openapi_openai 1.0.0 → 1.1.0

data/docs/CreateAssistantRequest.md

@@ -0,0 +1,30 @@
+# OpenApiOpenAIClient::CreateAssistantRequest
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **model** | [**CreateAssistantRequestModel**](CreateAssistantRequestModel.md) |  |  |
+| **name** | **String** | The name of the assistant. The maximum length is 256 characters.  | [optional] |
+| **description** | **String** | The description of the assistant. The maximum length is 512 characters.  | [optional] |
+| **instructions** | **String** | The system instructions that the assistant uses. The maximum length is 256,000 characters.  | [optional] |
+| **tools** | [**Array<AssistantObjectToolsInner>**](AssistantObjectToolsInner.md) | A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types `code_interpreter`, `retrieval`, or `function`.  | [optional] |
+| **file_ids** | **Array<String>** | A list of [file](/docs/api-reference/files) IDs attached to this assistant. There can be a maximum of 20 files attached to the assistant. Files are ordered by their creation date in ascending order.  | [optional] |
+| **metadata** | **Object** | Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.  | [optional] |
+
+## Example
+
+```ruby
+require 'openapi_openai'
+
+instance = OpenApiOpenAIClient::CreateAssistantRequest.new(
+  model: null,
+  name: null,
+  description: null,
+  instructions: null,
+  tools: null,
+  file_ids: null,
+  metadata: null
+)
+```
+

data/docs/CreateAssistantRequestModel.md

@@ -0,0 +1,15 @@
+# OpenApiOpenAIClient::CreateAssistantRequestModel
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+
+## Example
+
+```ruby
+require 'openapi_openai'
+
+instance = OpenApiOpenAIClient::CreateAssistantRequestModel.new()
+```
+

data/docs/CreateChatCompletionFunctionResponse.md

@@ -0,0 +1,30 @@
+# OpenApiOpenAIClient::CreateChatCompletionFunctionResponse
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **id** | **String** | A unique identifier for the chat completion. |  |
+| **choices** | [**Array<CreateChatCompletionFunctionResponseChoicesInner>**](CreateChatCompletionFunctionResponseChoicesInner.md) | A list of chat completion choices. Can be more than one if `n` is greater than 1. |  |
+| **created** | **Integer** | The Unix timestamp (in seconds) of when the chat completion was created. |  |
+| **model** | **String** | The model used for the chat completion. |  |
+| **system_fingerprint** | **String** | This fingerprint represents the backend configuration that the model runs with.  Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism.  | [optional] |
+| **object** | **String** | The object type, which is always `chat.completion`. |  |
+| **usage** | [**CompletionUsage**](CompletionUsage.md) |  | [optional] |
+
+## Example
+
+```ruby
+require 'openapi_openai'
+
+instance = OpenApiOpenAIClient::CreateChatCompletionFunctionResponse.new(
+  id: null,
+  choices: null,
+  created: null,
+  model: null,
+  system_fingerprint: null,
+  object: null,
+  usage: null
+)
+```
+

data/docs/CreateChatCompletionFunctionResponseChoicesInner.md

@@ -0,0 +1,22 @@
+# OpenApiOpenAIClient::CreateChatCompletionFunctionResponseChoicesInner
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **finish_reason** | **String** | The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, or `function_call` if the model called a function.  |  |
+| **index** | **Integer** | The index of the choice in the list of choices. |  |
+| **message** | [**ChatCompletionResponseMessage**](ChatCompletionResponseMessage.md) |  |  |
+
+## Example
+
+```ruby
+require 'openapi_openai'
+
+instance = OpenApiOpenAIClient::CreateChatCompletionFunctionResponseChoicesInner.new(
+  finish_reason: null,
+  index: null,
+  message: null
+)
+```
+

