1:- module(prolog2gpt,[
    2   init_gptkey/0,
    3   gpt_models/1, gpt_models/2,
    4   gpt_models_detail/2, 
    5   gpt_extract_data/4,
    6   gpt_extract_fields/3,
    7   gpt_extract_field_pairs/4,
    8   gpt_completions/4, gpt_completions/5,
    9   gpt_edits/4, gpt_edits/5,
   10   gpt_images_create/3, gpt_images_create/4,
   11   gpt_images_edits/4, gpt_images_edits/5,
   12   gpt_images_variations/3, gpt_images_variations/4,
   13   gpt_embeddings/4, gpt_embeddings/5,
   14   gpt_files/1, gpt_files/2,
   15   gpt_files_upload/4, gpt_files_upload/5,
   16   gpt_files_delete/2, gpt_files_delete/3,
   17   gpt_files_retrieve/2, gpt_files_retrieve/3,
   18   gpt_files_retrieve_content/2, gpt_files_retrieve_content/3,
   19   gpt_fine_tunes/1,gpt_fine_tunes/2,gpt_fine_tunes/3, gpt_fine_tunes/4,
   20   gpt_fine_tunes_detail/2, gpt_fine_tunes_detail/3,
   21   gpt_fine_tunes_cancel/2, gpt_fine_tunes_cancel/3,
   22   gpt_fine_tunes_events/2, gpt_fine_tunes_events/3,
   23   gpt_fine_tunes_delete/2, gpt_fine_tunes_delete/3,
   24   gpt_moderations/3, gpt_moderations/4
   25]).

Prolog interface to GPT

Introduction

This module provides prolog predicates to call the GPT API.

Large Language Models (LLM) like GPT essentially predict what text comes next, based on learning the (latent) probabilistic relationships between text tokens. By training the model on massive samples of text, the natural language capabilities have improved dramatically in recent years.

However, such language models can benefit from interaction with other types of modules, such as logic engines. To aid in developing such interactions, this library aims to make it easy to interact with GPT directly from Prolog, using predicates that call the GPT API.

The Prolog predicates are based on the OpenAI API Reference: https://platform.openai.com/docs/api-reference

Usage

  1. Create your GPT account at https://platform.openai.com
  2. Create an API key at https://platform.openai.com/account/api-keys and, as instructed, save that key somewhere (e.g. in a text file in a secure folder).
  3. Set an environment variable called GPTKEY to the key value (don't forget in Linux that if you added the environment variable to your bash startup script, e.g. `~/.bashrc`, then you need to source your `~/.bashrc` script to activate the new environment variable).
  4. Use the prolog2gpt.pro Prolog module as usual @author Richard de Rozario @license MIT */ 
   56:- use_module(library(http/http_open)).
   57:- use_module(library(http/http_client)).
   58:- use_module(library(http/http_ssl_plugin)).
   59:- use_module(library(http/json)).
   60:- use_module(library(http/http_json)).
   61:- use_module(library(http/json_convert)).
 init_gptkey is semidet
Get the GPT API Key from the environment variable named GPTKEY and create a prolog flag (gptkey) with the key value. Note: execute this predicate before using any of the others, because the gpt key is needed for authorization with each gpt api call.

Example use:

:- init_gptkey, current_prolog_flag(gptkey,Key), writeln(Key).
Key = sk-manycharactersoftheacturalkeyvalue
   75init_gptkey:-
   76   getenv('GPTKEY',Key),
   77   create_prolog_flag(gptkey,Key,[type(atom)]).
 gpt_models(-Models:list) is semidet
 gpt_models(-Models:json, +Raw:boolean) is semidet
Get a list of the available GPT models

Example use:

:- gpt_models(Models).
Models = [babbage,davinci,...]
Arguments:
Models- The list of model names, or JSON term with model details
Raw- If true then Models is the raw json result, else Models is a list of model names
   92gpt_models(Models):- gpt_models(Models,false).
   93gpt_models(Models,Raw):-
   94   current_prolog_flag(gptkey,Key),
   95   http_get('https://api.openai.com/v1/models',Ms,
   96            [authorization(bearer(Key)),application/json]),
   97   (  Raw=false
   98   -> gpt_extract_data(data,id,Ms,Models)
   99   ;  Models=Ms
  100   ).
 gpt_models_detail(+Model:atom, -ModelDetails:json) is semidet
Get the details of a particular model

Example use:

:- gpt_models('text-davinci-003',Details).
Details = ...  % the JSON term
Arguments:
Model- The model name, Note: put names that end with numeric suffixes in single quotes, to avoid the numeric being treated as a number. For example, use 'text-davinci-003'
Details- The details of the model as a JSON term
  117gpt_models_detail(Model,Details):-
  118   current_prolog_flag(gptkey,Key),
  119   atomic_concat('https://api.openai.com/v1/models/',Model,URL),
  120   http_get(URL,Details,[authorization(bearer(Key)),application/json]).
 gpt_extract_data(+Group:atom, +Fielname:atom, +Data:json, -Result:list) is semidet
Extract a list of field data from a gpt json structure. Note: this predicate makes some simple assumptions about how GPT API result data is structured.

