api

type ApiMeta struct {
	ApiVersion  *ApiMetaApiVersion  `json:"api_version,omitempty" url:"api_version,omitempty"`
	BilledUnits *ApiMetaBilledUnits `json:"billed_units,omitempty" url:"billed_units,omitempty"`
	Tokens      *ApiMetaTokens      `json:"tokens,omitempty" url:"tokens,omitempty"`
	Warnings    []string            `json:"warnings,omitempty" url:"warnings,omitempty"`
	// contains filtered or unexported fields
}

type ApiMetaApiVersion struct {
	Version        string `json:"version" url:"version"`
	IsDeprecated   *bool  `json:"is_deprecated,omitempty" url:"is_deprecated,omitempty"`
	IsExperimental *bool  `json:"is_experimental,omitempty" url:"is_experimental,omitempty"`
	// contains filtered or unexported fields
}

type ApiMetaBilledUnits struct {
	// The number of billed input tokens.
	InputTokens *float64 `json:"input_tokens,omitempty" url:"input_tokens,omitempty"`
	// The number of billed output tokens.
	OutputTokens *float64 `json:"output_tokens,omitempty" url:"output_tokens,omitempty"`
	// The number of billed search units.
	SearchUnits *float64 `json:"search_units,omitempty" url:"search_units,omitempty"`
	// The number of billed classifications units.
	Classifications *float64 `json:"classifications,omitempty" url:"classifications,omitempty"`
	// contains filtered or unexported fields
}

type ApiMetaTokens struct {
	// The number of tokens used as input to the model.
	InputTokens *float64 `json:"input_tokens,omitempty" url:"input_tokens,omitempty"`
	// The number of tokens produced by the model.
	OutputTokens *float64 `json:"output_tokens,omitempty" url:"output_tokens,omitempty"`
	// contains filtered or unexported fields
}

type AuthTokenType string

type BadRequestError struct {
	*core.APIError
	Body interface{}
}

type ChatCitation struct {
	// The index of text that the citation starts at, counting from zero. For example, a generation of `Hello, world!` with a citation on `world` would have a start value of `7`. This is because the citation starts at `w`, which is the seventh character.
	Start int `json:"start" url:"start"`
	// The index of text that the citation ends after, counting from zero. For example, a generation of `Hello, world!` with a citation on `world` would have an end value of `11`. This is because the citation ends after `d`, which is the eleventh character.
	End int `json:"end" url:"end"`
	// The text of the citation. For example, a generation of `Hello, world!` with a citation of `world` would have a text value of `world`.
	Text string `json:"text" url:"text"`
	// Identifiers of documents cited by this section of the generated reply.
	DocumentIds []string `json:"document_ids,omitempty" url:"document_ids,omitempty"`
	// contains filtered or unexported fields
}

type ChatCitationGenerationEvent struct {
	// Citations for the generated reply.
	Citations []*ChatCitation `json:"citations,omitempty" url:"citations,omitempty"`
	// contains filtered or unexported fields
}

type ChatConnector struct {
	// The identifier of the connector.
	Id string `json:"id" url:"id"`
	// When specified, this user access token will be passed to the connector in the Authorization header instead of the Cohere generated one.
	UserAccessToken *string `json:"user_access_token,omitempty" url:"user_access_token,omitempty"`
	// Defaults to `false`.
	//
	// When `true`, the request will continue if this connector returned an error.
	ContinueOnFailure *bool `json:"continue_on_failure,omitempty" url:"continue_on_failure,omitempty"`
	// Provides the connector with different settings at request time. The key/value pairs of this object are specific to each connector.
	//
	// For example, the connector `web-search` supports the `site` option, which limits search results to the specified domain.
	Options map[string]interface{} `json:"options,omitempty" url:"options,omitempty"`
	// contains filtered or unexported fields
}

type ChatDataMetrics struct {
	// The sum of all turns of valid train examples.
	NumTrainTurns *string `json:"num_train_turns,omitempty" url:"num_train_turns,omitempty"`
	// The sum of all turns of valid eval examples.
	NumEvalTurns *string `json:"num_eval_turns,omitempty" url:"num_eval_turns,omitempty"`
	// The preamble of this dataset.
	Preamble *string `json:"preamble,omitempty" url:"preamble,omitempty"`
	// contains filtered or unexported fields
}

type ChatDocument = map[string]string

type ChatMessage struct {
	// One of `CHATBOT`, `SYSTEM`, or `USER` to identify who the message is coming from.
	Role ChatMessageRole `json:"role" url:"role"`
	// Contents of the chat message.
	Message string `json:"message" url:"message"`
	// contains filtered or unexported fields
}