data/docs/CreateChatCompletionRequest.md

@@ -4,20 +4,26 @@
 
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
+| **messages** | [**Array<ChatCompletionRequestMessage>**](ChatCompletionRequestMessage.md) | A list of messages comprising the conversation so far. [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models). |  |
 | **model** | [**CreateChatCompletionRequestModel**](CreateChatCompletionRequestModel.md) |  |  |
-| **messages** | [**Array<ChatCompletionRequestMessage>**](ChatCompletionRequestMessage.md) | A list of messages comprising the conversation so far. [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb). |  |
-| **functions** | [**Array<ChatCompletionFunctions>**](ChatCompletionFunctions.md) | A list of functions the model may generate JSON inputs for. | [optional] |
-| **function_call** | [**CreateChatCompletionRequestFunctionCall**](CreateChatCompletionRequestFunctionCall.md) |  | [optional] |
+| **frequency_penalty** | **Float** | 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.  [See more information about frequency and presence penalties.](/docs/guides/text-generation/parameter-details)  | [optional][default to 0] |
+| **logit_bias** | **Hash<String, Integer>** | Modify the likelihood of specified tokens appearing in the completion.  Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. 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.  | [optional] |
+| **logprobs** | **Boolean** | Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`. | [optional][default to false] |
+| **top_logprobs** | **Integer** | An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used. | [optional] |
+| **max_tokens** | **Integer** | The maximum number of [tokens](/tokenizer) that can be generated in the chat completion.  The total length of input tokens and generated tokens is limited by the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens.  | [optional] |
+| **n** | **Integer** | How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs. | [optional][default to 1] |
+| **presence_penalty** | **Float** | Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.  [See more information about frequency and presence penalties.](/docs/guides/text-generation/parameter-details)  | [optional][default to 0] |
+| **response_format** | [**CreateChatCompletionRequestResponseFormat**](CreateChatCompletionRequestResponseFormat.md) |  | [optional] |
+| **seed** | **Integer** | This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.  | [optional] |
+| **stop** | [**CreateChatCompletionRequestStop**](CreateChatCompletionRequestStop.md) |  | [optional] |
+| **stream** | **Boolean** | If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).  | [optional][default to false] |
 | **temperature** | **Float** | What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.  We generally recommend altering this or `top_p` but not both.  | [optional][default to 1] |
 | **top_p** | **Float** | 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.  We generally recommend altering this or `temperature` but not both.  | [optional][default to 1] |
-| **n** | **Integer** | How many chat completion choices to generate for each input message. | [optional][default to 1] |
-| **stream** | **Boolean** | If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_stream_completions.ipynb).  | [optional][default to false] |
-| **stop** | [**CreateChatCompletionRequestStop**](CreateChatCompletionRequestStop.md) |  | [optional] |
-| **max_tokens** | **Integer** | The maximum number of [tokens](/tokenizer) to generate in the chat completion.  The total length of input tokens and generated tokens is limited by the model's context length. [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb) for counting tokens.  | [optional] |
-| **presence_penalty** | **Float** | Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.  [See more information about frequency and presence penalties.](/docs/api-reference/parameter-details)  | [optional][default to 0] |
-| **frequency_penalty** | **Float** | 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.  [See more information about frequency and presence penalties.](/docs/api-reference/parameter-details)  | [optional][default to 0] |
-| **logit_bias** | **Object** | Modify the likelihood of specified tokens appearing in the completion.  Accepts a json object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. 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.  | [optional] |
+| **tools** | [**Array<ChatCompletionTool>**](ChatCompletionTool.md) | A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.  | [optional] |
+| **tool_choice** | [**ChatCompletionToolChoiceOption**](ChatCompletionToolChoiceOption.md) |  | [optional] |
 | **user** | **String** | A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).  | [optional] |
+| **function_call** | [**CreateChatCompletionRequestFunctionCall**](CreateChatCompletionRequestFunctionCall.md) |  | [optional] |
+| **functions** | [**Array<ChatCompletionFunctions>**](ChatCompletionFunctions.md) | Deprecated in favor of `tools`.  A list of functions the model may generate JSON inputs for.  | [optional] |
 
 ## Example
 
@@ -25,20 +31,26 @@
 require 'openapi_openai'
 
 instance = OpenApiOpenAIClient::CreateChatCompletionRequest.new(
-  model: null,
   messages: null,
-  functions: null,
-  function_call: null,
-  temperature: 1,
-  top_p: 1,
-  n: 1,
-  stream: null,
-  stop: null,
-  max_tokens: null,
-  presence_penalty: null,
+  model: null,
   frequency_penalty: null,
   logit_bias: null,
-  user: user-1234
+  logprobs: null,
+  top_logprobs: null,
+  max_tokens: null,
+  n: 1,
+  presence_penalty: null,
+  response_format: null,
+  seed: null,
+  stop: null,
+  stream: null,
+  temperature: 1,
+  top_p: 1,
+  tools: null,
+  tool_choice: null,
+  user: user-1234,
+  function_call: null,
+  functions: null
 )
 ```
 

data/docs/CreateChatCompletionRequestFunctionCall.md

@@ -14,7 +14,7 @@ require 'openapi_openai'
 OpenApiOpenAIClient::CreateChatCompletionRequestFunctionCall.openapi_one_of
 # =>
 # [
-#   :'CreateChatCompletionRequestFunctionCallOneOf',
+#   :'ChatCompletionFunctionCallOption',
 #   :'String'
 # ]
 ```
@@ -29,7 +29,7 @@ Find the appropriate object from the `openapi_one_of` list and casts the data in
 require 'openapi_openai'
 