Example use:

:- gpt_models(Ms,true), gpt_extract_data(data,id,Ms,Models).
Models = ['babbage','text-davinci-001',...]
Arguments:
Group- The GPT data group name. e.g. data, choices,...
Fieldname- The name of the field whose data we want
Data- The json data list from the GPT API, that contains one or more field values
Result- The resulting list of data values
  137gpt_extract_data(Group,Fieldname,json(Data),Result):-
  138   member(Group=Fieldlist,Data),
  139   gpt_extract_fields(Fieldname,Fieldlist,Result).
 gpt_extract_fields(+Fieldname:atom, +Data:json, -Result:list) is semidet
Extract a list of field data from a gpt json structure. Note: this predicate makes some simple assumptions about how GPT API result data is structured.

Example use:

:- Data=[json([id='babbage',object='model']),json([id='text-davinci-001',object='model'])], gpt_extract_data(data,id,Data,Models).
Models = ['babbage','text-davinci-001']
Arguments:
Fieldname- The name of the field whose data we want
Data- The list with json data from the GPT API, that contains one or more field values
Result- The resulting list of data values
  154gpt_extract_fields(_,[],[]):-!.
  155gpt_extract_fields(Fieldname,[json(Fields)|Fs],Results):-
  156   (  member(Fieldname=R,Fields)
  157   -> Results=[R|Res]
  158   ;  Results=Res
  159   ),
  160   gpt_extract_fields(Fieldname,Fs,Res).
 gpt_extract_field_pairs(+Field1:atom, +Field2:atom, +Data:json, -Result:list) is semidet
Extract a list of field pairs from a gpt json structure. Note: this predicate makes some simple assumptions about how GPT API result data is structured.

Example use:

:- Data=[json([id='123',filename=file1]),json([id='345',filename=file2])], gpt_extract_field_pairs(filename,id,Data,FieldPairs).
FieldPairs = [file1-'123',file2-'345']
Arguments:
Fieldname- The name of the field whose data we want
Data- The list with json data from the GPT API, that contains one or more field values
Result- The resulting list of data values
  175gpt_extract_field_pairs(_,_,[],[]):-!.
  176gpt_extract_field_pairs(Field1,Field2,[json(Fields)|Fs],Results):-
  177   (  member(Field1=F1,Fields)
  178      -> (  member(Field2=F2,Fields)
  179         -> Results = [F1-F2|Res]
  180         ;  Results = Res
  181         )
  182      ;  Results = Res
  183   ),!,
  184  gpt_extract_field_pairs(Field1,Field2,Fs,Res).
 gpt_completions(+Model:atom, +Prompt:atom, -Result:text, +Options:list) is semidet
 gpt_completions(+Model:atom, +Prompt:atom, -Result:term, ?Raw:boolean, +Options:list) is semidet
Get a prompted text completion from a GPT model.

Example use:

:- gpt_completions('text-davinci-003','My favourite animal is ',Result,_,[]),
Result = ['a dog']
Arguments:
Model- The GPT model name, Note: put names that end with numeric suffixes in single quotes, to avoid the numeric being treated as a number. For example, use 'text-davinci-003'
Prompt- The prompt that GPT will complete
Result- The text result, or json term with the result from GPT
Raw- If true the Result will be the json term, if false (default) the Result will be the text completion result
Options- The model completion options as list of json pair values (see below)

Options (Note option descriptions are mostly from the GPT API reference -- see the https://platform.openai.com/docs/api-reference for up-to-date and further details):

suffix=S
A string (S) that is inserted after the completion
max_tokens=M
The size of output, where M is a natural number (incl. 0). GPT-3 can theoretically return up to 4096 tokens, but in practice less than half that. One token is about 4 characters or 0.75 average word length. Defaults to 16.
temperature=N
Controls "randomness" of output, with `0<=N<=2`. Defaults to 1. Higher temperature means text will be more diverse, but also risks more grammar mistakes and nonsense. Recommended to change either this or top_p, but not both.
top_p
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. Use this, or temperature, but not both. Defaults to 1.
n=N
The number of completions (e.g. Results) to generate for each prompt. Defaults to 1.
stream=TF
If true then tokens will be sent as data-only `server-sent events` as they become available, with the stream terminated by a data: [DONE] message. Defaults to false
logprobs=N
Include the log probabilities on most likely tokens. For example, if logprobs=5, the API will return a list of the 5 most likely tokens. The API will always return the log probability of the sampled token, so there may be up to logprobs+1 elements in the response. Defaults to 0.
echo=TF
If true, echo back the prompt in addition to the completion. Defaults to false
stop=S
(string or list of strings). Up to 4 strings ("sequences") where the API will stop generating further tokens. The returned text will not contain the stop sequences. Defaults to null
presence_penalty=N
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increase the model's likelihood to talk about new topics. Defaults to 0.
frequency_penalty=N
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. Defaults to 0.
best_of=N
Generates best_of completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed.

