openai.ex
v0.6.2
Emballage non officiel de la communauté pour les API de repos Openai Voir https://platform.openai.com/docs/api-reference/introduction pour plus d'informations sur les points de terminaison de repos
Merci pour votre compréhension et votre soutien et merci à tous ceux qui ont contribué à la bibliothèque jusqu'à présent!
Ajouter : ouvrir en tant que dépendance dans votre fichier mix.exs.
def deps do
[
{ :openai , "~> 0.6.2" }
]
end Vous pouvez configurer OpenAI dans votre mix config.exs (par défaut $ project_root / config / config.exs). Si vous utilisez Phoenix, ajoutez la configuration dans vos fichiers config / dev.exs | test.exs | prod.exs. Un exemple de configuration est:
import Config
config :openai ,
# find it at https://platform.openai.com/account/api-keys
api_key: "your-api-key" ,
# find it at https://platform.openai.com/account/org-settings under "Organization ID"
organization_key: "your-organization-key" ,
# optional, use when required by an OpenAI API beta, e.g.:
beta: "assistants=v1" ,
# optional, passed to [HTTPoison.Request](https://hexdocs.pm/httpoison/HTTPoison.Request.html) options
http_options: [ recv_timeout: 30_000 ] ,
# optional, useful if you want to do local integration tests using Bypass or similar
# (https://github.com/PSPDFKit-labs/bypass), do not use it for production code,
# but only in your test config!
api_url: "http://localhost/" Remarque: Vous pouvez charger vos variables Env Os dans le fichier de configuration, si vous définissez une variable Env pour la clé API nommée OPENAI_API_KEY vous pouvez l'obtenir dans le code en faisant System.get_env("OPENAI_API_KEY") .
config.exs est le temps de compilation, donc la fonction get_env/1 est exécutée pendant la version, si vous souhaitez obtenir les variables Env pendant l'exécution, veuillez utiliser runtime.exs au lieu de config.exs dans votre application (Elixir Doc Ref).
La configuration de la bibliothèque client peut être écrasée dans l'exécution en passant un %OpenAI.Config{} struct comme dernier argument de la fonction que vous devez utiliser. Par exemple, si vous avez besoin d'utiliser une autre api_key , organization_key ou http_options vous pouvez simplement faire:
config_override = % OpenAI.Config { api_key: "test-api-key" } # this will return a config struct with "test-api-key" as api_key, all the other config are defaulted by the client by using values taken from config.exs, so you don't need to set the defaults manually
# chat_completion with overriden config
OpenAI . chat_completion ( [
model: "gpt-3.5-turbo" ,
messages: [
% { role: "system" , content: "You are a helpful assistant." } ,
% { role: "user" , content: "Who won the world series in 2020?" } ,
% { role: "assistant" , content: "The Los Angeles Dodgers won the World Series in 2020." } ,
% { role: "user" , content: "Where was it played?" }
]
] ,
config_override # <--- pass the overriden configuration as last argument of the function
)
# chat_completion with standard config
OpenAI . chat_completion (
model: "gpt-3.5-turbo" ,
messages: [
% { role: "system" , content: "You are a helpful assistant." } ,
% { role: "user" , content: "Who won the world series in 2020?" } ,
% { role: "assistant" , content: "The Los Angeles Dodgers won the World Series in 2020." } ,
% { role: "user" , content: "Where was it played?" }
]
) Vous pouvez effectuer un dépôt de configuration dans toutes les fonctions, notez que l'argument params doit être passé explicitement en tant que liste entre crochets si la configuration doit être écrasée, comme dans l'exemple ci-dessus.
Obtenez votre clé API à partir de https://platform.openai.com/account/api-Keys
Récupérer la liste des modèles disponibles
OpenAI . models ( ) { :ok , % {
data: [ % {
"created" => 1651172505 ,
"id" => "davinci-search-query" ,
"object" => "model" ,
"owned_by" => "openai-dev" ,
"parent" => nil ,
"permission" => [
% {
"allow_create_engine" => false ,
"allow_fine_tuning" => false ,
"allow_logprobs" => true ,
...
}
] ,
"root" => "davinci-search-query"
} ,
... . ] ,
object: "list"
} }Voir: https://platform.openai.com/docs/api-reference/models/list
Récupérer des informations de modèle spécifiques
OpenAI . models ( "davinci-search-query" ) { :ok ,
% {
created: 1651172505 ,
id: "davinci-search-query" ,
object: "model" ,
owned_by: "openai-dev" ,
parent: nil ,
permission: [
% {
"allow_create_engine" => false ,
"allow_fine_tuning" => false ,
"allow_logprobs" => true ,
"allow_sampling" => true ,
"allow_search_indices" => true ,
"allow_view" => true ,
"created" => 1669066353 ,
"group" => nil ,
"id" => "modelperm-lYkiTZMmJMWm8jvkPx2duyHE" ,
"is_blocking" => false ,
"object" => "model_permission" ,
"organization" => "*"
}
] ,
root: "davinci-search-query"
} }Voir: https://platform.openai.com/docs/api-reference/models/retReve
Il renvoie un ou plusieurs achèvement prévus avec une invite. La fonction accepte comme arguments le "moteur_id" et l'ensemble des paramètres utilisés par l'API EXCHELIONS OpenAI
OpenAI . completions (
model: "finetuned-model" ,
prompt: "once upon a time" ,
max_tokens: 5 ,
temperature: 1 ,
...
) ## Example response
{ :ok , % {
choices: [
% {
"finish_reason" => "length" ,
"index" => 0 ,
"logprobs" => nil ,
"text" => " " thing we are given"
}
] ,
created: 1617147958 ,
id: "..." ,
model: "..." ,
object: "text_completion"
}
}Voir: https://platform.openai.com/docs/api-reference/completions/create
Cette API a été obsolète par OpenAI, car engines sont remplacés par models . Si vous l'utilisez, considérez pour passer aux completions(params) dès que possible!
OpenAI . completions (
"davinci" , # engine_id
prompt: "once upon a time" ,
max_tokens: 5 ,
temperature: 1 ,
...