 OpenApiOpenAIClient::CreateChatCompletionRequestFunctionCall.build(data)
-# => #<CreateChatCompletionRequestFunctionCallOneOf:0x00007fdd4aab02a0>
+# => #<ChatCompletionFunctionCallOption:0x00007fdd4aab02a0>
 
 OpenApiOpenAIClient::CreateChatCompletionRequestFunctionCall.build(data_that_doesnt_match)
 # => nil
@@ -43,7 +43,7 @@ OpenApiOpenAIClient::CreateChatCompletionRequestFunctionCall.build(data_that_doe
 
 #### Return type
 
-- `CreateChatCompletionRequestFunctionCallOneOf`
+- `ChatCompletionFunctionCallOption`
 - `String`
 - `nil` (if no type matches)
 

data/docs/CreateChatCompletionRequestModel.md

@@ -1,47 +1,15 @@
 # OpenApiOpenAIClient::CreateChatCompletionRequestModel
 
-## Class instance methods
+## Properties
 
-### `openapi_one_of`
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
 
-Returns the list of classes defined in oneOf.
-
-#### Example
-
-```ruby
-require 'openapi_openai'
-
-OpenApiOpenAIClient::CreateChatCompletionRequestModel.openapi_one_of
-# =>
-# [
-#   :'String'
-# ]
-```
-
-### build
-
-Find the appropriate object from the `openapi_one_of` list and casts the data into it.
-
-#### Example
+## Example
 
 ```ruby
 require 'openapi_openai'
 
-OpenApiOpenAIClient::CreateChatCompletionRequestModel.build(data)
-# => #<String:0x00007fdd4aab02a0>
-
-OpenApiOpenAIClient::CreateChatCompletionRequestModel.build(data_that_doesnt_match)
-# => nil
+instance = OpenApiOpenAIClient::CreateChatCompletionRequestModel.new()
 ```
 
-#### Parameters
-
-| Name | Type | Description |
-| ---- | ---- | ----------- |
-| **data** | **Mixed** | data to be matched against the list of oneOf items |
-
-#### Return type
-
-- `String`
-- `nil` (if no type matches)
-

data/docs/CreateChatCompletionRequestResponseFormat.md

@@ -0,0 +1,18 @@
+# OpenApiOpenAIClient::CreateChatCompletionRequestResponseFormat
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **type** | **String** | Must be one of `text` or `json_object`. | [optional][default to 'text'] |
+
+## Example
+
+```ruby
+require 'openapi_openai'
+
+instance = OpenApiOpenAIClient::CreateChatCompletionRequestResponseFormat.new(
+  type: json_object
+)
+```
+

data/docs/CreateChatCompletionResponse.md

@@ -4,12 +4,13 @@
 
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
-| **id** | **String** |  |  |
-| **object** | **String** |  |  |
-| **created** | **Integer** |  |  |
-| **model** | **String** |  |  |
-| **choices** | [**Array<CreateChatCompletionResponseChoicesInner>**](CreateChatCompletionResponseChoicesInner.md) |  |  |
-| **usage** | [**CreateCompletionResponseUsage**](CreateCompletionResponseUsage.md) |  | [optional] |
+| **id** | **String** | A unique identifier for the chat completion. |  |
+| **choices** | [**Array<CreateChatCompletionResponseChoicesInner>**](CreateChatCompletionResponseChoicesInner.md) | A list of chat completion choices. Can be more than one if `n` is greater than 1. |  |
+| **created** | **Integer** | The Unix timestamp (in seconds) of when the chat completion was created. |  |
+| **model** | **String** | The model used for the chat completion. |  |
+| **system_fingerprint** | **String** | This fingerprint represents the backend configuration that the model runs with.  Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism.  | [optional] |
+| **object** | **String** | The object type, which is always `chat.completion`. |  |
+| **usage** | [**CompletionUsage**](CompletionUsage.md) |  | [optional] |
 