When used with n, best_of controls the number of candidate completions and n specifies how many to return – best_of must be greater than n.

Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.

logit_bias=JSON_TERM
Modify the likelihood of specified tokens appearing in the completion.

Accepts a json object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this tokenizer tool (which works for both GPT-2 and GPT-3) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.

As an example, you can pass json('50256': -100) to prevent the <|endoftext|> token from being generated.

user=S
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
  284gpt_completions(Model,Prompt,Result,Options):- 
  285   gpt_completions(Model,Prompt,Result,false,Options),!.
  286
  287gpt_completions(Model,Prompt,Result,Raw,Options):-
  288   current_prolog_flag(gptkey,Key),
  289   atom_json_term(D,json([model=Model,prompt=Prompt|Options]),[]),
  290   Data = atom(application/json,D),
  291   http_post('https://api.openai.com/v1/completions',Data,ReturnData,
  292            [authorization(bearer(Key)),application/json]),
  293   (  Raw=false
  294   -> gpt_extract_data(choices,text,ReturnData,Result)
  295   ;  Result= ReturnData
  296   ).
 gpt_edits(+Model:atom, +Instruction:atom, -Result:text, +Options:list) is semidet
 gpt_edits(+Model:atom, +Instruction:atom, -Result:term, ?Raw:boolean, +Options:list) is semidet
Get a new edit for a given model, input and instruction. Note: Only for the 'text-davinci-edit-001' or 'code-davinci-edit-001' models.

Example use:

:- gpt_edit('text-davinci-001','Fix the spelling mistakes',Result,_,
            [  input='What day of the wek is it?'
            ]),
Result = 'What day of the week is it?'
Arguments:
Model- The GPT model name, Note: put names that end with numeric suffixes in single quotes, to avoid the numeric being treated as a number. For example, use 'text-davinci-003'
Instruction- The natural language editing instruction.
Result- The text result, or json term with the result from GPT
Raw- If true the Result will be the json term, if false (default) the Result will be the (first) text result
Options- The edit options as list of json pair values (see below)

Options (Note option descriptions are mostly from the GPT API reference -- see the https://platform.openai.com/docs/api-reference for up-to-date and further details):

input=S
An atom of text (S) that the model needs to edit. Default=''
max_tokens=M
The size of output, where M is a natural number (incl. 0). GPT-3 can theoretically return up to 4096 tokens, but in practice less than half that. One token is about 4 characters or 0.75 average word length. Defaults to 16.
n=N
The number of completions (e.g. Results) to generate for each prompt. Defaults to 1.
temperature=N
Controls "randomness" of output, with `0<=N<=2`. Defaults to 1. Higher temperature means text will be more diverse, but also risks more grammar mistakes and nonsense. Recommended to change either this or top_p, but not both.
top_p
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. Use this, or temperature, but not both. Defaults to 1.
  343gpt_edits(Model,Instruction,Result,Options):- 
  344   gpt_edits(Model,Instruction,Result,false,Options),!.
  345
  346gpt_edits(Model,Instruction,Result,Raw,Options):-
  347   current_prolog_flag(gptkey,Key),
  348   atom_json_term(D,json([model=Model,instruction=Instruction|Options]),[]),
  349   Data = atom(application/json,D),
  350   http_post('https://api.openai.com/v1/edits',Data,ReturnData,
  351            [authorization(bearer(Key)),application/json]),
  352   (  Raw=false
  353   -> gpt_extract_data(choices,text,ReturnData,Result)
  354   ;  Result= ReturnData
  355   ).
 gpt_images_create(+Prompt:atom, -Result:term, +Options:list) is semidet
 gpt_images_create(+Prompt:atom, -Result:term, ?Raw:boolean, +Options:list) is semidet
Create an image from a text prompt.