) { :ok , % {
choices: [
% {
"finish_reason" => "length" ,
"index" => 0 ,
"logprobs" => nil ,
"text" => " " thing we are given"
}
] ,
created: 1617147958 ,
id: "..." ,
model: "..." ,
object: "text_completion"
}
}Voir: https://beta.openai.com/docs/api-reference/completions/create pour la liste complète des paramètres que vous pouvez transmettre à la fonction de complétion
Crée une réalisation du message de chat
OpenAI . chat_completion (
model: "gpt-3.5-turbo" ,
messages: [
% { role: "system" , content: "You are a helpful assistant." } ,
% { role: "user" , content: "Who won the world series in 2020?" } ,
% { role: "assistant" , content: "The Los Angeles Dodgers won the World Series in 2020." } ,
% { role: "user" , content: "Where was it played?" }
]
) { :ok ,
% {
choices: [
% {
"finish_reason" => "stop" ,
"index" => 0 ,
"message" => % {
"content" =>
"The 2020 World Series was played at Globe Life Field in Arlington, Texas due to the COVID-19 pandemic." ,
"role" => "assistant"
}
}
] ,
created: 1_677_773_799 ,
id: "chatcmpl-6pftfA4NO9pOQIdxao6Z4McDlx90l" ,
model: "gpt-3.5-turbo-0301" ,
object: "chat.completion" ,
usage: % {
"completion_tokens" => 26 ,
"prompt_tokens" => 56 ,
"total_tokens" => 82
}
} }Voir: https://platform.openai.com/docs/api-reference/chat/create pour la liste complète des paramètres que vous pouvez transmettre à la fonction de complétion
Crée une réalisation du message de chat, par défaut, il diffuse à self() , mais vous pouvez remplacer la configuration en passant un dépôt de configuration à la fonction avec un paramètre stream_to http_options différent.
import Config
config :openai ,
api_key: "your-api-key" ,
http_options: [ recv_timeout: :infinity , async: :once ] ,
... http_options doit être défini comme ci-dessus lorsque vous souhaitez traiter l'achèvement du chat comme un flux.
OpenAI . chat_completion ( [
model: "gpt-3.5-turbo" ,
messages: [
% { role: "system" , content: "You are a helpful assistant." } ,
% { role: "user" , content: "Who won the world series in 2020?" } ,
% { role: "assistant" , content: "The Los Angeles Dodgers won the World Series in 2020." } ,
% { role: "user" , content: "Where was it played?" }
] ,
stream: true , # set this param to true
]
)
|> Stream . each ( fn res ->
IO . inspect ( res )
end )
|> Stream . run ( ) % {
"choices" => [
% { "delta" => % { "role" => "assistant" } , "finish_reason" => nil , "index" => 0 }
] ,
"created" => 1682700668 ,
"id" => "chatcmpl-7ALbIuLju70hXy3jPa3o5VVlrxR6a" ,
"model" => "gpt-3.5-turbo-0301" ,
"object" => "chat.completion.chunk"
}
% {
"choices" => [
% { "delta" => % { "content" => "The" } , "finish_reason" => nil , "index" => 0 }
] ,
"created" => 1682700668 ,
"id" => "chatcmpl-7ALbIuLju70hXy3jPa3o5VVlrxR6a" ,
"model" => "gpt-3.5-turbo-0301" ,
"object" => "chat.completion.chunk"
}
% {
"choices" => [
% { "delta" => % { "content" => " World" } , "finish_reason" => nil , "index" => 0 }
] ,
"created" => 1682700668 ,
"id" => "chatcmpl-7ALbIuLju70hXy3jPa3o5VVlrxR6a" ,
"model" => "gpt-3.5-turbo-0301" ,
"object" => "chat.completion.chunk"
}
% {
"choices" => [
% {
"delta" => % { "content" => " Series" } ,
"finish_reason" => nil ,
"index" => 0
}
] ,
"created" => 1682700668 ,
"id" => "chatcmpl-7ALbIuLju70hXy3jPa3o5VVlrxR6a" ,
"model" => "gpt-3.5-turbo-0301" ,
"object" => "chat.completion.chunk"
}
% {
"choices" => [
% { "delta" => % { "content" => " in" } , "finish_reason" => nil , "index" => 0 }
] ,
"created" => 1682700668 ,
"id" => "chatcmpl-7ALbIuLju70hXy3jPa3o5VVlrxR6a" ,
"model" => "gpt-3.5-turbo-0301" ,
"object" => "chat.completion.chunk"
}
...Crée une nouvelle modification pour l'entrée, l'instruction et les paramètres fournis
OpenAI . edits (
model: "text-davinci-edit-001" ,
input: "What day of the wek is it?" ,
instruction: "Fix the spelling mistakes"
) { :ok ,
% {
choices: [ % { "index" => 0 , "text" => "What day of the week is it? n " } ] ,
created: 1675443483 ,
object: "edit" ,
usage: % {
"completion_tokens" => 28 ,
"prompt_tokens" => 25 ,
"total_tokens" => 53
}
} }Voir: https://platform.openai.com/docs/api-reference/edits/create
Cela génère une image basée sur l'invite donnée. Les fonctions d'image nécessitent certains moments pour s'exécuter, et l'API peut renvoyer une erreur de délai d'expiration, si nécessaire, vous pouvez passer une structure de configuration facultative avec HttpOison http_options comme deuxième argument de la fonction pour augmenter le délai d'attente.
OpenAI . images_generations (
[ prompt: "A developer writing a test" , size: "256x256" ] ,
% OpenAI.Config { http_options: [ recv_timeout: 10 * 60 * 1000 ] } # optional!
) { :ok ,
% {
created: 1670341737 ,
data: [
% {
"url" => ... Returned url
}
]
} } Remarque: Cette signature API a changé en v0.3.0 pour être conforme aux conventions d'autres API, l'alias OpenAI.image_generations(params, request_options) est toujours disponible pour la rétrocompatibilité. Si vous l'utilisez, envisagez de passer à OpenAI.images_generations(params, request_options) dès que possible.
Remarque2: La manière officielle de passer des http_options a changé en v0.5.0 pour être conforme aux conventions d'autres API, l'alias OpenAI.images_generations(file_path, params, request_options) , mais est toujours disponible pour la rétrocompatibilité. Si vous l'utilisez, considérez pour passer à OpenAI.images_variations(params, config)
Voir: https://platform.openai.com/docs/api-reference/images/create
Modifier une image existante basée sur les fonctions d'image invite nécessite certains fois pour s'exécuter, et l'API peut renvoyer une erreur de délai d'expiration, si nécessaire, vous pouvez transmettre une structure de configuration facultative avec HttpOison http_options comme deuxième argument de la fonction pour augmenter le délai d'attente.