type ChatMessageRole string

type ChatRequest struct {
	// Text input for the model to respond to.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	Message string `json:"message" url:"message"`
	// Defaults to `command-r-plus`.
	//
	// The name of a compatible [Cohere model](https://docs.cohere.com/docs/models) or the ID of a [fine-tuned](https://docs.cohere.com/docs/chat-fine-tuning) model.
	// Compatible Deployments: Cohere Platform, Private Deployments
	Model *string `json:"model,omitempty" url:"model,omitempty"`
	// When specified, the default Cohere preamble will be replaced with the provided one. Preambles are a part of the prompt used to adjust the model's overall behavior and conversation style, and use the `SYSTEM` role.
	//
	// The `SYSTEM` role is also used for the contents of the optional `chat_history=` parameter. When used with the `chat_history=` parameter it adds content throughout a conversation. Conversely, when used with the `preamble=` parameter it adds content at the start of the conversation only.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	Preamble *string `json:"preamble,omitempty" url:"preamble,omitempty"`
	// A list of previous messages between the user and the model, giving the model conversational context for responding to the user's `message`.
	//
	// Each item represents a single message in the chat history, excluding the current user turn. It has two properties: `role` and `message`. The `role` identifies the sender (`CHATBOT`, `SYSTEM`, or `USER`), while the `message` contains the text content.
	//
	// The chat_history parameter should not be used for `SYSTEM` messages in most cases. Instead, to add a `SYSTEM` role message at the beginning of a conversation, the `preamble` parameter should be used.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	ChatHistory []*ChatMessage `json:"chat_history,omitempty" url:"chat_history,omitempty"`
	// An alternative to `chat_history`.
	//
	// Providing a `conversation_id` creates or resumes a persisted conversation with the specified ID. The ID can be any non empty string.
	// Compatible Deployments: Cohere Platform
	ConversationId *string `json:"conversation_id,omitempty" url:"conversation_id,omitempty"`
	// Defaults to `AUTO` when `connectors` are specified and `OFF` in all other cases.
	//
	// Dictates how the prompt will be constructed.
	//
	// With `prompt_truncation` set to "AUTO", some elements from `chat_history` and `documents` will be dropped in an attempt to construct a prompt that fits within the model's context length limit. During this process the order of the documents and chat history will be changed and ranked by relevance.
	//
	// With `prompt_truncation` set to "AUTO_PRESERVE_ORDER", some elements from `chat_history` and `documents` will be dropped in an attempt to construct a prompt that fits within the model's context length limit. During this process the order of the documents and chat history will be preserved as they are inputted into the API.
	//
	// With `prompt_truncation` set to "OFF", no elements will be dropped. If the sum of the inputs exceeds the model's context length limit, a `TooManyTokens` error will be returned.
	// Compatible Deployments: Cohere Platform Only AUTO_PRESERVE_ORDER: Azure, AWS Sagemaker, Private Deployments
	PromptTruncation *ChatRequestPromptTruncation `json:"prompt_truncation,omitempty" url:"prompt_truncation,omitempty"`
	// Accepts `{"id": "web-search"}`, and/or the `"id"` for a custom [connector](https://docs.cohere.com/docs/connectors), if you've [created](https://docs.cohere.com/docs/creating-and-deploying-a-connector) one.
	//
	// When specified, the model's reply will be enriched with information found by quering each of the connectors (RAG).
	// Compatible Deployments: Cohere Platform
	Connectors []*ChatConnector `json:"connectors,omitempty" url:"connectors,omitempty"`
	// Defaults to `false`.
	//
	// When `true`, the response will only contain a list of generated search queries, but no search will take place, and no reply from the model to the user's `message` will be generated.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	SearchQueriesOnly *bool `json:"search_queries_only,omitempty" url:"search_queries_only,omitempty"`
	// A list of relevant documents that the model can cite to generate a more accurate reply. Each document is a string-string dictionary.
	//
	// Example:
	// `[
	//
	//	{ "title": "Tall penguins", "text": "Emperor penguins are the tallest." },
	//	{ "title": "Penguin habitats", "text": "Emperor penguins only live in Antarctica." },
	//
	// ]`
	//
	// Keys and values from each document will be serialized to a string and passed to the model. The resulting generation will include citations that reference some of these documents.
	//
	// Some suggested keys are "text", "author", and "date". For better generation quality, it is recommended to keep the total word count of the strings in the dictionary to under 300 words.
	//
	// An `id` field (string) can be optionally supplied to identify the document in the citations. This field will not be passed to the model.
	//
	// An `_excludes` field (array of strings) can be optionally supplied to omit some key-value pairs from being shown to the model. The omitted fields will still show up in the citation object. The "_excludes" field will not be passed to the model.
	//
	// See ['Document Mode'](https://docs.cohere.com/docs/retrieval-augmented-generation-rag#document-mode) in the guide for more information.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	Documents []ChatDocument `json:"documents,omitempty" url:"documents,omitempty"`
	// Defaults to `"accurate"`.
	//
	// Dictates the approach taken to generating citations as part of the RAG flow by allowing the user to specify whether they want `"accurate"` results or `"fast"` results.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	CitationQuality *ChatRequestCitationQuality `json:"citation_quality,omitempty" url:"citation_quality,omitempty"`
	// Defaults to `0.3`.
	//
	// A non-negative float that tunes the degree of randomness in generation. Lower temperatures mean less random generations, and higher temperatures mean more random generations.
	//
	// Randomness can be further maximized by increasing the  value of the `p` parameter.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	Temperature *float64 `json:"temperature,omitempty" url:"temperature,omitempty"`
	// The maximum number of tokens the model will generate as part of the response. Note: Setting a low value may result in incomplete generations.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	MaxTokens *int `json:"max_tokens,omitempty" url:"max_tokens,omitempty"`
	// The maximum number of input tokens to send to the model. If not specified, `max_input_tokens` is the model's context length limit minus a small buffer.
	//
	// Input will be truncated according to the `prompt_truncation` parameter.
	// Compatible Deployments: Cohere Platform
	MaxInputTokens *int `json:"max_input_tokens,omitempty" url:"max_input_tokens,omitempty"`
	// Ensures only the top `k` most likely tokens are considered for generation at each step.
	// Defaults to `0`, min value of `0`, max value of `500`.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	K *int `json:"k,omitempty" url:"k,omitempty"`
	// Ensures that only the most likely tokens, with total probability mass of `p`, are considered for generation at each step. If both `k` and `p` are enabled, `p` acts after `k`.
	// Defaults to `0.75`. min value of `0.01`, max value of `0.99`.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	P *float64 `json:"p,omitempty" url:"p,omitempty"`
	// If specified, the backend will make a best effort to sample tokens
	// deterministically, such that repeated requests with the same
	// seed and parameters should return the same result. However,
	// determinism cannot be totally guaranteed.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	Seed *float64 `json:"seed,omitempty" url:"seed,omitempty"`
	// A list of up to 5 strings that the model will use to stop generation. If the model generates a string that matches any of the strings in the list, it will stop generating tokens and return the generated text up to that point not including the stop sequence.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	StopSequences []string `json:"stop_sequences,omitempty" url:"stop_sequences,omitempty"`
	// Defaults to `0.0`, min value of `0.0`, max value of `1.0`.
	//
	// Used to reduce repetitiveness of generated tokens. The higher the value, the stronger a penalty is applied to previously present tokens, proportional to how many times they have already appeared in the prompt or prior generation.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	FrequencyPenalty *float64 `json:"frequency_penalty,omitempty" url:"frequency_penalty,omitempty"`
	// Defaults to `0.0`, min value of `0.0`, max value of `1.0`.
	//
	// Used to reduce repetitiveness of generated tokens. Similar to `frequency_penalty`, except that this penalty is applied equally to all tokens that have already appeared, regardless of their exact frequencies.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	PresencePenalty *float64 `json:"presence_penalty,omitempty" url:"presence_penalty,omitempty"`
	// When enabled, the user's prompt will be sent to the model without
	// any pre-processing.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	RawPrompting *bool `json:"raw_prompting,omitempty" url:"raw_prompting,omitempty"`
	// The prompt is returned in the `prompt` response field when this is enabled.
	ReturnPrompt *bool `json:"return_prompt,omitempty" url:"return_prompt,omitempty"`
	// A list of available tools (functions) that the model may suggest invoking before producing a text response.
	//
	// When `tools` is passed (without `tool_results`), the `text` field in the response will be `""` and the `tool_calls` field in the response will be populated with a list of tool calls that need to be made. If no calls need to be made, the `tool_calls` array will be empty.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	Tools []*Tool `json:"tools,omitempty" url:"tools,omitempty"`
	// A list of results from invoking tools recommended by the model in the previous chat turn. Results are used to produce a text response and will be referenced in citations. When using `tool_results`, `tools` must be passed as well.
	// Each tool_result contains information about how it was invoked, as well as a list of outputs in the form of dictionaries.
	//
	// **Note**: `outputs` must be a list of objects. If your tool returns a single object (eg `{"status": 200}`), make sure to wrap it in a list.
	// “`
	// tool_results = [
	//
	//	{
	//	  "call": {
	//	    "name": <tool name>,
	//	    "parameters": {
	//	      <param name>: <param value>
	//	    }
	//	  },
	//	  "outputs": [{
	//	    <key>: <value>
	//	  }]
	//	},
	//	...
	//
	// ]
	// “`
	// **Note**: Chat calls with `tool_results` should not be included in the Chat history to avoid duplication of the message text.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	ToolResults []*ChatRequestToolResultsItem `json:"tool_results,omitempty" url:"tool_results,omitempty"`
	// contains filtered or unexported fields
}

