openai.ex
v0.6.2
Envoltorio no oficial de la comunidad Mantenida para las API de REST OPERAI Vea https://platform.openai.com/docs/api-reference/introduction para obtener información adicional sobre puntos finales REST
¡Gracias por su comprensión y apoyo y gracias a todos los que han contribuido a la biblioteca hasta ahora!
Agregar : OpenAI como dependencia en su archivo mix.exs.
def deps do
[
{ :openai , "~> 0.6.2" }
]
end Puede configurar OpenAI en su mezcla config.exs (predeterminado $ proyecto_root/config/config.exs). Si está utilizando Phoenix, agregue la configuración en sus archivos config/dev.exs | test.exs | prod.exs. Una configuración de ejemplo es:
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/" Nota: puede cargar sus variables ENV de sistema operativo en el archivo de configuración, si establece una variable ENV para la tecla API llamada OPENAI_API_KEY puede obtenerlo en el código haciendo System.get_env("OPENAI_API_KEY") .
config.exs es el tiempo de compilación, por lo que la función get_env/1 se ejecuta durante la compilación, si desea obtener las variables ENV durante el tiempo de ejecución, use runtime.exs en lugar de config.exs en su aplicación (Elixir Doc Ref).
La configuración de la biblioteca de clientes se puede sobrescribir en tiempo de ejecución pasando un %OpenAI.Config{} structs como último argumento de la función que necesita usar. Por ejemplo, si necesita usar un api_key , organization_key o http_options diferente, simplemente puede hacer:
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?" }
]
) Puede realizar una anulación de configuración en todas las funciones, tenga en cuenta que el argumento params debe aprobarse explícitamente como una lista en los soportes cuadrados si la configuración se debe sobrescribir, como en el ejemplo anterior.
Obtenga su clave API de https://platform.openai.com/account/api-keys
Recuperar la lista de modelos 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"
} }Ver: https://platform.openai.com/docs/api-reference/models/list
Recuperar información de modelo específica
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"
} }Ver: https://platform.openai.com/docs/api-reference/models/retrieve
Devuelve una o más terminaciones predichas dadas un aviso. La función acepta como argumentos el "Engine_ID" y el conjunto de parámetros utilizados por las finalizaciones OpenAI API
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"
}
}Ver: https://platform.openai.com/docs/api-reference/completions/create
Esta API se ha desactivado por OpenAI, ya que engines son reemplazados por models . Si lo está utilizando, ¡Considere cambiar a completions(params) lo antes posible!
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"
}
}Ver: https://beta.openai.com/docs/api-reference/completions/create para la lista completa de parámetros que puede pasar a la función de finalización
Crea una finalización para el mensaje 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
}
} }Consulte: https://platform.openai.com/docs/api-reference/chat/create para la lista completa de parámetros que puede pasar a la función de finalización
Crea una finalización para el mensaje de chat, de forma predeterminada se transmite a self() , pero puede anular la configuración pasando una anulación de configuración a la función con un parámetro stream_to http_options diferente.
import Config
config :openai ,
api_key: "your-api-key" ,
http_options: [ recv_timeout: :infinity , async: :once ] ,
... http_options debe establecerse como arriba cuando desee tratar la finalización del chat como una transmisión.
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"
}
...Crea una nueva edición para la entrada, instrucción y parámetros proporcionados
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
}
} }Ver: https://platform.openai.com/docs/api-reference/edits/create
Esto genera una imagen basada en el aviso dado. Las funciones de imagen requieren algunas veces para ejecutar, y la API puede devolver un error de tiempo de espera, si es necesario, puede pasar una estructura de configuración opcional con httpoison http_options como segundo argumento de la función para aumentar el tiempo de espera.
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
}
]
} } Nota: Esta firma de API ha cambiado en v0.3.0 para cumplir con las convenciones de otras API, el alias OpenAI.image_generations(params, request_options) todavía está disponible para la retrocompatibilidad. Si lo está utilizando, considere cambiar a OpenAI.images_generations(params, request_options) lo antes posible.