OpenAI . images_edits (
"/home/developer/myImg.png" ,
[ prompt: "A developer writing a test" , size: "256x256" ] ,
% OpenAI.Config { http_options: [ recv_timeout: 10 * 60 * 1000 ] } # optional!
) { :ok ,
% {
created: 1670341737 ,
data: [
% {
"url" => ... Returned url
}
]
} } Remarque: La manière officielle de passer des http_options a changé dans v0.5.0 pour être conforme aux conventions d'autres API, l'alias OpenAI.images_edits(file_path, params, request_options) , mais est toujours disponible pour la rétrocompatibilité. Si vous l'utilisez, envisagez pour passer à OpenAI.images_edits(file_path, params, config)
Voir: https://platform.openai.com/docs/api-reference/images/create-edit
Les fonctions d'image nécessitent certains moments pour s'exécuter, et l'API peut renvoyer une erreur de délai d'expiration, si nécessaire, vous pouvez passer une structure de configuration facultative avec HttpOison http_options comme deuxième argument de la fonction pour augmenter le délai d'attente.
OpenAI . images_variations (
"/home/developer/myImg.png" ,
[ n: "5" ] ,
% OpenAI.Config { http_options: [ recv_timeout: 10 * 60 * 1000 ] } # optional!
) { :ok ,
% {
created: 1670341737 ,
data: [
% {
"url" => ... Returned url
}
]
} } Remarque: La manière officielle de passer des http_options a changé en v0.5.0 pour être conforme aux conventions d'autres API, l'alias OpenAI.images_variations(file_path, params, request_options) , mais est toujours disponible pour la rétrocompatibilité. Si vous l'utilisez, envisagez pour passer à OpenAI.images_edits(file_path, params, config)
Voir: https://platform.openai.com/docs/api-reference/images/create-variation
OpenAI . embeddings (
model: "text-embedding-ada-002" ,
input: "The food was delicious and the waiter..."
) { :ok ,
% {
data: [
% {
"embedding" => [ 0.0022523515000000003 , - 0.009276069000000001 ,
0.015758524000000003 , - 0.007790373999999999 , - 0.004714223999999999 ,
0.014806155000000001 , - 0.009803046499999999 , - 0.038323310000000006 ,
- 0.006844355 , - 0.028672641 , 0.025345700000000002 , 0.018145794000000003 ,
- 0.0035904291999999997 , - 0.025498080000000003 , 5.142790000000001e-4 ,
- 0.016317246 , 0.028444072 , 0.0053713582 , 0.009631619999999999 ,
- 0.016469626 , - 0.015390275 , 0.004301531 , 0.006984035499999999 ,
- 0.007079272499999999 , - 0.003926933 , 0.018602932000000003 , 0.008666554 ,
- 0.022717162999999995 , 0.011460166999999997 , 0.023860006 ,
0.015568050999999998 , - 0.003587254600000001 , - 0.034843990000000005 ,
- 0.0041555012999999995 , - 0.026107594000000005 , - 0.02151083 ,
- 0.0057618289999999996 , 0.011714132499999998 , 0.008355445999999999 ,
0.004098358999999999 , 0.019199749999999998 , - 0.014336321 , 0.008952264 ,
0.0063395994 , - 0.04576447999999999 , ... ] ,
"index" => 0 ,
"object" => "embedding"
}
] ,
model: "text-embedding-ada-002-v2" ,
object: "list" ,
usage: % { "prompt_tokens" => 8 , "total_tokens" => 8 }
} }Voir: https://platform.openai.com/docs/api-reference/embedings/create
Génère l'audio à partir du texte d'entrée.
OpenAI . audio_speech (
model: "tts-1" ,
input: "You know that Voight-Kampf test of yours. Did you ever take that test yourself?" ,
voice: "alloy"
) { :ok , << 255 , 255 , ... >> }Voir: https://platform.openai.com/docs/api-reference/audio/create pour obtenir des informations sur les paramètres acceptés par l'API
Transcrit l'audio dans la langue d'entrée.
OpenAI . audio_transcription (
"./path_to_file/blade_runner.mp3" , # file path
model: "whisper-1"
) { :ok ,
% {
text: "I've seen things you people wouldn't believe.."
} }Voir: https://platform.openai.com/docs/api-reference/audio/create pour obtenir des informations sur les paramètres acceptés par l'API
Traduit l'audio en anglais.
OpenAI . audio_translation (
"./path_to_file/werner_herzog_interview.mp3" , # file path
model: "whisper-1"
) { :ok ,
% {
text: "I thought if I walked, I would be saved. It was almost like a pilgrimage. I will definitely continue to walk long distances. It is a very unique form of life and existence that we have lost almost entirely from our normal life."
}
}Voir: https://platform.openai.com/docs/api-reference/audio/create pour obtenir des informations sur les paramètres acceptés par l'API
Renvoie une liste de fichiers appartenant à l'organisation de l'utilisateur.
OpenAI . files ( ) { :ok ,
% {
data: [
% {
"bytes" => 123 ,
"created_at" => 213 ,
"filename" => "file.jsonl" ,
"id" => "file-123321" ,
"object" => "file" ,
"purpose" => "fine-tune" ,
"status" => "processed" ,
"status_details" => nil
}
] ,
object: "list"
}
}Voir: https://platform.openai.com/docs/api-reference/files
Renvoie un fichier qui appartient à l'organisation de l'utilisateur, étant donné un ID de fichier
OpenAI . files ( "file-123321" ) { :ok ,
% {
bytes: 923 ,
created_at: 1675370979 ,
filename: "file.jsonl" ,
id: "file-123321" ,
object: "file" ,
purpose: "fine-tune" ,
status: "processed" ,
status_details: nil
}
}Voir: https://platform.openai.com/docs/api-reference/files/retReve
Téléchargez un fichier contenant des documents à utiliser sur divers points de terminaison / fonctionnalités. Actuellement, la taille de tous les fichiers téléchargés par une organisation peut atteindre 1 Go. Veuillez contacter OpenAI si vous devez augmenter la limite de stockage.