type ChatRequestCitationQuality string

type ChatRequestConnectorsSearchOptions struct {
	Model       interface{} `json:"model,omitempty" url:"model,omitempty"`
	Temperature interface{} `json:"temperature,omitempty" url:"temperature,omitempty"`
	MaxTokens   interface{} `json:"max_tokens,omitempty" url:"max_tokens,omitempty"`
	Preamble    interface{} `json:"preamble,omitempty" url:"preamble,omitempty"`
	// If specified, the backend will make a best effort to sample tokens deterministically, such that repeated requests with the same seed and parameters should return the same result. However, determinsim cannot be totally guaranteed.
	Seed *float64 `json:"seed,omitempty" url:"seed,omitempty"`
	// contains filtered or unexported fields
}

type ChatRequestPromptTruncation string

type ChatRequestToolResultsItem struct {
	Call    *ToolCall                `json:"call,omitempty" url:"call,omitempty"`
	Outputs []map[string]interface{} `json:"outputs,omitempty" url:"outputs,omitempty"`
	// contains filtered or unexported fields
}

type ChatSearchQueriesGenerationEvent struct {
	// Generated search queries, meant to be used as part of the RAG flow.
	SearchQueries []*ChatSearchQuery `json:"search_queries,omitempty" url:"search_queries,omitempty"`
	// contains filtered or unexported fields
}

type ChatSearchQuery struct {
	// The text of the search query.
	Text string `json:"text" url:"text"`
	// Unique identifier for the generated search query. Useful for submitting feedback.
	GenerationId string `json:"generation_id" url:"generation_id"`
	// contains filtered or unexported fields
}

type ChatSearchResult struct {
	SearchQuery *ChatSearchQuery `json:"search_query,omitempty" url:"search_query,omitempty"`
	// The connector from which this result comes from.
	Connector *ChatSearchResultConnector `json:"connector,omitempty" url:"connector,omitempty"`
	// Identifiers of documents found by this search query.
	DocumentIds []string `json:"document_ids,omitempty" url:"document_ids,omitempty"`
	// An error message if the search failed.
	ErrorMessage *string `json:"error_message,omitempty" url:"error_message,omitempty"`
	// Whether a chat request should continue or not if the request to this connector fails.
	ContinueOnFailure *bool `json:"continue_on_failure,omitempty" url:"continue_on_failure,omitempty"`
	// contains filtered or unexported fields
}

type ChatSearchResultConnector struct {
	// The identifier of the connector.
	Id string `json:"id" url:"id"`
	// contains filtered or unexported fields
}

type ChatSearchResultsEvent struct {
	// Conducted searches and the ids of documents retrieved from each of them.
	SearchResults []*ChatSearchResult `json:"search_results,omitempty" url:"search_results,omitempty"`
	// Documents fetched from searches or provided by the user.
	Documents []ChatDocument `json:"documents,omitempty" url:"documents,omitempty"`
	// contains filtered or unexported fields
}

