in reply to Re^2: perl hooks for AI
in thread perl hooks for AI

NOAA gives you a text file. When to pull new data? What are the exact parsing rules? Are there exceptions when the format could slightly change? How to convert the values into a nice 1-5 scale? Those are the things you have to spend a day painstakingly searching and reading obscure documents...

That. First, you have to create a known data set from the data, then you have to do a whole bunch of very complex math to normalize all the data that's way above my head (super thanks goes out to no_slogan who did all of the math for me in this thread).

After that, you do have to remember to update the data (typically every five years, but there are known to be incremental changes as well. If the format changes at all, you have to rewrite your parser code that translates it to a format the code understands.

An API would be much more helpful :)

Replies are listed 'Best First'.
Re^4: perl hooks for AI
by Aldebaran (Curate) on Dec 18, 2023 at 07:47 UTC
    An API would be much more helpful :)

    Hey stevie, how's tricks? Did you get stomped by winter storms? (They went north of me.)

    I thought I was closing in on this:

    #!/usr/bin/perl use v5.030; use utf8; use LWP::UserAgent; use JSON; ## get credentials my $ini_path = qw( /Users/mymac/Documents/1.тай&#108 +5;ый.txt ); # get key my $ref_config = get_тайный($ini_p +ath); $DB::single = 1; my %h = %$ref_config; ## dial up server # Your OpenAI API endpoint and token my $api_url = 'https://api.openai.com/v1/engines/davinci-codex/complet +ions'; # Replace with the correct API endpoint if needed my $auth_token = $h{key}; # The prompt you want to send my $prompt = "How many units are there in a mole?"; my $ua = LWP::UserAgent->new; $ua->ssl_opts( verify_hostname => 1, SSL_ca_file => '/Users/mymac/Documents/cacert-2023-12-12.pem', ); # Set up Request my $req = HTTP::Request->new(POST => $api_url); $req->header('Content-Type' => 'application/json'); $req->header('Authorization' => "Bearer $auth_token"); # Add the JSON-encoded data to the request my $json_data = encode_json({ prompt => $prompt, max_tokens => 150 }); + # Adjust the number of tokens as needed $req->content($json_data); # Perform the request my $res = $ua->request($req); # Check the outcome if ($res->is_success) { print $res->decoded_content; } else { print "Error: " . $res->status_line . "\n"; } ## don't change anything about this subroutine sub get_тайный { use Config::Tiny; use Data::Dump; my %h; #creating here and exporting reference to caller my $ini_path = shift; #caller provides inipath my $sub_hash1 = "openai"; my $Config = Config::Tiny->new; $Config = Config::Tiny->read( $ini_path, 'utf8' ); # -> is optional between brackets $h{email} = $Config->{$sub_hash1}{'email'}; $h{key} = $Config->{$sub_hash1}{'key'}; my $ref_config = \%h; dd $ref_config; $DB::single = 1; return ($ref_config); } __END__

    It comes back as a 404, and looks like this in the debugger:

    main::(3.openai.pl:26): my $ua = LWP::UserAgent->new; >> n main::(3.openai.pl:27): $ua->ssl_opts( main::(3.openai.pl:28): verify_hostname => 1, main::(3.openai.pl:29): SSL_ca_file => '/Users/mymac/Docume +nts/cacert-2023-12-12.pem', >> s LWP::UserAgent::ssl_opts(/System/Library/Perl/Extras/5.30/LWP/UserAgen +t.pm:713): 713: my $self = shift; >> r void context return from LWP::UserAgent::ssl_opts ... main::(3.openai.pl:46): if ($res->is_success) { >> y $api_url = 'https://api.openai.com/v1/engines/davinci-codex/completion +s' $auth_token = 'redacted but correct' $json_data = '{"max_tokens":150,"prompt":"How many units are there in +a mole?"}' $prompt = 'How many units are there in a mole?' ... $req = HTTP::Request=HASH(0x14103e258) '_content' => '{"max_tokens":150,"prompt":"How many units are there + in a mole?"}' '_headers' => HTTP::Headers=HASH(0x14105a110) '::std_case' => HASH(0x131958040) 'if-ssl-cert-subject' => 'If-SSL-Cert-Subject' 'authorization' => 'Bearer sk-...' 'content-type' => 'application/json' 'user-agent' => 'libwww-perl/6.44' '_method' => 'POST' '_uri' => URI::https=SCALAR(0x140444dc8) -> 'https://api.openai.com/v1/engines/davinci-codex/completions' '_uri_canonical' => URI::https=SCALAR(0x140444dc8) -> REUSED_ADDRESS $res = HTTP::Response=HASH(0x140698518) '_content' => '{ "error": { "message": "The model `davinci-codex` does not exist or you do + not have access to it.", "type": "invalid_request_error", "param": null, "code": "model_not_found" }

    Fishing for tips,