OpenAI . files_upload ( "./file.jsonl" , purpose: "fine-tune" ) { :ok ,
% {
bytes: 923 ,
created_at: 1675373519 ,
filename: "file.jsonl" ,
id: "file-123" ,
object: "file" ,
purpose: "fine-tune" ,
status: "uploaded" ,
status_details: nil
}
}Voir: https://platform.openai.com/docs/api-reference/files/upload
Supprimer un fichier
OpenAI . files_delete ( "file-123" ) { :ok , % { deleted: true , id: "file-123" , object: "file" } }Voir: https://platform.openai.com/docs/api-reference/files/delete
Énumérez les travaux de réglage fin de votre organisation.
OpenAI . finetunes ( ) { :ok ,
% {
object: "list" ,
data: [ % {
"id" => "t-AF1WoRqd3aJAHsqc9NY7iL8F" ,
"object" => "fine-tune" ,
"model" => "curie" ,
"created_at" => 1614807352 ,
"fine_tuned_model" => null ,
"hyperparams" => { ... } ,
"organization_id" => "org-..." ,
"result_files" = [ ] ,
"status": "pending" ,
"validation_files" => [ ] ,
"training_files" => [ { ... } ] ,
"updated_at" => 1614807352 ,
} ] ,
}
}Voir: https://platform.openai.com/docs/api-reference/fine-tunes/list
Obtient des informations sur un travail final.
OpenAI . finetunes ( "t-AF1WoRqd3aJAHsqc9NY7iL8F" ) { :ok ,
% {
object: "list" ,
data: [ % {
"id" => "t-AF1WoRqd3aJAHsqc9NY7iL8F" ,
"object" => "fine-tune" ,
"model" => "curie" ,
"created_at" => 1614807352 ,
"fine_tuned_model" => null ,
"hyperparams" => { ... } ,
"organization_id" => "org-..." ,
"result_files" = [ ] ,
"status": "pending" ,
"validation_files" => [ ] ,
"training_files" => [ { ... } ] ,
"updated_at" => 1614807352 ,
} ] ,
}
}Voir: https://platform.openai.com/docs/api-reference/fine-tunes/retReve
Crée un travail qui affine un modèle spécifié à partir d'un ensemble de données donné.
OpenAI . finetunes_create (
training_file: "file-123213231" ,
model: "curie" ,
) { :ok ,
% {
created_at: 1675527767 ,
events: [
% {
"created_at" => 1675527767 ,
"level" => "info" ,
"message" => "Created fine-tune: ft-IaBYfSSAK47UUCbebY5tBIEj" ,
"object" => "fine-tune-event"
}
] ,
fine_tuned_model: nil ,
hyperparams: % {
"batch_size" => nil ,
"learning_rate_multiplier" => nil ,
"n_epochs" => 4 ,
"prompt_loss_weight" => 0.01
} ,
id: "ft-IaBYfSSAK47UUCbebY5tBIEj" ,
model: "curie" ,
object: "fine-tune" ,
organization_id: "org-1iPTOIak4b5fpuIB697AYMmO" ,
result_files: [ ] ,
status: "pending" ,
training_files: [
% {
"bytes" => 923 ,
"created_at" => 1675373519 ,
"filename" => "file-12321323.jsonl" ,
"id" => "file-12321323" ,
"object" => "file" ,
"purpose" => "fine-tune" ,
"status" => "processed" ,
"status_details" => nil
}
] ,
updated_at: 1675527767 ,
validation_files: [ ]
} }Voir: https://platform.openai.com/docs/api-reference/fine-tunes/create
Obtenez des mises à jour de statut à grain fin pour un emploi à amende.
OpenAI . finetunes_list_events ( "ft-AF1WoRqd3aJAHsqc9NY7iL8F" ) { :ok ,
% {
data: [
% {
"created_at" => 1675376995 ,
"level" => "info" ,
"message" => "Created fine-tune: ft-123" ,
"object" => "fine-tune-event"
} ,
% {
"created_at" => 1675377104 ,
"level" => "info" ,
"message" => "Fine-tune costs $0.00" ,
"object" => "fine-tune-event"
} ,
% {
"created_at" => 1675377105 ,
"level" => "info" ,
"message" => "Fine-tune enqueued. Queue number: 18" ,
"object" => "fine-tune-event"
} ,
... ,
]
}
}Voir: https://platform.openai.com/docs/api-reference/fine-tunes/events
Annulez immédiatement un travail d'adaptation.
OpenAI . finetunes_cancel ( "ft-AF1WoRqd3aJAHsqc9NY7iL8F" ) { :ok ,
% {
created_at: 1675527767 ,
events: [
...
% {
"created_at" => 1675528080 ,
"level" => "info" ,
"message" => "Fine-tune cancelled" ,
"object" => "fine-tune-event"
}
] ,
fine_tuned_model: nil ,
hyperparams: % {
"batch_size" => 1 ,
"learning_rate_multiplier" => 0.1 ,
"n_epochs" => 4 ,
"prompt_loss_weight" => 0.01
} ,
id: "ft-IaBYfSSAK47UUCbebY5tBIEj" ,
model: "curie" ,
object: "fine-tune" ,
organization_id: "org-1iPTOIak4b5fpuIB697AYMmO" ,
result_files: [ ] ,
status: "cancelled" ,
training_files: [
% {
"bytes" => 923 ,
"created_at" => 1675373519 ,
"filename" => "file123.jsonl" ,
"id" => "file-123" ,
"object" => "file" ,
"purpose" => "fine-tune" ,
"status" => "processed" ,
"status_details" => nil
}
] ,
updated_at: 1675528080 ,
validation_files: [ ]
} }Annulez immédiatement un travail d'adaptation.
OpenAI . finetunes_delete_model ( "model-id" ) { :ok ,
% {
id: "model-id" ,
object: "model" ,
deleted: true
}
}Voir: https://platform.openai.com/docs/api-reference/fine-tunes/delete-model
Classifie si le texte viole la politique de contenu d'Openai
OpenAI . moderations ( input: "I want to kill everyone!" ) { :ok ,
% {
id: "modr-6gEWXyuaU8dqiHpbAHIsdru0zuC88" ,
model: "text-moderation-004" ,
results: [
% {
"categories" => % {
"hate" => false ,
"hate/threatening" => false ,
"self-harm" => false ,
"sexual" => false ,
"sexual/minors" => false ,
"violence" => true ,
"violence/graphic" => false
} ,
"category_scores" => % {
"hate" => 0.05119025334715844 ,
"hate/threatening" => 0.00321022979915142 ,
"self-harm" => 7.337320857914165e-5 ,
"sexual" => 1.1111642379546538e-6 ,
"sexual/minors" => 3.588798147546868e-10 ,
"violence" => 0.9190407395362855 ,
"violence/graphic" => 1.2791929293598514e-7
} ,
"flagged" => true
}
]
} }Voir: https://platform.openai.com/docs/api-reference/moderations/create
Les API suivantes sont actuellement en version bêta, pour les utiliser, assurez-vous de définir le paramètre beta dans votre configuration.
config :openai ,
# optional, use when required by an OpenAI API beta, e.g.:
beta: "assistants=v1"Récupère la liste des assistants.