type ChatStreamEndEvent struct {
	// - `COMPLETE` - the model sent back a finished reply
	// - `ERROR_LIMIT` - the reply was cut off because the model reached the maximum number of tokens for its context length
	// - `MAX_TOKENS` - the reply was cut off because the model reached the maximum number of tokens specified by the max_tokens parameter
	// - `ERROR` - something went wrong when generating the reply
	// - `ERROR_TOXIC` - the model generated a reply that was deemed toxic
	FinishReason ChatStreamEndEventFinishReason `json:"finish_reason" url:"finish_reason"`
	// The consolidated response from the model. Contains the generated reply and all the other information streamed back in the previous events.
	Response *NonStreamedChatResponse `json:"response,omitempty" url:"response,omitempty"`
	// contains filtered or unexported fields
}

type ChatStreamEndEventFinishReason string

type ChatStreamEvent struct {
	// contains filtered or unexported fields
}

type ChatStreamRequest struct {
	// Text input for the model to respond to.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	Message string `json:"message" url:"message"`
	// Defaults to `command-r-plus`.
	//
	// The name of a compatible [Cohere model](https://docs.cohere.com/docs/models) or the ID of a [fine-tuned](https://docs.cohere.com/docs/chat-fine-tuning) model.
	// Compatible Deployments: Cohere Platform, Private Deployments
	Model *string `json:"model,omitempty" url:"model,omitempty"`
	// When specified, the default Cohere preamble will be replaced with the provided one. Preambles are a part of the prompt used to adjust the model's overall behavior and conversation style, and use the `SYSTEM` role.
	//
	// The `SYSTEM` role is also used for the contents of the optional `chat_history=` parameter. When used with the `chat_history=` parameter it adds content throughout a conversation. Conversely, when used with the `preamble=` parameter it adds content at the start of the conversation only.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	Preamble *string `json:"preamble,omitempty" url:"preamble,omitempty"`
	// A list of previous messages between the user and the model, giving the model conversational context for responding to the user's `message`.
	//
	// Each item represents a single message in the chat history, excluding the current user turn. It has two properties: `role` and `message`. The `role` identifies the sender (`CHATBOT`, `SYSTEM`, or `USER`), while the `message` contains the text content.
	//
	// The chat_history parameter should not be used for `SYSTEM` messages in most cases. Instead, to add a `SYSTEM` role message at the beginning of a conversation, the `preamble` parameter should be used.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	ChatHistory []*ChatMessage `json:"chat_history,omitempty" url:"chat_history,omitempty"`
	// An alternative to `chat_history`.
	//
	// Providing a `conversation_id` creates or resumes a persisted conversation with the specified ID. The ID can be any non empty string.
	// Compatible Deployments: Cohere Platform
	ConversationId *string `json:"conversation_id,omitempty" url:"conversation_id,omitempty"`
	// Defaults to `AUTO` when `connectors` are specified and `OFF` in all other cases.
	//
	// Dictates how the prompt will be constructed.
	//
	// With `prompt_truncation` set to "AUTO", some elements from `chat_history` and `documents` will be dropped in an attempt to construct a prompt that fits within the model's context length limit. During this process the order of the documents and chat history will be changed and ranked by relevance.
	//
	// With `prompt_truncation` set to "AUTO_PRESERVE_ORDER", some elements from `chat_history` and `documents` will be dropped in an attempt to construct a prompt that fits within the model's context length limit. During this process the order of the documents and chat history will be preserved as they are inputted into the API.
	//
	// With `prompt_truncation` set to "OFF", no elements will be dropped. If the sum of the inputs exceeds the model's context length limit, a `TooManyTokens` error will be returned.
	// Compatible Deployments: Cohere Platform Only AUTO_PRESERVE_ORDER: Azure, AWS Sagemaker, Private Deployments
	PromptTruncation *ChatStreamRequestPromptTruncation `json:"prompt_truncation,omitempty" url:"prompt_truncation,omitempty"`
	// Accepts `{"id": "web-search"}`, and/or the `"id"` for a custom [connector](https://docs.cohere.com/docs/connectors), if you've [created](https://docs.cohere.com/docs/creating-and-deploying-a-connector) one.
	//
	// When specified, the model's reply will be enriched with information found by quering each of the connectors (RAG).
	// Compatible Deployments: Cohere Platform
	Connectors []*ChatConnector `json:"connectors,omitempty" url:"connectors,omitempty"`
	// Defaults to `false`.
	//
	// When `true`, the response will only contain a list of generated search queries, but no search will take place, and no reply from the model to the user's `message` will be generated.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	SearchQueriesOnly *bool `json:"search_queries_only,omitempty" url:"search_queries_only,omitempty"`
	// A list of relevant documents that the model can cite to generate a more accurate reply. Each document is a string-string dictionary.
	//
	// Example:
	// `[
	//
	//	{ "title": "Tall penguins", "text": "Emperor penguins are the tallest." },
	//	{ "title": "Penguin habitats", "text": "Emperor penguins only live in Antarctica." },
	//
	// ]`
	//
	// Keys and values from each document will be serialized to a string and passed to the model. The resulting generation will include citations that reference some of these documents.
	//
	// Some suggested keys are "text", "author", and "date". For better generation quality, it is recommended to keep the total word count of the strings in the dictionary to under 300 words.
	//
	// An `id` field (string) can be optionally supplied to identify the document in the citations. This field will not be passed to the model.
	//
	// An `_excludes` field (array of strings) can be optionally supplied to omit some key-value pairs from being shown to the model. The omitted fields will still show up in the citation object. The "_excludes" field will not be passed to the model.
	//
	// See ['Document Mode'](https://docs.cohere.com/docs/retrieval-augmented-generation-rag#document-mode) in the guide for more information.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	Documents []ChatDocument `json:"documents,omitempty" url:"documents,omitempty"`