Example use:

:- gpt_images_create('A cute baby sea otter',Result,_,[]),
Result = ['https://...'] % url of the resulting image
Arguments:
Prompt- The prompt that GPT will complete
Result- The text result, or json term with the result from GPT
Raw- If true the Result will be the json term, if false (default) the Result will be the (first) url or b64 result
Options- The edit options as list of json pair values (see below)

Options (Note option descriptions are mostly from the GPT API reference -- see the https://platform.openai.com/docs/api-reference for up-to-date and further details):

n=N
The number of images to generate. Defaults to 1.
size=Z
The size of the image. Must be one of '256x256', '512x512', or '1024x1024'. Default is '1024x1024'
response_format=S
The format of the generated images. Must be one of url or b64_json. Default is url
user=S
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
  385gpt_images_create(Prompt,Result,Options):-
  386   gpt_images_create(Prompt,Result,false,Options).
  387gpt_images_create(Prompt,Result,Raw,Options):-
  388   current_prolog_flag(gptkey,Key),
  389   atom_json_term(D,json([prompt=Prompt|Options]),[]),
  390   Data = atom(application/json,D),
  391   http_post('https://api.openai.com/v1/images/generations',Data,ReturnData,
  392            [authorization(bearer(Key)),application/json]),
  393   ( member(response_format=Format,Options) -> true ; Format=url ),
  394   (  Raw=false
  395   -> gpt_extract_data(data,Format,ReturnData,Result)
  396   ;  Result= ReturnData
  397   ).
 gpt_images_edits(+Prompt:atom, -Result:term, +Options:list) is semidet
 gpt_images_edits(+Prompt:atom, -Result:term, ?Raw:boolean, +Options:list) is semidet
Modify an image from a text prompt.

Example use:

:- gpt_images_edits('A cute baby sea otter with a hat','./test/otter.png',Result,_,[]),
Result = ['https://...'] % url of the resulting image
Arguments:
Prompt- The prompt that GPT will complete
File- The path/filename of the image to edit
Result- The text result, or json term with the result from GPT
Raw- If true the Result will be the json term, if false (default) the Result will be the (first) url or b64 result
Options- The edit options as list of pair values (see below)

Options (Note option descriptions are mostly from the GPT API reference -- see the https://platform.openai.com/docs/api-reference for up-to-date and further details):

n=N
The number of images to generate. Defaults to 1.
size=Z
The size of the image. Must be one of '256x256', '512x512', or '1024x1024'. Default is '1024x1024'
mask
An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where image should be edited. Must be a valid PNG file, less than 4MB, and have the same dimensions as image.
response_format=S
The format of the generated images. Must be one of url or b64_json. Default is url
user=S
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
  432gpt_images_edits(Prompt,Image,Result,Options):-
  433   gpt_images_edits(Prompt,Image,Result,false,Options).
  434gpt_images_edits(Prompt,Image,Result,Raw,Options):-
  435   current_prolog_flag(gptkey,Key),
  436   Data = form_data([prompt=Prompt,image=file(Image)|Options]),
  437   http_post('https://api.openai.com/v1/images/edits',Data,ReturnData,
  438            [authorization(bearer(Key)),application/json]),
  439   ( member(response_format=Format,Options) -> true ; Format=url ),
  440   (  Raw=false
  441   -> gpt_extract_data(data,Format,ReturnData,Result)
  442   ;  Result= ReturnData
  443   ).
 gpt_images_variations(+File:atom, -Result:term, +Options:list) is semidet
 gpt_images_variations(+File:atom, -Result:term, ?Raw:boolean, +Options:list) is semidet
Produce variation(s) of an image.

Example use:

:- gpt_images_variations('./test/otter.png',Result,_,[]),
Result = ['https://...'] % url of the resulting image
Arguments:
Image- The path/filename of image to vary
Result- The text result, or json term with the result from GPT
Raw- If true the Result will be the json term, if false (default) the Result will be the (first) url or b64 result
Options- The edit options as list of pair values (see below)

Options (Note option descriptions are mostly from the GPT API reference -- see the https://platform.openai.com/docs/api-reference for up-to-date and further details):

n=N
The number of images to generate. Defaults to 1.
size=Z
The size of the image. Must be one of '256x256', '512x512', or '1024x1024'. Default is '1024x1024'
response_format=S
The format of the generated images. Must be one of url or b64_json. Default is url
user=S
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
  473gpt_images_variations(Image,Result,Options):-
  474   gpt_images_variations(Image,Result,false,Options).
  475
  476gpt_images_variations(Image,Result,Raw,Options):-
  477   current_prolog_flag(gptkey,Key),
  478   Data = form_data([image=file(Image)|Options]),
  479   http_post('https://api.openai.com/v1/images/variations',Data,ReturnData,
  480            [authorization(bearer(Key)),application/json]),
  481   ( member(response_format=Format,Options) -> true ; Format=url ),
  482   (  Raw=false
  483   -> gpt_extract_data(data,Format,ReturnData,Result)
  484   ;  Result= ReturnData
  485   ).
 gpt_embeddings(+Input:text, -Result:list) is semidet
 gpt_embeddings(+Input:text, -Result:list, +Raw:boolean) is semidet
Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.