OpenAI . assistants ( ) { :ok ,
% {
data: [
% {
"created_at" => 1699472932 ,
"description" => nil ,
"file_ids" => [ "file-..." ] ,
"id" => "asst_..." ,
"instructions" => "..." ,
"metadata" => % { } ,
"model" => "gpt-4-1106-preview" ,
"name" => "..." ,
"object" => "assistant" ,
"tools" => [ % { "type" => "retrieval" } ]
}
] ,
first_id: "asst_..." ,
has_more: false ,
last_id: "asst_..." ,
object: "list"
} }Voir: https://platform.openai.com/docs/api-reference/assistants/Listassistants
Récupère la liste des assistants filtrés par paramètres de requête.
OpenAI . assistants ( after: "" , limit: 10 ) { :ok ,
% {
data: [
% {
"created_at" => 1699472932 ,
"description" => nil ,
"file_ids" => [ "file-..." ] ,
"id" => "asst_..." ,
"instructions" => "..." ,
"metadata" => % { } ,
"model" => "gpt-4-1106-preview" ,
"name" => "..." ,
"object" => "assistant" ,
"tools" => [ % { "type" => "retrieval" } ]
} ,
...
] ,
first_id: "asst_..." ,
has_more: false ,
last_id: "asst_..." ,
object: "list"
} }Voir: https://platform.openai.com/docs/api-reference/assistants/Listassistants
Récupère un assistant par son identifiant.
OpenAI . assistants ( "asst_..." ) { :ok ,
% {
created_at: 1699472932 ,
description: nil ,
file_ids: [ "file-..." ] ,
id: "asst_..." ,
instructions: "..." ,
metadata: % { } ,
model: "gpt-4-1106-preview" ,
name: "..." ,
object: "assistant" ,
tools: [ % { "type" => "retrieval" } ]
} }Voir: https://platform.openai.com/docs/api-reference/assistants/getassistant
Crée un nouvel assistant.
OpenAI . assistants_create (
model: "gpt-3.5-turbo-1106" ,
name: "My assistant" ,
instructions: "You are a research assistant." ,
tools: [
% { type: "retrieval" }
] ,
file_ids: [ "file-..." ]
) { :ok ,
% {
created_at: 1699640038 ,
description: nil ,
file_ids: [ "file-..." ] ,
id: "asst_..." ,
instructions: "You are a research assistant." ,
metadata: % { } ,
model: "gpt-3.5-turbo-1106" ,
name: "My assistant" ,
object: "assistant" ,
tools: [ % { "type" => "retrieval" } ]
} }Voir: https://platform.openai.com/docs/api-reference/assistants/createasSistant
Modifie un assistant existant.
OpenAI . assistants_modify (
"asst_..." ,
model: "gpt-4-1106-preview" ,
name: "My upgraded assistant"
) { :ok ,
% {
created_at: 1699640038 ,
description: nil ,
file_ids: [ "file-..." ] ,
id: "asst_..." ,
instructions: "You are a research assistant." ,
metadata: % { } ,
model: "gpt-4-1106-preview" ,
name: "My upgraded assistant"
object: "assistant" ,
tools: [ % { "type" => "retrieval" } ]
} }Voir: https://platform.openai.com/docs/api-reference/assistants/modifyassistant
Supprime un assistant.
OpenAI . assistants_delete ( "asst_..." ) { :ok ,
% {
deleted: true ,
id: "asst_..." ,
object: "assistant.deleted"
} }Voir: https://platform.openai.com/docs/api-reference/assistants/deleasSistant
Récupère la liste des fichiers associés à un assistant particulier.
OpenAI . assistant_files ( "asst_..." ) { :ok ,
% {
data: [
% {
"assistant_id" => "asst_..." ,
"created_at" => 1699472933 ,
"id" => "file-..." ,
"object" => "assistant.file"
}
] ,
first_id: "file-..." ,
has_more: false ,
last_id: "file-..." ,
object: "list"
} }Voir: https://platform.openai.com/docs/api-reference/assistants/listassistantfiles
Récupère la liste des fichiers associés à un assistant particulier, filtré par paramètres de requête.
OpenAI . assistant_files ( "asst_..." , order: "desc" ) { :ok ,
% {
data: [
% {
"assistant_id" => "asst_..." ,
"created_at" => 1699472933 ,
"id" => "file-..." ,
"object" => "assistant.file"
}
] ,
first_id: "file-..." ,
has_more: false ,
last_id: "file-..." ,
object: "list"
} }Voir: https://platform.openai.com/docs/api-reference/assistants/listassistantfiles
Récupère un dossier assistant par son identifiant
OpenAI . assistant_file ( "asst_..." , "file_..." ) { :ok ,
% {
assistant_id: "asst_..." ,
created_at: 1699472933 ,
id: "file-..." ,
object: "assistant.file"
} }Voir: https://platform.openai.com/docs/api-reference/assistants/getassistantfile
Joigne un fichier précédemment téléchargé sur l'assistant.
OpenAI . assistant_file_create ( "asst_..." , file_id: "file-..." ) { :ok ,
% {
assistant_id: "asst_..." ,
created_at: 1699472933 ,
id: "file-..." ,
object: "assistant.file"
} }Voir: https://platform.openai.com/docs/api-reference/assistants/createasSistantfile
Détache un dossier de l'assistant. Le fichier lui-même n'est pas automatiquement supprimé.
OpenAI . assistant_file_delete ( "asst_..." , "file-..." ) { :ok ,
% {
deleted: true ,
id: "file-..." ,
object: "assistant.file.deleted"
} }Voir: https://platform.openai.com/docs/api-reference/assistants/DeleSheSistantFile
Récupère la liste des fils. Remarque: Au moment de la rédaction de cet article, cette fonctionnalité reste sans papiers par OpenAI.