	// Defaults to `"accurate"`.
	//
	// Dictates the approach taken to generating citations as part of the RAG flow by allowing the user to specify whether they want `"accurate"` results or `"fast"` results.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	CitationQuality *ChatStreamRequestCitationQuality `json:"citation_quality,omitempty" url:"citation_quality,omitempty"`
	// Defaults to `0.3`.
	//
	// A non-negative float that tunes the degree of randomness in generation. Lower temperatures mean less random generations, and higher temperatures mean more random generations.
	//
	// Randomness can be further maximized by increasing the  value of the `p` parameter.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	Temperature *float64 `json:"temperature,omitempty" url:"temperature,omitempty"`
	// The maximum number of tokens the model will generate as part of the response. Note: Setting a low value may result in incomplete generations.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	MaxTokens *int `json:"max_tokens,omitempty" url:"max_tokens,omitempty"`
	// The maximum number of input tokens to send to the model. If not specified, `max_input_tokens` is the model's context length limit minus a small buffer.
	//
	// Input will be truncated according to the `prompt_truncation` parameter.
	// Compatible Deployments: Cohere Platform
	MaxInputTokens *int `json:"max_input_tokens,omitempty" url:"max_input_tokens,omitempty"`
	// Ensures only the top `k` most likely tokens are considered for generation at each step.
	// Defaults to `0`, min value of `0`, max value of `500`.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	K *int `json:"k,omitempty" url:"k,omitempty"`
	// Ensures that only the most likely tokens, with total probability mass of `p`, are considered for generation at each step. If both `k` and `p` are enabled, `p` acts after `k`.
	// Defaults to `0.75`. min value of `0.01`, max value of `0.99`.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	P *float64 `json:"p,omitempty" url:"p,omitempty"`
	// If specified, the backend will make a best effort to sample tokens
	// deterministically, such that repeated requests with the same
	// seed and parameters should return the same result. However,
	// determinism cannot be totally guaranteed.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	Seed *float64 `json:"seed,omitempty" url:"seed,omitempty"`
	// A list of up to 5 strings that the model will use to stop generation. If the model generates a string that matches any of the strings in the list, it will stop generating tokens and return the generated text up to that point not including the stop sequence.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	StopSequences []string `json:"stop_sequences,omitempty" url:"stop_sequences,omitempty"`
	// Defaults to `0.0`, min value of `0.0`, max value of `1.0`.
	//
	// Used to reduce repetitiveness of generated tokens. The higher the value, the stronger a penalty is applied to previously present tokens, proportional to how many times they have already appeared in the prompt or prior generation.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	FrequencyPenalty *float64 `json:"frequency_penalty,omitempty" url:"frequency_penalty,omitempty"`
	// Defaults to `0.0`, min value of `0.0`, max value of `1.0`.
	//
	// Used to reduce repetitiveness of generated tokens. Similar to `frequency_penalty`, except that this penalty is applied equally to all tokens that have already appeared, regardless of their exact frequencies.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	PresencePenalty *float64 `json:"presence_penalty,omitempty" url:"presence_penalty,omitempty"`
	// When enabled, the user's prompt will be sent to the model without
	// any pre-processing.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	RawPrompting *bool `json:"raw_prompting,omitempty" url:"raw_prompting,omitempty"`
	// The prompt is returned in the `prompt` response field when this is enabled.
	ReturnPrompt *bool `json:"return_prompt,omitempty" url:"return_prompt,omitempty"`
	// A list of available tools (functions) that the model may suggest invoking before producing a text response.
	//
	// When `tools` is passed (without `tool_results`), the `text` field in the response will be `""` and the `tool_calls` field in the response will be populated with a list of tool calls that need to be made. If no calls need to be made, the `tool_calls` array will be empty.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	Tools []*Tool `json:"tools,omitempty" url:"tools,omitempty"`
	// A list of results from invoking tools recommended by the model in the previous chat turn. Results are used to produce a text response and will be referenced in citations. When using `tool_results`, `tools` must be passed as well.
	// Each tool_result contains information about how it was invoked, as well as a list of outputs in the form of dictionaries.
	//
	// **Note**: `outputs` must be a list of objects. If your tool returns a single object (eg `{"status": 200}`), make sure to wrap it in a list.
	// “`
	// tool_results = [
	//
	//	{
	//	  "call": {
	//	    "name": <tool name>,
	//	    "parameters": {
	//	      <param name>: <param value>
	//	    }
	//	  },
	//	  "outputs": [{
	//	    <key>: <value>
	//	  }]
	//	},
	//	...
	//
	// ]
	// “`
	// **Note**: Chat calls with `tool_results` should not be included in the Chat history to avoid duplication of the message text.
	// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
	ToolResults []*ChatStreamRequestToolResultsItem `json:"tool_results,omitempty" url:"tool_results,omitempty"`
	// contains filtered or unexported fields
}

type ChatStreamRequestCitationQuality string

type ChatStreamRequestConnectorsSearchOptions struct {
	Model       interface{} `json:"model,omitempty" url:"model,omitempty"`
	Temperature interface{} `json:"temperature,omitempty" url:"temperature,omitempty"`
	MaxTokens   interface{} `json:"max_tokens,omitempty" url:"max_tokens,omitempty"`
	Preamble    interface{} `json:"preamble,omitempty" url:"preamble,omitempty"`
	// If specified, the backend will make a best effort to sample tokens deterministically, such that repeated requests with the same seed and parameters should return the same result. However, determinsim cannot be totally guaranteed.
	Seed *float64 `json:"seed,omitempty" url:"seed,omitempty"`
	// contains filtered or unexported fields
}

