$embs.elems X ^$embs.elems).map({ %( i => $_[0], j => $_[1], dot => sum($embs[$_[0]] >>*<< $embs[$_[1]])) }).Array;
say to-pretty-table(cross-tabulate(@ct, 'i', 'j', 'dot'), field-names => (^$embs.elems)>>.Str);
Remark: Note that the fourth element (the cooking recipe request) is an outlier. (Judging by the table with dot products.)
Chat completions with engineered prompts
Here is a prompt for "emojification" (see the Wolfram Prompt Repository entry "Emojify"):
my $preEmojify = q:to/END/;
Rewrite the following text and convert some of it into emojis.
The emojis are all related to whatever is in the text.
Keep a lot of the text, but convert key words into emojis.
Do not modify the text except to add emoji.
Respond only with the modified text, do not include any summary or explanation.
Do not respond with only emoji, most of the text should remain as normal words.
END
Here is an example of chat completion with emojification:
mistralai-chat-completion([ system => $preEmojify, user => 'Python sucks, Raku rocks, and Perl is annoying'], max-tokens => 200, format => 'values')
For more examples see the document "Chat-completion-examples".
Command Line Interface
Playground access
The package provides a Command Line Interface (CLI) script:
mistralai-playground --help
Remark: When the authorization key argument "auth-key" is specified set to "Whatever"
then mistralai-playground
attempts to use the env variable MISTRAL_API_KEY
.
Mermaid diagram
The following flowchart corresponds to the steps in the package function mistralai-playground
:
References
Packages
[AAp1] Anton Antonov, WWW::OpenAI Raku package, (2023), GitHub/antononcube.
[AAp2] Anton Antonov, WWW::PaLM Raku package, (2023), GitHub/antononcube.
[MAI1] MistralAI, MistralAI platform.
[MAI2] MistralAI Platform documentation, MistralAI documentation.
[MAIp1] MistralAI, [https://github.com/mistralai/client-python), (2023), GitHub/mistralai.