Nota 2: La forma oficial de aprobar http_options cambió en v0.5.0 para cumplir con las convenciones de otras API, el alias OpenAI.images_generations(file_path, params, request_options) , pero todavía está disponible para la retocompatibilidad. Si lo está utilizando, considere cambiar a OpenAI.images_variations(params, config)
Ver: https://platform.openai.com/docs/api-reference/images/create
Editar una imagen existente basada en las funciones de imagen rápida requiere algunas veces ejecutar, y la API puede devolver un error de tiempo de espera, si es necesario, puede pasar una estructura de configuración opcional con httpoison http_options como segundo argumento de la función para aumentar el tiempo de espera.
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
}
]
} } Nota: La forma oficial de aprobar http_options cambió en v0.5.0 para cumplir con las convenciones de otras API, el alias OpenAI.images_edits(file_path, params, request_options) , pero todavía está disponible para la retrocompatibilidad. Si lo está utilizando, considere cambiar a OpenAI.images_edits(file_path, params, config)
Ver: https://platform.openai.com/docs/api-reference/images/create-edit
Las funciones de imagen requieren algunas veces para ejecutar, y la API puede devolver un error de tiempo de espera, si es necesario, puede pasar una estructura de configuración opcional con httpoison http_options como segundo argumento de la función para aumentar el tiempo de espera.
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
}
]
} } Nota: La forma oficial de aprobar http_options cambió en v0.5.0 para cumplir con las convenciones de otras API, el alias OpenAI.images_variations(file_path, params, request_options) , pero todavía está disponible para la retocompatibilidad. Si lo está utilizando, considere cambiar a OpenAI.images_edits(file_path, params, config)
Ver: 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 }
} }Ver: https://platform.openai.com/docs/api-reference/embeddings/create
Genera audio a partir del texto de entrada.
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 , ... >> }Consulte: https://platform.openai.com/docs/api-reference/audio/create para obtener información sobre los parámetros aceptados por la API
Transcribe audio al lenguaje de entrada.
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.."
} }Consulte: https://platform.openai.com/docs/api-reference/audio/create para obtener información sobre los parámetros aceptados por la API
Traduce el audio al inglés.
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."
}
}Consulte: https://platform.openai.com/docs/api-reference/audio/create para obtener información sobre los parámetros aceptados por la API
Devuelve una lista de archivos que pertenecen a la organización del usuario.
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"
}
}Ver: https://platform.openai.com/docs/api-reference/files
Devuelve un archivo que pertenece a la organización del usuario, dada una ID de archivo
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
}
}Ver: https://platform.openai.com/docs/api-reference/files/retrieve
Cargue un archivo que contenga documentos que se utilizarán en varios puntos finales/características. Actualmente, el tamaño de todos los archivos cargados por una organización puede ser de hasta 1 GB. Póngase en contacto con OpenAI si necesita aumentar el límite de almacenamiento.
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
}
}Ver: https://platform.openai.com/docs/api-reference/files/upload
eliminar un archivo
OpenAI . files_delete ( "file-123" ) { :ok , % { deleted: true , id: "file-123" , object: "file" } }Ver: https://platform.openai.com/docs/api-reference/files/delete
Enumere los trabajos de ajuste de su organización.
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 ,
} ] ,
}
}Ver: https://platform.openai.com/docs/api-reference/fine-tunes/list
Obtiene información sobre un trabajo de ajuste.
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 ,
} ] ,
}
}Vea: https://platform.openai.com/docs/api-reference/fine-unes/retrieve
Crea un trabajo que ajusta un modelo especificado de un conjunto de datos dado.
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: [ ]
} }Ver: https://platform.openai.com/docs/api-reference/fine-tunes/create
Obtenga actualizaciones de estado de grano fino para un trabajo de ajuste fino.
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"
} ,
... ,
]
}
}Ver: https://platform.openai.com/docs/api-reference/fine-tunes/events
Cancelar inmediatamente un trabajo de ajuste.
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: [ ]
} }Cancelar inmediatamente un trabajo de ajuste.