type ChatStreamRequestPromptTruncation string

type ChatStreamRequestToolResultsItem struct {
	Call    *ToolCall                `json:"call,omitempty" url:"call,omitempty"`
	Outputs []map[string]interface{} `json:"outputs,omitempty" url:"outputs,omitempty"`
	// contains filtered or unexported fields
}

type ChatStreamStartEvent struct {
	// Unique identifier for the generated reply. Useful for submitting feedback.
	GenerationId string `json:"generation_id" url:"generation_id"`
	// contains filtered or unexported fields
}

type ChatTextGenerationEvent struct {
	// The next batch of text generated by the model.
	Text string `json:"text" url:"text"`
	// contains filtered or unexported fields
}

type ChatToolCallsGenerationEvent struct {
	ToolCalls []*ToolCall `json:"tool_calls,omitempty" url:"tool_calls,omitempty"`
	// contains filtered or unexported fields
}

type CheckApiKeyResponse struct {
	Valid          bool    `json:"valid" url:"valid"`
	OrganizationId *string `json:"organization_id,omitempty" url:"organization_id,omitempty"`
	OwnerId        *string `json:"owner_id,omitempty" url:"owner_id,omitempty"`
	// contains filtered or unexported fields
}

type ClassifyDataMetrics struct {
	LabelMetrics []*LabelMetric `json:"label_metrics,omitempty" url:"label_metrics,omitempty"`
	// contains filtered or unexported fields
}

type ClassifyExample struct {
	Text  *string `json:"text,omitempty" url:"text,omitempty"`
	Label *string `json:"label,omitempty" url:"label,omitempty"`
	// contains filtered or unexported fields
}

type ClassifyRequest struct {
	// A list of up to 96 texts to be classified. Each one must be a non-empty string.
	// There is, however, no consistent, universal limit to the length a particular input can be. We perform classification on the first `x` tokens of each input, and `x` varies depending on which underlying model is powering classification. The maximum token length for each model is listed in the "max tokens" column [here](https://docs.cohere.com/docs/models).
	// Note: by default the `truncate` parameter is set to `END`, so tokens exceeding the limit will be automatically dropped. This behavior can be disabled by setting `truncate` to `NONE`, which will result in validation errors for longer texts.
	Inputs []string `json:"inputs,omitempty" url:"inputs,omitempty"`
	// An array of examples to provide context to the model. Each example is a text string and its associated label/class. Each unique label requires at least 2 examples associated with it; the maximum number of examples is 2500, and each example has a maximum length of 512 tokens. The values should be structured as `{text: "...",label: "..."}`.
	// Note: [Fine-tuned Models](https://docs.cohere.com/docs/classify-fine-tuning) trained on classification examples don't require the `examples` parameter to be passed in explicitly.
	Examples []*ClassifyExample `json:"examples,omitempty" url:"examples,omitempty"`
	// The identifier of the model. Currently available models are `embed-multilingual-v2.0`, `embed-english-light-v2.0`, and `embed-english-v2.0` (default). Smaller "light" models are faster, while larger models will perform better. [Fine-tuned models](https://docs.cohere.com/docs/fine-tuning) can also be supplied with their full ID.
	Model *string `json:"model,omitempty" url:"model,omitempty"`
	// The ID of a custom playground preset. You can create presets in the [playground](https://dashboard.cohere.ai/playground/classify?model=large). If you use a preset, all other parameters become optional, and any included parameters will override the preset's parameters.
	Preset *string `json:"preset,omitempty" url:"preset,omitempty"`
	// One of `NONE|START|END` to specify how the API will handle inputs longer than the maximum token length.
	// Passing `START` will discard the start of the input. `END` will discard the end of the input. In both cases, input is discarded until the remaining input is exactly the maximum input token length for the model.
	// If `NONE` is selected, when the input exceeds the maximum input token length an error will be returned.
	Truncate *ClassifyRequestTruncate `json:"truncate,omitempty" url:"truncate,omitempty"`
}

type ClassifyRequestTruncate string

type ClassifyResponse struct {
	Id              string                                 `json:"id" url:"id"`
	Classifications []*ClassifyResponseClassificationsItem `json:"classifications,omitempty" url:"classifications,omitempty"`
	Meta            *ApiMeta                               `json:"meta,omitempty" url:"meta,omitempty"`
	// contains filtered or unexported fields
}

type ClassifyResponseClassificationsItem struct {
	Id string `json:"id" url:"id"`
	// The input text that was classified
	Input *string `json:"input,omitempty" url:"input,omitempty"`
	// The predicted label for the associated query (only filled for single-label models)
	Prediction *string `json:"prediction,omitempty" url:"prediction,omitempty"`
	// An array containing the predicted labels for the associated query (only filled for single-label classification)
	Predictions []string `json:"predictions,omitempty" url:"predictions,omitempty"`
	// The confidence score for the top predicted class (only filled for single-label classification)
	Confidence *float64 `json:"confidence,omitempty" url:"confidence,omitempty"`
	// An array containing the confidence scores of all the predictions in the same order
	Confidences []float64 `json:"confidences,omitempty" url:"confidences,omitempty"`
	// A map containing each label and its confidence score according to the classifier. All the confidence scores add up to 1 for single-label classification. For multi-label classification the label confidences are independent of each other, so they don't have to sum up to 1.
	Labels map[string]*ClassifyResponseClassificationsItemLabelsValue `json:"labels,omitempty" url:"labels,omitempty"`
	// The type of classification performed
	ClassificationType ClassifyResponseClassificationsItemClassificationType `json:"classification_type" url:"classification_type"`
	// contains filtered or unexported fields
}

type ClassifyResponseClassificationsItemClassificationType string

type ClassifyResponseClassificationsItemLabelsValue struct {
	Confidence *float64 `json:"confidence,omitempty" url:"confidence,omitempty"`
	// contains filtered or unexported fields
}