 ## Example
 
@@ -18,10 +19,11 @@ require 'openapi_openai'
 
 instance = OpenApiOpenAIClient::CreateChatCompletionResponse.new(
   id: null,
-  object: null,
+  choices: null,
   created: null,
   model: null,
-  choices: null,
+  system_fingerprint: null,
+  object: null,
   usage: null
 )
 ```

data/docs/CreateChatCompletionResponseChoicesInner.md

@@ -4,9 +4,10 @@
 
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
-| **index** | **Integer** |  | [optional] |
-| **message** | [**ChatCompletionResponseMessage**](ChatCompletionResponseMessage.md) |  | [optional] |
-| **finish_reason** | **String** |  | [optional] |
+| **finish_reason** | **String** | The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function.  |  |
+| **index** | **Integer** | The index of the choice in the list of choices. |  |
+| **message** | [**ChatCompletionResponseMessage**](ChatCompletionResponseMessage.md) |  |  |
+| **logprobs** | [**CreateChatCompletionResponseChoicesInnerLogprobs**](CreateChatCompletionResponseChoicesInnerLogprobs.md) |  |  |
 
 ## Example
 
@@ -14,9 +15,10 @@
 require 'openapi_openai'
 
 instance = OpenApiOpenAIClient::CreateChatCompletionResponseChoicesInner.new(
+  finish_reason: null,
   index: null,
   message: null,
-  finish_reason: null
+  logprobs: null
 )
 ```
 

data/docs/CreateChatCompletionResponseChoicesInnerLogprobs.md

@@ -0,0 +1,18 @@
+# OpenApiOpenAIClient::CreateChatCompletionResponseChoicesInnerLogprobs
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **content** | [**Array<ChatCompletionTokenLogprob>**](ChatCompletionTokenLogprob.md) | A list of message content tokens with log probability information. |  |
+
+## Example
+
+```ruby
+require 'openapi_openai'
+
+instance = OpenApiOpenAIClient::CreateChatCompletionResponseChoicesInnerLogprobs.new(
+  content: null
+)
+```
+

data/docs/CreateChatCompletionStreamResponse.md

@@ -4,11 +4,12 @@
 
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
-| **id** | **String** |  |  |
-| **object** | **String** |  |  |
-| **created** | **Integer** |  |  |
-| **model** | **String** |  |  |
-| **choices** | [**Array<CreateChatCompletionStreamResponseChoicesInner>**](CreateChatCompletionStreamResponseChoicesInner.md) |  |  |
+| **id** | **String** | A unique identifier for the chat completion. Each chunk has the same ID. |  |
+| **choices** | [**Array<CreateChatCompletionStreamResponseChoicesInner>**](CreateChatCompletionStreamResponseChoicesInner.md) | A list of chat completion choices. Can be more than one if `n` is greater than 1. |  |
+| **created** | **Integer** | The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp. |  |
+| **model** | **String** | The model to generate the completion. |  |
+| **system_fingerprint** | **String** | This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism.  | [optional] |
+| **object** | **String** | The object type, which is always `chat.completion.chunk`. |  |
 
 ## Example
 
@@ -17,10 +18,11 @@ require 'openapi_openai'
 
 instance = OpenApiOpenAIClient::CreateChatCompletionStreamResponse.new(
   id: null,
-  object: null,
+  choices: null,
   created: null,
   model: null,
-  choices: null
+  system_fingerprint: null,
+  object: null
 )
 ```
 

data/docs/CreateChatCompletionStreamResponseChoicesInner.md

@@ -4,9 +4,10 @@
 
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
-| **index** | **Integer** |  | [optional] |
-| **delta** | [**ChatCompletionStreamResponseDelta**](ChatCompletionStreamResponseDelta.md) |  | [optional] |
-| **finish_reason** | **String** |  | [optional] |
+| **delta** | [**ChatCompletionStreamResponseDelta**](ChatCompletionStreamResponseDelta.md) |  |  |
+| **logprobs** | [**CreateChatCompletionResponseChoicesInnerLogprobs**](CreateChatCompletionResponseChoicesInnerLogprobs.md) |  | [optional] |
+| **finish_reason** | **String** | The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function.  |  |
+| **index** | **Integer** | The index of the choice in the list of choices. |  |
 
 ## Example
 
@@ -14,9 +15,10 @@
 require 'openapi_openai'
 
 instance = OpenApiOpenAIClient::CreateChatCompletionStreamResponseChoicesInner.new(
-  index: null,
   delta: null,
-  finish_reason: null
+  logprobs: null,
+  finish_reason: null,
+  index: null
 )
 ```
 