Example use:

:- gpt_embeddings('text-embedding-ada-002','The food was delicious',Result),
Result = [0.0023064255,-0.009327292,...]
Arguments:
Input- Atom, string, or list of such
Result- List of file names, or json term (depending on Raw)
Raw If `true` the Result will be the json term, if `false` (default) the Result will be a simple list of file names Options (Note option descriptions are mostly from the GPT API reference -- see the https://platform.openai.com/docs/api-reference for up-to-date and further details):
-
user=S
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
  505gpt_embeddings(Model,Input,Result,Options):-
  506   gpt_embeddings(Model,Input,Result,false,Options),!.
  507gpt_embeddings(Model,Input,Result,Raw,Options):-
  508   current_prolog_flag(gptkey,Key),
  509   atom_json_term(D,json([model=Model,input=Input|Options]),[]),
  510   Data = atom(application/json,D),
  511   http_post('https://api.openai.com/v1/embeddings',Data,ReturnData,
  512            [authorization(bearer(Key)),application/json]),
  513   (  Raw=false
  514   -> gpt_extract_data(data,embedding,ReturnData,Result)
  515   ;  Result= ReturnData
  516   ).
 gpt_files(-Result:list) is semidet
 gpt_files(-Result:list, +Raw:boolean) is semidet
List all files that belong to the user's organization.

Example use:

:- gpt_files(Result),
Result = ['file1.jsonl'-'file-12345','file2.jsonl'-'file-56789']
Arguments:
Result- List of Filename-ID pairs, or json term (depending on Raw)
Raw- If true the Result will be the json term, if false (default) the Result will be a simple list of file names
  532gpt_files(Result):-
  533   gpt_files(Result,false).
  534gpt_files(Result,Raw):-
  535   current_prolog_flag(gptkey,Key),
  536   http_get('https://api.openai.com/v1/files',json(ReturnData),
  537            [authorization(bearer(Key)),application/json]),
  538   (  Raw=false
  539   -> (  member(data=Files,ReturnData),
  540         gpt_extract_field_pairs(filename,id,Files,Result)
  541      )
  542   ;  Result= json(ReturnData)
  543   ).
 gpt_files_upload(+File:atom, +Purpose:text, -Result:list) is semidet
 gpt_files_upload(+File:atom, +Purpose:text, -Result:list, +Raw:boolean) is semidet
Upload a JSON Lines file (typically for fine-tuning)

Example use:

:- gpt_files_upload('./test/tune_answer.jsonl','fine-tune',Result),
Result = ['file-XjGxS3KTG0uNmNOK362iJua3']
Arguments:
File- Filename to upload
Purpose- Purpose of the file. Currently only 'fine-tune'
Result- List of file names, or json term (depending on Raw)
Raw- If true the Result will be the json term, if false (default) the Result will be a simple list of file names
  560gpt_files_upload(File,Purpose,Result,Options):-
  561   gpt_files_upload(File,Purpose,Result,false,Options),!.
  562gpt_files_upload(File,Purpose,Result,Raw,Options):-
  563   current_prolog_flag(gptkey,Key), 
  564   Data = form_data([file=file(File),purpose=Purpose|Options]),
  565   http_post('https://api.openai.com/v1/files',Data,json(ReturnData),
  566            [authorization(bearer(Key)),application/json]),
  567   (  Raw=false
  568   -> (member(id=ID,ReturnData),Result=[ID])
  569   ;  Result= json(ReturnData)
  570   ).
 gpt_files_delete(+FileID:atom, +Purpose:text, -Result:list) is semidet
 gpt_files_delete(+FileID:atom, +Purpose:text, -Result:list, +Raw:boolean) is semidet
Delete a (user) file from GPT storage

Example use:

:- gpt_files_delete('file-XjGxS3KTG0uNmNOK362iJua3',Result),
Result = ['file-XjGxS3KTG0uNmNOK362iJua3']
Arguments:
FileID- File ID of file in GPT storage to delete
Purpose- Purpose of the file. Currently only 'fine-tune'
Result- List of file names, or json term (depending on Raw)
Raw- If true the Result will be the json term, if false (default) the Result will be a simple list of file names
  587gpt_files_delete(FileID,Result):-
  588   gpt_files_delete(FileID,Result,false),!.
  589gpt_files_delete(FileID,Result,Raw):-
  590   current_prolog_flag(gptkey,Key),
  591   atomic_concat('https://api.openai.com/v1/files/',FileID,URL),
  592   http_delete(URL,json(ReturnData),
  593      [authorization(bearer(Key)),application/json]),
  594   (  Raw=false
  595   -> (member(id=ID,ReturnData), Result=[ID])
  596   ;  Result= json(ReturnData)
  597   ).
 gpt_files_retrieve(+FileID:atom, -Result:list) is semidet
 gpt_files_retrieve(+FileID:atom, -Result:list, +Raw:boolean) is semidet
Retrieve a (user) file details