OpenAI . finetunes_delete_model ( "model-id" ) { :ok ,
% {
id: "model-id" ,
object: "model" ,
deleted: true
}
}Ver: https://platform.openai.com/docs/api-reference/fine-tunes/delete-model
Clasifica si el texto viola la política de contenido de 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
}
]
} }Ver: https://platform.openai.com/docs/api-reference/moderations/create
Las siguientes API están actualmente en Beta, para usarlas, asegúrese de establecer el parámetro beta en su configuración.
config :openai ,
# optional, use when required by an OpenAI API beta, e.g.:
beta: "assistants=v1"Recupera la lista de asistentes.
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"
} }Ver: https://platform.openai.com/docs/api-reference/assistants/listassistants
Recupera la lista de asistentes filtrados por parámetros de consulta.
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"
} }Ver: https://platform.openai.com/docs/api-reference/assistants/listassistants
Recupera un asistente por su identificación.
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" } ]
} }Ver: https://platform.openai.com/docs/api-reference/assistants/getassistant
Crea un nuevo asistente.
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" } ]
} }Ver: https://platform.openai.com/docs/api-reference/assistants/createassistant
Modifica un asistente existente.
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" } ]
} }Ver: https://platform.openai.com/docs/api-reference/assistants/modifyassistant
Elimina un asistente.
OpenAI . assistants_delete ( "asst_..." ) { :ok ,
% {
deleted: true ,
id: "asst_..." ,
object: "assistant.deleted"
} }Ver: https://platform.openai.com/docs/api-reference/assistants/deleteassistant
Recupera la lista de archivos asociados con un asistente en particular.
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"
} }Ver: https://platform.openai.com/docs/api-reference/assistants/listassistantfiles
Recupera la lista de archivos asociados con un asistente en particular, filtrado por parámetros de consulta.
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"
} }Ver: https://platform.openai.com/docs/api-reference/assistants/listassistantfiles
Recupera un archivo de asistente por su identificación
OpenAI . assistant_file ( "asst_..." , "file_..." ) { :ok ,
% {
assistant_id: "asst_..." ,
created_at: 1699472933 ,
id: "file-..." ,
object: "assistant.file"
} }Ver: https://platform.openai.com/docs/api-reference/assistants/getassistantfile
Adjunta un archivo anteriormente cargado al asistente.
OpenAI . assistant_file_create ( "asst_..." , file_id: "file-..." ) { :ok ,
% {
assistant_id: "asst_..." ,
created_at: 1699472933 ,
id: "file-..." ,
object: "assistant.file"
} }Ver: https://platform.openai.com/docs/api-reference/assistants/createassistantfile
Se separa un archivo del asistente. El archivo en sí no se elimina automáticamente.
OpenAI . assistant_file_delete ( "asst_..." , "file-..." ) { :ok ,
% {
deleted: true ,
id: "file-..." ,
object: "assistant.file.deleted"
} }Ver: https://platform.openai.com/docs/api-reference/assistants/DeleteassistantFile
Recupera la lista de hilos. Nota: En el momento de este escrito, esta funcionalidad permanece indocumentada por 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"
} }Recupera la lista de hilos por parámetros de consulta. Nota: En el momento de este escrito, esta funcionalidad permanece indocumentada por 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"
} }Crea un nuevo hilo con algunos mensajes y metadatos.
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"
} }Ver: https://platform.openai.com/docs/api-reference/threads/createethread
Crea un nuevo hilo y lo ejecuta.
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" } ]
} }Ver: https://platform.openai.com/docs/api-reference/runs/createethreadandrun
Modifica un hilo existente.
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"
} }Ver: https://platform.openai.com/docs/api-reference/threads/modifythread
Modifica un hilo existente.
OpenAI . threads_delete ( "thread_..." ) { :ok ,
% {
deleted: true ,
id: "thread_..." ,
object: "thread.deleted"
} }Ver: https://platform.openai.com/docs/api-reference/threads/deletethread
Recupera la lista de mensajes asociados con un hilo en particular.
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"
} }Ver: https://platform.openai.com/docs/api-reference/messages/listmessages
Recupera la lista de mensajes asociados con un hilo particular, filtrado por parámetros de consulta.
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"
} }Ver: https://platform.openai.com/docs/api-reference/messages/listmessages
Recupera un mensaje de hilo por su ID.
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_..."