type CompatibleEndpoint string

type Connector struct {
	// The unique identifier of the connector (used in both `/connectors` & `/chat` endpoints).
	// This is automatically created from the name of the connector upon registration.
	Id string `json:"id" url:"id"`
	// The organization to which this connector belongs. This is automatically set to
	// the organization of the user who created the connector.
	OrganizationId *string `json:"organization_id,omitempty" url:"organization_id,omitempty"`
	// A human-readable name for the connector.
	Name string `json:"name" url:"name"`
	// A description of the connector.
	Description *string `json:"description,omitempty" url:"description,omitempty"`
	// The URL of the connector that will be used to search for documents.
	Url *string `json:"url,omitempty" url:"url,omitempty"`
	// The UTC time at which the connector was created.
	CreatedAt time.Time `json:"created_at" url:"created_at"`
	// The UTC time at which the connector was last updated.
	UpdatedAt time.Time `json:"updated_at" url:"updated_at"`
	// A list of fields to exclude from the prompt (fields remain in the document).
	Excludes []string `json:"excludes,omitempty" url:"excludes,omitempty"`
	// The type of authentication/authorization used by the connector. Possible values: [oauth, service_auth]
	AuthType *string `json:"auth_type,omitempty" url:"auth_type,omitempty"`
	// The OAuth 2.0 configuration for the connector.
	Oauth *ConnectorOAuth `json:"oauth,omitempty" url:"oauth,omitempty"`
	// The OAuth status for the user making the request. One of ["valid", "expired", ""]. Empty string (field is omitted) means the user has not authorized the connector yet.
	AuthStatus *ConnectorAuthStatus `json:"auth_status,omitempty" url:"auth_status,omitempty"`
	// Whether the connector is active or not.
	Active *bool `json:"active,omitempty" url:"active,omitempty"`
	// Whether a chat request should continue or not if the request to this connector fails.
	ContinueOnFailure *bool `json:"continue_on_failure,omitempty" url:"continue_on_failure,omitempty"`
	// contains filtered or unexported fields
}

type ConnectorAuthStatus string

type ConnectorOAuth struct {
	// The OAuth 2.0 client ID. This field is encrypted at rest.
	ClientId *string `json:"client_id,omitempty" url:"client_id,omitempty"`
	// The OAuth 2.0 client Secret. This field is encrypted at rest and never returned in a response.
	ClientSecret *string `json:"client_secret,omitempty" url:"client_secret,omitempty"`
	// The OAuth 2.0 /authorize endpoint to use when users authorize the connector.
	AuthorizeUrl string `json:"authorize_url" url:"authorize_url"`
	// The OAuth 2.0 /token endpoint to use when users authorize the connector.
	TokenUrl string `json:"token_url" url:"token_url"`
	// The OAuth scopes to request when users authorize the connector.
	Scope *string `json:"scope,omitempty" url:"scope,omitempty"`
	// contains filtered or unexported fields
}

type ConnectorsListRequest struct {
	// Maximum number of connectors to return [0, 100].
	Limit *float64 `json:"-" url:"limit,omitempty"`
	// Number of connectors to skip before returning results [0, inf].
	Offset *float64 `json:"-" url:"offset,omitempty"`
}

type ConnectorsOAuthAuthorizeRequest struct {
	// The URL to redirect to after the connector has been authorized.
	AfterTokenRedirect *string `json:"-" url:"after_token_redirect,omitempty"`
}

type CreateConnectorOAuth struct {
	// The OAuth 2.0 client ID. This fields is encrypted at rest.
	ClientId *string `json:"client_id,omitempty" url:"client_id,omitempty"`
	// The OAuth 2.0 client Secret. This field is encrypted at rest and never returned in a response.
	ClientSecret *string `json:"client_secret,omitempty" url:"client_secret,omitempty"`
	// The OAuth 2.0 /authorize endpoint to use when users authorize the connector.
	AuthorizeUrl *string `json:"authorize_url,omitempty" url:"authorize_url,omitempty"`
	// The OAuth 2.0 /token endpoint to use when users authorize the connector.
	TokenUrl *string `json:"token_url,omitempty" url:"token_url,omitempty"`
	// The OAuth scopes to request when users authorize the connector.
	Scope *string `json:"scope,omitempty" url:"scope,omitempty"`
	// contains filtered or unexported fields
}

type CreateConnectorRequest struct {
	// A human-readable name for the connector.
	Name string `json:"name" url:"name"`
	// A description of the connector.
	Description *string `json:"description,omitempty" url:"description,omitempty"`
	// The URL of the connector that will be used to search for documents.
	Url string `json:"url" url:"url"`
	// A list of fields to exclude from the prompt (fields remain in the document).
	Excludes []string `json:"excludes,omitempty" url:"excludes,omitempty"`
	// The OAuth 2.0 configuration for the connector. Cannot be specified if service_auth is specified.
	Oauth *CreateConnectorOAuth `json:"oauth,omitempty" url:"oauth,omitempty"`
	// Whether the connector is active or not.
	Active *bool `json:"active,omitempty" url:"active,omitempty"`
	// Whether a chat request should continue or not if the request to this connector fails.
	ContinueOnFailure *bool `json:"continue_on_failure,omitempty" url:"continue_on_failure,omitempty"`
	// The service to service authentication configuration for the connector. Cannot be specified if oauth is specified.
	ServiceAuth *CreateConnectorServiceAuth `json:"service_auth,omitempty" url:"service_auth,omitempty"`
}

type CreateConnectorResponse struct {
	Connector *Connector `json:"connector,omitempty" url:"connector,omitempty"`
	// contains filtered or unexported fields
}

type CreateConnectorServiceAuth struct {
	Type AuthTokenType `json:"type" url:"type"`
	// The token that will be used in the HTTP Authorization header when making requests to the connector. This field is encrypted at rest and never returned in a response.
	Token string `json:"token" url:"token"`
	// contains filtered or unexported fields
}