OpenAI . threads ( ) { :ok ,
% {
data: [
% {
"created_at" => 1699705727 ,
"id" => "thread_..." ,
"metadata" => % { "key_1" => "value 1" , "key_2" => "value 2" } ,
"object" => "thread"
} ,
...
] ,
first_id: "thread_..." ,
has_more: false ,
last_id: "thread_..." ,
object: "list"
} }Récupère la liste des threads par paramètres de requête. Remarque: Au moment de la rédaction de cet article, cette fonctionnalité reste sans papiers par OpenAI.
OpenAI . threads ( limit: 2 ) { :ok ,
% {
data: [
% {
"created_at" => 1699705727 ,
"id" => "thread_..." ,
"metadata" => % { "key_1" => "value 1" , "key_2" => "value 2" } ,
"object" => "thread"
} ,
...
] ,
first_id: "thread_..." ,
has_more: false ,
last_id: "thread_..." ,
object: "list"
} }Crée un nouveau fil avec quelques messages et métadonnées.
messages = [
% {
role: "user" ,
content: "Hello, what is AI?" ,
file_ids: [ "file-..." ]
} ,
% {
role: "user" ,
content: "How does AI work? Explain it in simple terms."
} ,
]
metadata = % {
key_1: "value 1" ,
key_2: "value 2"
}
OpenAI . threads_create ( messages: messages , metadata: metadata ) { :ok ,
% {
created_at: 1699703890 ,
id: "thread_..." ,
metadata: % { "key_1" => "value 1" , "key_2" => "value 2" } ,
object: "thread"
} }Voir: https://platform.openai.com/docs/api-reference/threads/createthread
Crée un nouveau fil et l'exécute.
messages = [
% {
role: "user" ,
content: "Hello, what is AI?" ,
file_ids: [ "file-..." ]
} ,
% {
role: "user" ,
content: "How does AI work? Explain it in simple terms."
} ,
]
thread_metadata = % {
key_1: "value 1" ,
key_2: "value 2"
}
thread = % {
messages: messages ,
metadata: thread_metadata
}
run_metadata = % {
key_3: "value 3"
}
params = [
assistant_id: "asst_..." ,
thread: thread ,
model: "gpt-4-1106-preview" ,
instructions: "You are an AI learning assistant." ,
tools: [ % {
"type" => "retrieval"
} ] ,
metadata: run_metadata
]
OpenAI . threads_create_and_run ( params ) { :ok ,
% {
assistant_id: "asst_..." ,
cancelled_at: nil ,
completed_at: nil ,
created_at: 1699897907 ,
expires_at: 1699898507 ,
failed_at: nil ,
file_ids: [ "file-..." ] ,
id: "run_..." ,
instructions: "You are an AI learning assistant." ,
last_error: nil ,
metadata: % { "key_3" => "value 3" } ,
model: "gpt-4-1106-preview" ,
object: "thread.run" ,
started_at: nil ,
status: "queued" ,
thread_id: "thread_..." ,
tools: [ % { "type" => "retrieval" } ]
} }Voir: https://platform.openai.com/docs/api-reference/runs/createthreadandrun
Modifie un thread existant.
metadata = % {
key_3: "value 3"
}
OpenAI . threads_modify ( "thread_..." , metadata: metadata ) { :ok ,
% {
created_at: 1699704406 ,
id: "thread_..." ,
metadata: % { "key_1" => "value 1" , "key_2" => "value 2" , "key_3" => "value 3" } ,
object: "thread"
} }Voir: https://platform.openai.com/docs/api-reference/threads/modifythread
Modifie un thread existant.
OpenAI . threads_delete ( "thread_..." ) { :ok ,
% {
deleted: true ,
id: "thread_..." ,
object: "thread.deleted"
} }Voir: https://platform.openai.com/docs/api-reference/threads/deleTethread
Récupère la liste des messages associés à un thread particulier.
OpenAI . thread_messages ( "thread_..." ) { :ok ,
% {
data: [
% {
"assistant_id" => nil ,
"content" => [
% {
"text" => % {
"annotations" => [ ] ,
"value" => "How does AI work? Explain it in simple terms."
} ,
"type" => "text"
}
] ,
"created_at" => 1699705727 ,
"file_ids" => [ ] ,
"id" => "msg_..." ,
"metadata" => % { } ,
"object" => "thread.message" ,
"role" => "user" ,
"run_id" => nil ,
"thread_id" => "thread_..."
} ,
...
] ,
first_id: "msg_..." ,
has_more: false ,
last_id: "msg_..." ,
object: "list"
} }Voir: https://platform.openai.com/docs/api-reference/messages/listMessages
Récupère la liste des messages associés à un thread particulier, filtré par paramètres de requête.
OpenAI . thread_messages ( "thread_..." , after: "msg_..." ) { :ok ,
% {
data: [
% {
"assistant_id" => nil ,
"content" => [
% {
"text" => % {
"annotations" => [ ] ,
"value" => "How does AI work? Explain it in simple terms."
} ,
"type" => "text"
}
] ,
"created_at" => 1699705727 ,
"file_ids" => [ ] ,
"id" => "msg_..." ,
"metadata" => % { } ,
"object" => "thread.message" ,
"role" => "user" ,
"run_id" => nil ,
"thread_id" => "thread_..."
} ,
...
] ,
first_id: "msg_..." ,
has_more: false ,
last_id: "msg_..." ,
object: "list"
} }Voir: https://platform.openai.com/docs/api-reference/messages/listMessages
Récupère un message de fil par son identifiant.
OpenAI . thread_message ( "thread_..." , "msg_..." ) { :ok ,
% {
assistant_id: nil ,
content: [
% {
"text" => % { "annotations" => [ ] , "value" => "Hello, what is AI?" } ,
"type" => "text"
}
] ,
created_at: 1699705727 ,
file_ids: [ "file-..." ] ,
id: "msg_..." ,
metadata: % { } ,
object: "thread.message" ,
role: "user" ,
run_id: nil ,
thread_id: "thread_..."