Example use:

:- gpt_files_retrieve('file-XjGxS3KTG0uNmNOK362iJua3',Result),
Result = ['myfile.jsonl']
Arguments:
FileID- File ID of file in GPT storage to retrieve
Result- List with file name, or json term (depending on Raw)
Raw- If true the Result will be the json term, if false (default) the Result will be a simple list of file names
  613gpt_files_retrieve(FileID,Result):-
  614   gpt_files_retrieve(FileID,Result,false),!.
  615gpt_files_retrieve(FileID,Result,Raw):-
  616   current_prolog_flag(gptkey,Key),
  617   atomic_concat('https://api.openai.com/v1/files/',FileID,URL),
  618   http_get(URL,json(ReturnData),
  619      [authorization(bearer(Key)),application/json]),
  620   (  Raw=false
  621   -> (member(filename=File,ReturnData), Result=[File])
  622   ;  Result= json(ReturnData)
  623   ).
 gpt_files_retrieve_content(+FileID:atom, +Purpose:text, -Result:list) is semidet
 gpt_files_retrieve(+FileID:atom, +Purpose:text, -Result:list, +Raw:boolean) is semidet
Retrieve a (user) file details

Example use:

:- gpt_files_retrieve('file-XjGxS3KTG0uNmNOK362iJua3',Result),
Result = ['myfile.jsonl']
Arguments:
FileID- File ID of file in GPT storage to retrieve
Result- List with file name, or json term (depending on Raw)
Raw If `true` the Result will be the json term, if `false` (default) the Result will be a simple list of file names TODO: ***** this API doesn't work for some reason *****
- 
  640gpt_files_retrieve_content(FileID,Result):-
  641   gpt_files_retrieve_content(FileID,Result,false),!.
  642gpt_files_retrieve_content(FileID,Result,Raw):-
  643   current_prolog_flag(gptkey,Key),
  644   atomic_list_concat(['https://api.openai.com/v1/files/',FileID,'/content'],URL),
  645   http_get(URL,ReturnData, [authorization(bearer(Key))]),
  646   (  Raw=false
  647   -> (member(filename=File,ReturnData), Result=[File])
  648   ;  Result= ReturnData
  649   ).
 gpt_fine_tunes(+TrainingFile:text, -Result:list) is semidet
 gpt_fine_tunes(+TrainingFile:text, -Result:list, +Raw:boolean) is semidet
Get a vector representation of a given TrainingFile that can be easily consumed by machine learning models and algorithms.

Example use:

:- gpt_fine_tunes('file-XGinujblHPwGLSztz8cPS8XY',Result),
Result = ['ft-AF1WoRqd3aJAHsqc9NY7iL8F']
Arguments:
TrainingFile- Atom with the GPT file ID of an uploaded file
Result- Fine-tuned request event in list, or json term of details (depending on Raw)
Raw If `true` the Result will be the json term, if `false` (default) the Result will be a simple list of file names Options (Note option descriptions are mostly from the GPT API reference -- see the https://platform.openai.com/docs/api-reference for up-to-date and further details):
-
validation_file=F
The ID of an uploaded file that contains validation data.

If you provide this file, the data is used to generate validation metrics periodically during fine-tuning. These metrics can be viewed in the fine-tuning results file. Your train and validation data should be mutually exclusive.

Your dataset must be formatted as a JSONL file, where each validation example is a JSON object with the keys "prompt" and "completion". Additionally, you must upload your file with the purpose fine-tune.

model=M
The name of the base model to fine-tune. You can select one of 'ada', 'babbage', 'curie', 'davinci', or a fine-tuned model created after 2022-04-21. To learn more about these models, see the Models documentation. Defaults to 'curie'.
n_epochs=N
The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset. Defaults to 4.
batch_size=N
The batch size to use for training. The batch size is the number of training examples used to train a single forward and backward pass.

By default, the batch size will be dynamically configured to be ~0.2% of the number of examples in the training set, capped at 256 - in general, we've found that larger batch sizes tend to work better for larger datasets. Defaults to null.

learning_rate_multiplier=N
The learning rate multiplier to use for training. The fine-tuning learning rate is the original learning rate used for pretraining multiplied by this value.

By default, the learning rate multiplier is the 0.05, 0.1, or 0.2 depending on final batch_size (larger learning rates tend to perform better with larger batch sizes). We recommend experimenting with values in the range 0.02 to 0.2 to see what produces the best results. Defaults to null.

prompt_loss_weight=N
The weight to use for loss on the prompt tokens. This controls how much the model tries to learn to generate the prompt (as compared to the completion which always has a weight of 1.0), and can add a stabilizing effect to training when completions are short.