data/docs/CreateCompletionRequest.md

@@ -6,19 +6,20 @@
 | ---- | ---- | ----------- | ----- |
 | **model** | [**CreateCompletionRequestModel**](CreateCompletionRequestModel.md) |  |  |
 | **prompt** | [**CreateCompletionRequestPrompt**](CreateCompletionRequestPrompt.md) |  |  |
-| **suffix** | **String** | The suffix that comes after a completion of inserted text. | [optional] |
-| **max_tokens** | **Integer** | The maximum number of [tokens](/tokenizer) to generate in the completion.  The token count of your prompt plus `max_tokens` cannot exceed the model's context length. [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb) for counting tokens.  | [optional][default to 16] |
-| **temperature** | **Float** | What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.  We generally recommend altering this or `top_p` but not both.  | [optional][default to 1] |
-| **top_p** | **Float** | 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.  We generally recommend altering this or `temperature` but not both.  | [optional][default to 1] |
-| **n** | **Integer** | How many completions to generate for each prompt.  **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`.  | [optional][default to 1] |
-| **stream** | **Boolean** | Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_stream_completions.ipynb).  | [optional][default to false] |
-| **logprobs** | **Integer** | Include the log probabilities on the `logprobs` most likely tokens, as well the chosen tokens. For example, if `logprobs` is 5, the API will return a list of the 5 most likely tokens. The API will always return the `logprob` of the sampled token, so there may be up to `logprobs+1` elements in the response.  The maximum value for `logprobs` is 5.  | [optional] |
+| **best_of** | **Integer** | 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`.  | [optional][default to 1] |
 | **echo** | **Boolean** | Echo back the prompt in addition to the completion  | [optional][default to false] |
+| **frequency_penalty** | **Float** | 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.  [See more information about frequency and presence penalties.](/docs/guides/text-generation/parameter-details)  | [optional][default to 0] |
+| **logit_bias** | **Hash<String, Integer>** | 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](/tokenizer?view=bpe) 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 `{\"50256\": -100}` to prevent the <|endoftext|> token from being generated.  | [optional] |
+| **logprobs** | **Integer** | Include the log probabilities on the `logprobs` most likely output tokens, as well the chosen tokens. For example, if `logprobs` is 5, the API will return a list of the 5 most likely tokens. The API will always return the `logprob` of the sampled token, so there may be up to `logprobs+1` elements in the response.  The maximum value for `logprobs` is 5.  | [optional] |
+| **max_tokens** | **Integer** | The maximum number of [tokens](/tokenizer) that can be generated in the completion.  The token count of your prompt plus `max_tokens` cannot exceed the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens.  | [optional][default to 16] |
+| **n** | **Integer** | How many completions to generate for each prompt.  **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`.  | [optional][default to 1] |
+| **presence_penalty** | **Float** | Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.  [See more information about frequency and presence penalties.](/docs/guides/text-generation/parameter-details)  | [optional][default to 0] |
+| **seed** | **Integer** | If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result.  Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.  | [optional] |
 | **stop** | [**CreateCompletionRequestStop**](CreateCompletionRequestStop.md) |  | [optional] |
-| **presence_penalty** | **Float** | Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.  [See more information about frequency and presence penalties.](/docs/api-reference/parameter-details)  | [optional][default to 0] |
-| **frequency_penalty** | **Float** | 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.  [See more information about frequency and presence penalties.](/docs/api-reference/parameter-details)  | [optional][default to 0] |
-| **best_of** | **Integer** | 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`.  | [optional][default to 1] |
-| **logit_bias** | **Object** | 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](/tokenizer?view=bpe) (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 `{\"50256\": -100}` to prevent the <|endoftext|> token from being generated.  | [optional] |
+| **stream** | **Boolean** | Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).  | [optional][default to false] |
+| **suffix** | **String** | The suffix that comes after a completion of inserted text.  This parameter is only supported for `gpt-3.5-turbo-instruct`.  | [optional] |
+| **temperature** | **Float** | What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.  We generally recommend altering this or `top_p` but not both.  | [optional][default to 1] |
+| **top_p** | **Float** | 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.  We generally recommend altering this or `temperature` but not both.  | [optional][default to 1] |
 | **user** | **String** | A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).  | [optional] |
 