} }Voir: https://platform.openai.com/docs/api-reference/messages/getMessage
Crée un message dans un fil.
params = [
role: "user" ,
content: "Hello, what is AI?" ,
file_ids: [ "file-9Riyo515uf9KVfwdSrIQiqtC" ] ,
metadata: % {
key_1: "value 1" ,
key_2: "value 2"
}
]
OpenAI . thread_message_create ( "thread_..." , params ) { :ok ,
% {
assistant_id: nil ,
content: [
% {
"text" => % { "annotations" => [ ] , "value" => "Hello, what is AI?" } ,
"type" => "text"
}
] ,
created_at: 1699706818 ,
file_ids: [ "file-..." ] ,
id: "msg_..." ,
metadata: % { "key_1" => "value 1" , "key_2" => "value 2" } ,
object: "thread.message" ,
role: "user" ,
run_id: nil ,
thread_id: "thread_..."
} }Voir: https://platform.openai.com/docs/api-reference/messages/createMessage
Crée un message dans un fil.
params = [
metadata: % {
key_3: "value 3"
}
]
OpenAI . thread_message_modify ( "thread_..." , "msg_..." , params ) { :ok ,
% {
assistant_id: nil ,
content: [
% {
"text" => % { "annotations" => [ ] , "value" => "Hello, what is AI?" } ,
"type" => "text"
}
] ,
created_at: 1699706818 ,
file_ids: [ "file-..." ] ,
id: "msg_..." ,
metadata: % { "key_1" => "value 1" , "key_2" => "value 2" , "key_3" => "value 3" } ,
object: "thread.message" ,
role: "user" ,
run_id: nil ,
thread_id: "thread_..."
} }Voir: https://platform.openai.com/docs/api-reference/messages/modifymesage
Récupère la liste des fichiers associés à un message particulier d'un thread.
OpenAI . thread_message_files ( "thread_..." , "msg_..." ) { :ok ,
% {
data: [
% {
"created_at" => 1699706818 ,
"id" => "file-..." ,
"message_id" => "msg_..." ,
"object" => "thread.message.file"
}
] ,
first_id: "file-..." ,
has_more: false ,
last_id: "file-..." ,
object: "list"
} }Voir: https://platform.openai.com/docs/api-reference/messages/listMessageFiles
Récupère la liste des fichiers associés à un message particulier d'un thread, filtré par paramètres de requête.
OpenAI . thread_message_files ( "thread_..." , "msg_..." , after: "file-..." ) { :ok ,
% {
data: [
% {
"created_at" => 1699706818 ,
"id" => "file-..." ,
"message_id" => "msg_..." ,
"object" => "thread.message.file"
}
] ,
first_id: "file-..." ,
has_more: false ,
last_id: "file-..." ,
object: "list"
} }Voir: https://platform.openai.com/docs/api-reference/messages/listMessageFiles
Récupère l'objet de fichier de message.
OpenAI . thread_message_file ( "thread_..." , "msg_..." , "file-..." ) { :ok ,
% {
created_at: 1699706818 ,
id: "file-..." ,
message_id: "msg_..." ,
object: "thread.message.file"
} }Voir: https://platform.openai.com/docs/api-reference/messages/getmesagefile
Récupère la liste des exécutions associées à un thread particulier, filtré par paramètres de requête.
OpenAI . thread_runs ( "thread_..." , limit: 10 ) { :ok , % {
data: [ ] ,
first_id: nil ,
has_more: false ,
last_id: nil ,
object: "list"
} }Voir: https://platform.openai.com/docs/api-reference/runs/listruns
Récupère un thread particulier exécuté par son identifiant.
OpenAI . thread_run ( "thread_..." , "run_..." ) { :ok ,
% {
assistant_id: "asst_J" ,
cancelled_at: nil ,
completed_at: 1700234149 ,
created_at: 1700234128 ,
expires_at: nil ,
failed_at: nil ,
file_ids: [ ] ,
id: "run_" ,
instructions: "You are an AI learning assistant." ,
last_error: nil ,
metadata: % { "key_3" => "value 3" } ,
model: "gpt-4-1106-preview" ,
object: "thread.run" ,
started_at: 1700234129 ,
status: "expired" ,
thread_id: "thread_" ,
tools: [ % { "type" => "retrieval" } ]
} }Voir: https://platform.openai.com/docs/api-reference/runs/getrun
Crée une course pour un fil à l'aide d'un assistant particulier.
params = [
assistant_id: "asst_..." ,
model: "gpt-4-1106-preview" ,
tools: [ % {
"type" => "retrieval"
} ]
]
OpenAI . thread_run_create ( "thread_..." , params ) { :ok ,
% {
assistant_id: "asst_..." ,
cancelled_at: nil ,
completed_at: nil ,
created_at: 1699711115 ,
expires_at: 1699711715 ,
failed_at: nil ,
file_ids: [ "file-..." ] ,
id: "run_..." ,
instructions: "..." ,
last_error: nil ,
metadata: % { } ,
model: "gpt-4-1106-preview" ,
object: "thread.run" ,
started_at: nil ,
status: "queued" ,
thread_id: "thread_..." ,
tools: [ % { "type" => "retrieval" } ]
} }Voir: https://platform.openai.com/docs/api-reference/runs/createrun
Modifie une exécution de thread existante.
params = [
metadata: % {
key_3: "value 3"
}
]
OpenAI . thread_run_modify ( "thread_..." , "run_..." , params ) { :ok ,
% {
assistant_id: "asst_..." ,
cancelled_at: nil ,
completed_at: 1699711125 ,
created_at: 1699711115 ,
expires_at: nil ,
failed_at: nil ,
file_ids: [ "file-..." ] ,
id: "run_..." ,
instructions: "..." ,
last_error: nil ,
metadata: % { "key_3" => "value 3" } ,
model: "gpt-4-1106-preview" ,
object: "thread.run" ,
started_at: 1699711115 ,
status: "expired" ,
thread_id: "thread_..." ,
tools: [ % { "type" => "retrieval" } ]
} }Voir: https://platform.openai.com/docs/api-reference/runs/modifyrun
Lorsqu'une exécution a le statut: "requires_action" et required_action.type est submit_tool_outputs , ce point de terminaison peut être utilisé pour soumettre les sorties des appels de l'outil une fois tous terminés. Toutes les sorties doivent être soumises en une seule demande.
params = [
tool_outputs: [ % {
tool_call_id: "call_abc123" ,
output: "test"
} ]
]
OpenAI . thread_run_submit_tool_outputs ( "thread_..." , "run_..." , params ) { :ok ,
% {
assistant_id: "asst_abc123" ,
cancelled_at: nil ,
completed_at: nil ,
created_at: 1699075592 ,
expires_at: 1699076192 ,
failed_at: nil ,
file_ids: [ ] ,
id: "run_abc123" ,
instructions: "You tell the weather." ,
last_error: nil ,
metadata: % { } ,
model: "gpt-4" ,
object: "thread.run" ,
started_at: 1699075592 ,
status: "queued" ,
thread_id: "thread_abc123" ,
tools: [
% {
"function" => % {
"description" => "Determine weather in my location" ,
"name" => "get_weather" ,
"parameters" => % {
"properties" => % {
"location" => % {
"description" => "The city and state e.g. San Francisco, CA" ,
"type" => "string"
} ,
"unit" => % { "enum" => [ "c" , "f" ] , "type" => "string" }
} ,
"required" => [ "location" ] ,
"type" => "object"
}
} ,
"type" => "function"
}
]
}
}Voir: https://platform.openai.com/docs/api-reference/runs/submittooloutputs
Annule une course in_progress .