If prompts are extremely long (relative to completions), it may make sense to reduce this weight so as to avoid over-prioritizing learning the prompt. Defaults to 0.01

compute_classification_metrics=B
If set, we calculate classification-specific metrics such as accuracy and F-1 score using the validation set at the end of every epoch. These metrics can be viewed in the results file.

In order to compute classification metrics, you must provide a validation_file. Additionally, you must specify classification_n_classes for multiclass classification or classification_positive_class for binary classification. Defaults to false

classification_n_classes=N
The number of classes in a classification task. This parameter is required for multiclass classification. Defaults to null.
classification_positive_class=S
The positive class in binary classification. This parameter is needed to generate precision, recall, and F1 metrics when doing binary classification. Defaults to null.
classification_betas=List
If this is provided, we calculate F-beta scores at the specified beta values. The F-beta score is a generalization of F-1 score. This is only used for binary classification.

With a beta of 1 (i.e. the F-1 score), precision and recall are given the same weight. A larger beta score puts more weight on recall and less on precision. A smaller beta score puts more weight on precision and less on recall. Defaults to null.

suffix=S
A string of up to 40 characters that will be added to your fine-tuned model name. For example, a suffix of "custom-model-name" would produce a model name like ada:ft-your-org:custom-model-name-2022-02-15-04-21-04.
  744gpt_fine_tunes(TrainingFile,Result,Options):-
  745   gpt_fine_tunes(TrainingFile,Result,false,Options),!.
  746gpt_fine_tunes(TrainingFile,Result,Raw,Options):-
  747   current_prolog_flag(gptkey,Key),
  748   atom_json_term(D,json([training_file=TrainingFile|Options]),[]),
  749   Data = atom(application/json,D),
  750   http_post('https://api.openai.com/v1/fine-tunes',Data,json(ReturnData),
  751            [authorization(bearer(Key)),application/json]),
  752   (  Raw=false
  753   -> member(id=Result,ReturnData)
  754   ;  Result= json(ReturnData)
  755   ).
 gpt_fine_tunes(-Result:list) is semidet
 gpt_fine_tunes(-Result:list, +Raw:boolean) is semidet
Gets a list of fine-tunes jobs.

Example use:

:- gpt_fine-tunes(Result),
Result = ['curie:ft-personal-2022-02-15-04-21-04'-'ft-090asf0asf0',...]
Arguments:
Result- List with file name, or json term (depending on Raw)
Raw- If true the Result will be the json term, if false (default) the Result will be a simple list of file names
  770gpt_fine_tunes(Result):-
  771   gpt_fine_tunes(Result,false),!.
  772gpt_fine_tunes(Result,Raw):-
  773   current_prolog_flag(gptkey,Key),
  774   http_get('https://api.openai.com/v1/fine-tunes',json(ReturnData),
  775      [authorization(bearer(Key)),application/json]),
  776   (  Raw=false
  777   -> (  member(data=Models,ReturnData),
  778         gpt_extract_field_pairs(fine_tuned_model,id,Models,Result)
  779      )
  780   ;  Result= json(ReturnData)
  781   ).
 gpt_fine_tunes_detail(+ID:atom, -Result:list) is semidet
 gpt_fine_tunes_detail(+ID:atom, -Result:list, +Raw:boolean) is semidet
Gets details of a fine-tunes job.

Example use:

:- gpt_fine_tunes_detail('ft-090asf0asf0',Result),
Result = ['curie:ft-personal-2022-02-15-04-21-04']
Arguments:
Result- List with file name, or json term (depending on Raw)
Raw- If true the Result will be the json term, if false (default) the Result will be a simple list of file names
  796gpt_fine_tunes_detail(ID,Result):-
  797   gpt_fine_tunes_detail(ID,Result,false),!.
  798gpt_fine_tunes_detail(ID,Result,Raw):-
  799   current_prolog_flag(gptkey,Key),
  800   atomic_concat('https://api.openai.com/v1/fine-tunes/',ID,URL),
  801   http_get(URL,json(ReturnData),
  802      [authorization(bearer(Key)),application/json]),
  803   (  Raw=false
  804   -> (  member(fine_tuned_model=TunedModel,ReturnData),
  805         Result=[TunedModel]
  806      )
  807   ;  Result= json(ReturnData)
  808   ).
 gpt_fine_tunes_cancel(+ID:atom, -Result:list) is semidet
 gpt_fine_tunes_cancel(+ID:atom, -Result:list, +Raw:boolean) is semidet
Cancel a fine-tunes job.