 ## Example
@@ -29,19 +30,20 @@ require 'openapi_openai'
 instance = OpenApiOpenAIClient::CreateCompletionRequest.new(
   model: null,
   prompt: null,
-  suffix: test.,
-  max_tokens: 16,
-  temperature: 1,
-  top_p: 1,
-  n: 1,
-  stream: null,
-  logprobs: null,
+  best_of: null,
   echo: null,
-  stop: null,
-  presence_penalty: null,
   frequency_penalty: null,
-  best_of: null,
   logit_bias: null,
+  logprobs: null,
+  max_tokens: 16,
+  n: 1,
+  presence_penalty: null,
+  seed: null,
+  stop: null,
+  stream: null,
+  suffix: test.,
+  temperature: 1,
+  top_p: 1,
   user: user-1234
 )
 ```

data/docs/CreateCompletionRequestModel.md

@@ -1,47 +1,15 @@
 # OpenApiOpenAIClient::CreateCompletionRequestModel
 
-## Class instance methods
+## Properties
 
-### `openapi_one_of`
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
 
-Returns the list of classes defined in oneOf.
-
-#### Example
-
-```ruby
-require 'openapi_openai'
-
-OpenApiOpenAIClient::CreateCompletionRequestModel.openapi_one_of
-# =>
-# [
-#   :'String'
-# ]
-```
-
-### build
-
-Find the appropriate object from the `openapi_one_of` list and casts the data into it.
-
-#### Example
+## Example
 
 ```ruby
 require 'openapi_openai'
 
-OpenApiOpenAIClient::CreateCompletionRequestModel.build(data)
-# => #<String:0x00007fdd4aab02a0>
-
-OpenApiOpenAIClient::CreateCompletionRequestModel.build(data_that_doesnt_match)
-# => nil
+instance = OpenApiOpenAIClient::CreateCompletionRequestModel.new()
 ```
 
-#### Parameters
-
-| Name | Type | Description |
-| ---- | ---- | ----------- |
-| **data** | **Mixed** | data to be matched against the list of oneOf items |
-
-#### Return type
-
-- `String`
-- `nil` (if no type matches)
-

data/docs/CreateCompletionResponse.md

@@ -4,12 +4,13 @@
 
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
-| **id** | **String** |  |  |
-| **object** | **String** |  |  |
-| **created** | **Integer** |  |  |
-| **model** | **String** |  |  |
-| **choices** | [**Array<CreateCompletionResponseChoicesInner>**](CreateCompletionResponseChoicesInner.md) |  |  |
-| **usage** | [**CreateCompletionResponseUsage**](CreateCompletionResponseUsage.md) |  | [optional] |
+| **id** | **String** | A unique identifier for the completion. |  |
+| **choices** | [**Array<CreateCompletionResponseChoicesInner>**](CreateCompletionResponseChoicesInner.md) | The list of completion choices the model generated for the input prompt. |  |
+| **created** | **Integer** | The Unix timestamp (in seconds) of when the completion was created. |  |
+| **model** | **String** | The model used for completion. |  |
+| **system_fingerprint** | **String** | This fingerprint represents the backend configuration that the model runs with.  Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism.  | [optional] |
+| **object** | **String** | The object type, which is always \"text_completion\" |  |
+| **usage** | [**CompletionUsage**](CompletionUsage.md) |  | [optional] |
 
 ## Example
 
@@ -18,10 +19,11 @@ require 'openapi_openai'
 
 instance = OpenApiOpenAIClient::CreateCompletionResponse.new(
   id: null,
-  object: null,
+  choices: null,
   created: null,
   model: null,
-  choices: null,
+  system_fingerprint: null,
+  object: null,
   usage: null
 )
 ```

data/docs/CreateCompletionResponseChoicesInner.md

@@ -4,10 +4,10 @@
 
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
-| **text** | **String** |  |  |
+| **finish_reason** | **String** | The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, or `content_filter` if content was omitted due to a flag from our content filters.  |  |
 | **index** | **Integer** |  |  |
 | **logprobs** | [**CreateCompletionResponseChoicesInnerLogprobs**](CreateCompletionResponseChoicesInnerLogprobs.md) |  |  |
-| **finish_reason** | **String** |  |  |
+| **text** | **String** |  |  |
 
 ## Example
 
@@ -15,10 +15,10 @@
 require 'openapi_openai'
 
 instance = OpenApiOpenAIClient::CreateCompletionResponseChoicesInner.new(
-  text: null,
+  finish_reason: null,
   index: null,
   logprobs: null,
-  finish_reason: null
+  text: null
 )
 ```