OpenAI . thread_run_cancel ( "thread_..." , "run_..." ) { :ok ,
% {
assistant_id: "asst_..." ,
cancelled_at: nil ,
completed_at: 1699711125 ,
created_at: 1699711115 ,
expires_at: nil ,
failed_at: nil ,
file_ids: [ "file-..." ] ,
id: "run_..." ,
instructions: "..." ,
last_error: nil ,
metadata: % { "key_3" => "value 3" } ,
model: "gpt-4-1106-preview" ,
object: "thread.run" ,
started_at: 1699711115 ,
status: "expired" ,
thread_id: "thread_..." ,
tools: [ % { "type" => "retrieval" } ]
} }Voir: https://platform.openai.com/docs/api-reference/runs/cancelrun
Récupère la liste des étapes associées à une série particulière d'un fil.
OpenAI . thread_run_steps ( "thread_..." , "run_..." ) { :ok ,
% {
data: [
% {
"assistant_id" => "asst_..." ,
"cancelled_at" => nil ,
"completed_at" => 1699897927 ,
"created_at" => 1699897908 ,
"expires_at" => nil ,
"failed_at" => nil ,
"id" => "step_..." ,
"last_error" => nil ,
"object" => "thread.run.step" ,
"run_id" => "run_..." ,
"status" => "completed" ,
"step_details" => % {
"message_creation" => % { "message_id" => "msg_..." } ,
"type" => "message_creation"
} ,
"thread_id" => "thread_..." ,
"type" => "message_creation"
}
] ,
first_id: "step_..." ,
has_more: false ,
last_id: "step_..." ,
object: "list"
} }Voir: https://platform.openai.com/docs/api-reference/runs/listrunsteps
Récupère la liste des étapes associées à une exécution particulière d'un thread, filtrée par paramètres de requête.
OpenAI . thread_run_steps ( "thread_..." , "run_..." , order: "asc" ) { :ok ,
% {
data: [
% {
"assistant_id" => "asst_..." ,
"cancelled_at" => nil ,
"completed_at" => 1699897927 ,
"created_at" => 1699897908 ,
"expires_at" => nil ,
"failed_at" => nil ,
"id" => "step_..." ,
"last_error" => nil ,
"object" => "thread.run.step" ,
"run_id" => "run_..." ,
"status" => "completed" ,
"step_details" => % {
"message_creation" => % { "message_id" => "msg_..." } ,
"type" => "message_creation"
} ,
"thread_id" => "thread_..." ,
"type" => "message_creation"
}
] ,
first_id: "step_..." ,
has_more: false ,
last_id: "step_..." ,
object: "list"
} }Voir: https://platform.openai.com/docs/api-reference/runs/listrunsteps
Récupère la liste des étapes associées à une exécution particulière d'un thread, filtrée par paramètres de requête.
OpenAI . thread_run_steps ( "thread_..." , "run_..." , order: "asc" ) { :ok ,
% {
data: [
% {
"assistant_id" => "asst_..." ,
"cancelled_at" => nil ,
"completed_at" => 1699897927 ,
"created_at" => 1699897908 ,
"expires_at" => nil ,
"failed_at" => nil ,
"id" => "step_..." ,
"last_error" => nil ,
"object" => "thread.run.step" ,
"run_id" => "run_..." ,
"status" => "completed" ,
"step_details" => % {
"message_creation" => % { "message_id" => "msg_..." } ,
"type" => "message_creation"
} ,
"thread_id" => "thread_..." ,
"type" => "message_creation"
}
] ,
first_id: "step_..." ,
has_more: false ,
last_id: "step_..." ,
object: "list"
} }Voir: https://platform.openai.com/docs/api-reference/runs/listrunsteps
Récupère une étape d'exécution de thread par son identifiant.
OpenAI . thread_run_step ( "thread_..." , "run_..." , "step_..." ) { :ok ,
% {
assistant_id: "asst_..." ,
cancelled_at: nil ,
completed_at: 1699897927 ,
created_at: 1699897908 ,
expires_at: nil ,
failed_at: nil ,
id: "step_..." ,
last_error: nil ,
object: "thread.run.step" ,
run_id: "run_..." ,
status: "completed" ,
step_details: % {
"message_creation" => % { "message_id" => "msg_..." } ,
"type" => "message_creation"
} ,
thread_id: "thread_..." ,
type: "message_creation"
} }Voir: https://platform.openai.com/docs/api-reference/runs/getrunstep
Les API suivantes sont obsolètes, mais actuellement prises en charge par la bibliothèque pour la rétrocompatibilité avec des versions plus anciennes. Si vous utilisez les API suivantes, envisagez de le supprimer dès que possible de votre projet!
Remarque: De la version 0.5.0 Recherche, les réponses, les classifications API ne sont pas prises en charge (puisqu'ils ont été supprimés par OpenAI), si vous en avez toujours besoin, envisagez d'utiliser V0.4.2
Obtenez la liste des moteurs disponibles
OpenAI . engines ( ) { :ok , % {
"data" => [
% { "id" => "davinci" , "object" => "engine" , "max_replicas": ... } ,
... ,
...
]
}
Voir: https://beta.openai.com/docs/api-reference/ngines/list
Récupérer des informations spécifiques sur le moteur
OpenAI . engines ( "davinci" ) { :ok , % {
"id" => "davinci" ,
"object" => "engine" ,
"max_replicas": ...
}
}Voir: https://beta.openai.com/docs/api-reference/ngines/retReve
Le package est disponible en open source en vertu des termes de la licence MIT.