Example use:

:- gpt_fine_tunes_cancel([_-ID]),(ID,Result),
Result = ['curie:ft-personal-2022-02-15-04-21-04']
Arguments:
ID- ID of the fine-tunes job
Result- List with file name, or json term (depending on Raw)
Raw If `true` the Result will be the json term, if `false` (default) the Result will be a simple list of file names TODO: ***** DOES NOT WORK **** something to do with post without data?
- 
  825gpt_fine_tunes_cancel(ID,Result):-
  826   gpt_fine_tunes_cancel(ID,Result,false),!.
  827gpt_fine_tunes_cancel(ID,Result,Raw):-
  828   current_prolog_flag(gptkey,Key),
  829   atomic_list_concat(['https://api.openai.com/v1/fine-tunes/',ID,'/cancel'],URL),
  830   http_post(URL,[],json(ReturnData),
  831      [authorization(bearer(Key)),application/json]),
  832   (  Raw=false
  833   -> (  member(fine_tuned_model=TunedModel,ReturnData),
  834         Result=[TunedModel]
  835      )
  836   ;  Result= json(ReturnData)
  837   ).
 gpt_fine_tunes_events(+ID:atom, -Result:list) is semidet
 gpt_fine_tunes_events(+ID:atom, -Result:list, +Raw:boolean) is semidet
List events of a fine-tunes job.

Example use:

:- gpt_fine_tunes_events([_-ID]),(ID,Result),
Result = ['curie:ft-personal-2022-02-15-04-21-04']
Arguments:
ID- ID of the fine-tunes job
Result- List with file name, or json term (depending on Raw)
Raw If `true` the Result will be the json term, if `false` (default) the Result will be a simple list of file names TODO: ***** DOES NOT WORK **** something to do with post without data?
- 
  854gpt_fine_tunes_events(ID,Result):-
  855   gpt_fine_tunes_events(ID,Result,false),!.
  856gpt_fine_tunes_events(ID,Result,Raw):-
  857   current_prolog_flag(gptkey,Key),
  858   atomic_list_concat(['https://api.openai.com/v1/fine-tunes/',ID,'/events'],URL),
  859   http_get(URL,json(ReturnData),
  860      [authorization(bearer(Key)),application/json]),
  861   (  Raw=false
  862   -> (  member(fine_tuned_model=TunedModel,ReturnData),
  863         Result=[TunedModel]
  864      )
  865   ;  Result= json(ReturnData)
  866   ).
 gpt_fine_tunes_delete(+ID:atom, -Result:list) is semidet
 gpt_fine_tunes_delete(+ID:atom, -Result:list, +Raw:boolean) is semidet
Delete a fine-tunes job from GPT storage

Example use:

:- gpt_fine_tunes([_-ID]),gpt_fine_tunes_delete(ID,Result),
Result = ['ft-XjGxS3KTG0uNmNOK362iJua3']
Arguments:
ID- File ID of file in GPT storage to delete
Purpose- Purpose of the file. Currently only 'fine-tune'
Result- List of file names, or json term (depending on Raw)
Raw- If true the Result will be the json term, if false (default) the Result will be a simple list of file names
  883gpt_fine_tunes_delete(ID,Result):-
  884   gpt_fine_tunes_delete(ID,Result,false),!.
  885gpt_fine_tunes_delete(ID,Result,Raw):-
  886   current_prolog_flag(gptkey,Key),
  887   atomic_concat('https://api.openai.com/v1/models/',ID,URL),
  888   http_delete(URL,json(ReturnData),
  889      [authorization(bearer(Key)),application/json]),
  890   (  Raw=false
  891   -> (member(id=ID,ReturnData), Result=[ID])
  892   ;  Result= json(ReturnData)
  893   ).
 gpt_moderations(+Model:atom, +Input:text, -Result:list, +Options:list) is semidet
Given a input text, outputs if the model classifies it as violating OpenAI's content policy.

Example use:

:- gpt_moderations('I want to kill them',Result),
Result = [sexual=false, hate=false, violence=true, 'self-harm'=false,
'sexual/minors'=false, 'hate/threatening'=false, 'violence/graphic'=false].
Arguments:
Input- Text to test for content policy violation
Result- JSON structure with policy scores
  908gpt_moderations(Input,Result,Options):-
  909   gpt_moderations(Input,Result,false,Options).
  910gpt_moderations(Input,Result,Raw,Options):-
  911   current_prolog_flag(gptkey,Key), 
  912   atom_json_term(D,json([input=Input|Options]),[]),
  913   Data = atom(application/json,D),
  914   http_post('https://api.openai.com/v1/moderations',Data,ReturnData,
  915            [authorization(bearer(Key)),application/json]),
  916   (  Raw=false
  917   -> (  gpt_extract_data(results,categories,ReturnData,[json(R)]),
  918         maplist(json_pair_boolean,R,Result)
  919      )
  920   ;  Result= ReturnData
  921   ).
  922
  923json_pair_boolean(Name='@'(Boolean),Name=Boolean):-!.
  924json_pair_boolean(Name=Val,Name=Val):-!