} }Ver: https://platform.openai.com/docs/api-reference/messages/getmessage
Crea un mensaje dentro de un hilo.
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_..."
} }Ver: https://platform.openai.com/docs/api-reference/messages/createMessage
Crea un mensaje dentro de un hilo.
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_..."
} }Ver: https://platform.openai.com/docs/api-reference/messages/modifymessage
Recupera la lista de archivos asociados con un mensaje particular de un hilo.
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"
} }Ver: https://platform.openai.com/docs/api-reference/messages/listmessagefiles
Recupera la lista de archivos asociados con un mensaje particular de un hilo, filtrado por parámetros de consulta.
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"
} }Ver: https://platform.openai.com/docs/api-reference/messages/listmessagefiles
Recupera el objeto del archivo del mensaje.
OpenAI . thread_message_file ( "thread_..." , "msg_..." , "file-..." ) { :ok ,
% {
created_at: 1699706818 ,
id: "file-..." ,
message_id: "msg_..." ,
object: "thread.message.file"
} }Ver: https://platform.openai.com/docs/api-reference/messages/getmessagefile
Recupera la lista de ejecuciones asociadas con un hilo particular, filtrado por parámetros de consulta.
OpenAI . thread_runs ( "thread_..." , limit: 10 ) { :ok , % {
data: [ ] ,
first_id: nil ,
has_more: false ,
last_id: nil ,
object: "list"
} }Ver: https://platform.openai.com/docs/api-reference/runs/listruns
Recupera un hilo particular ejecutado por su ID.
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" } ]
} }Ver: https://platform.openai.com/docs/api-reference/runs/getrun
Crea una ejecución para un hilo usando un asistente en particular.
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" } ]
} }Ver: https://platform.openai.com/docs/api-reference/runs/createrun
Modifica una ejecución de hilo existente.
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" } ]
} }Ver: https://platform.openai.com/docs/api-reference/runs/modifyrun
Cuando una ejecución tiene el estado: "requires_action" y required_action.type es submit_tool_outputs , este punto final se puede usar para enviar las salidas de las llamadas de la herramienta una vez que están todos completados. Todas las salidas deben enviarse en una sola solicitud.
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"
}
]
}
}Consulte: https://platform.openai.com/docs/api-reference/runs/subMitTooLoutputs
Cancela una ejecución 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" } ]
} }Ver: https://platform.openai.com/docs/api-reference/runs/cancelrun
Recupera la lista de pasos asociados con una ejecución particular de un hilo.
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"
} }Ver: https://platform.openai.com/docs/api-reference/runs/listrunsteps
Recupera la lista de pasos asociados con una ejecución particular de un hilo, filtrado por parámetros de consulta.
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"
} }Ver: https://platform.openai.com/docs/api-reference/runs/listrunsteps
Recupera la lista de pasos asociados con una ejecución particular de un hilo, filtrado por parámetros de consulta.
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"
} }Ver: https://platform.openai.com/docs/api-reference/runs/listrunsteps
Recupera un paso de hilo por su identificación.
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"
} }Ver: https://platform.openai.com/docs/api-reference/runs/getrunstep
Las siguientes API están en desuso, pero actualmente compatibles con la biblioteca para retrocompatibilidad con versiones anteriores. ¡Si está utilizando las siguientes API, considere eliminarlo lo antes posible de su proyecto!
Nota: De la versión 0.5.0 Búsqueda, respuestas, clasificaciones La API no es compatible (ya que OpenAI ha eliminado las ha eliminado, si aún necesita que usen V0.4.2
Obtenga la lista de motores disponibles
OpenAI . engines ( ) { :ok , % {
"data" => [
% { "id" => "davinci" , "object" => "engine" , "max_replicas": ... } ,
... ,
...
]
}
Ver: https://beta.openai.com/docs/api-reference/engines/list
Recuperar información específica del motor
OpenAI . engines ( "davinci" ) { :ok , % {
"id" => "davinci" ,
"object" => "engine" ,
"max_replicas": ...
}
}Ver: https://beta.openai.com/docs/api-reference/engines/retrieve
El paquete está disponible como código abierto bajo los términos de la licencia MIT.