type CreateEmbedJobRequest struct {
	// ID of the embedding model.
	//
	// Available models and corresponding embedding dimensions:
	//
	// - `embed-english-v3.0` : 1024
	// - `embed-multilingual-v3.0` : 1024
	// - `embed-english-light-v3.0` : 384
	// - `embed-multilingual-light-v3.0` : 384
	Model string `json:"model" url:"model"`
	// ID of a [Dataset](https://docs.cohere.com/docs/datasets). The Dataset must be of type `embed-input` and must have a validation status `Validated`
	DatasetId string         `json:"dataset_id" url:"dataset_id"`
	InputType EmbedInputType `json:"input_type" url:"input_type"`
	// The name of the embed job.
	Name *string `json:"name,omitempty" url:"name,omitempty"`
	// Specifies the types of embeddings you want to get back. Not required and default is None, which returns the Embed Floats response type. Can be one or more of the following types.
	//
	// * `"float"`: Use this when you want to get back the default float embeddings. Valid for all models.
	// * `"int8"`: Use this when you want to get back signed int8 embeddings. Valid for only v3 models.
	// * `"uint8"`: Use this when you want to get back unsigned int8 embeddings. Valid for only v3 models.
	// * `"binary"`: Use this when you want to get back signed binary embeddings. Valid for only v3 models.
	// * `"ubinary"`: Use this when you want to get back unsigned binary embeddings. Valid for only v3 models.
	EmbeddingTypes []EmbeddingType `json:"embedding_types,omitempty" url:"embedding_types,omitempty"`
	// One of `START|END` to specify how the API will handle inputs longer than the maximum token length.
	//
	// Passing `START` will discard the start of the input. `END` will discard the end of the input. In both cases, input is discarded until the remaining input is exactly the maximum input token length for the model.
	Truncate *CreateEmbedJobRequestTruncate `json:"truncate,omitempty" url:"truncate,omitempty"`
}

type CreateEmbedJobRequestTruncate string

type CreateEmbedJobResponse struct {
	JobId string   `json:"job_id" url:"job_id"`
	Meta  *ApiMeta `json:"meta,omitempty" url:"meta,omitempty"`
	// contains filtered or unexported fields
}

type Dataset struct {
	// The dataset ID
	Id string `json:"id" url:"id"`
	// The name of the dataset
	Name string `json:"name" url:"name"`
	// The creation date
	CreatedAt time.Time `json:"created_at" url:"created_at"`
	// The last update date
	UpdatedAt        time.Time               `json:"updated_at" url:"updated_at"`
	DatasetType      DatasetType             `json:"dataset_type" url:"dataset_type"`
	ValidationStatus DatasetValidationStatus `json:"validation_status" url:"validation_status"`
	// Errors found during validation
	ValidationError *string `json:"validation_error,omitempty" url:"validation_error,omitempty"`
	// the avro schema of the dataset
	Schema         *string  `json:"schema,omitempty" url:"schema,omitempty"`
	RequiredFields []string `json:"required_fields,omitempty" url:"required_fields,omitempty"`
	PreserveFields []string `json:"preserve_fields,omitempty" url:"preserve_fields,omitempty"`
	// the underlying files that make up the dataset
	DatasetParts []*DatasetPart `json:"dataset_parts,omitempty" url:"dataset_parts,omitempty"`
	// warnings found during validation
	ValidationWarnings []string `json:"validation_warnings,omitempty" url:"validation_warnings,omitempty"`
	// contains filtered or unexported fields
}

type DatasetPart struct {
	// The dataset part ID
	Id string `json:"id" url:"id"`
	// The name of the dataset part
	Name string `json:"name" url:"name"`
	// The download url of the file
	Url *string `json:"url,omitempty" url:"url,omitempty"`
	// The index of the file
	Index *int `json:"index,omitempty" url:"index,omitempty"`
	// The size of the file in bytes
	SizeBytes *int `json:"size_bytes,omitempty" url:"size_bytes,omitempty"`
	// The number of rows in the file
	NumRows *int `json:"num_rows,omitempty" url:"num_rows,omitempty"`
	// The download url of the original file
	OriginalUrl *string `json:"original_url,omitempty" url:"original_url,omitempty"`
	// The first few rows of the parsed file
	Samples []string `json:"samples,omitempty" url:"samples,omitempty"`
	// contains filtered or unexported fields
}

type DatasetType string

type DatasetValidationStatus string

type DatasetsCreateRequest struct {
	// The name of the uploaded dataset.
	Name string `json:"-" url:"name"`
	// The dataset type, which is used to validate the data. Valid types are `embed-input`, `reranker-finetune-input`, `single-label-classification-finetune-input`, `chat-finetune-input`, and `multi-label-classification-finetune-input`.
	Type DatasetType `json:"-" url:"type"`
	// Indicates if the original file should be stored.
	KeepOriginalFile *bool `json:"-" url:"keep_original_file,omitempty"`
	// Indicates whether rows with malformed input should be dropped (instead of failing the validation check). Dropped rows will be returned in the warnings field.
	SkipMalformedInput *bool `json:"-" url:"skip_malformed_input,omitempty"`
	// List of names of fields that will be persisted in the Dataset. By default the Dataset will retain only the required fields indicated in the [schema for the corresponding Dataset type](https://docs.cohere.com/docs/datasets#dataset-types). For example, datasets of type `embed-input` will drop all fields other than the required `text` field. If any of the fields in `keep_fields` are missing from the uploaded file, Dataset validation will fail.
	KeepFields []*string `json:"-" url:"keep_fields,omitempty"`
	// List of names of fields that will be persisted in the Dataset. By default the Dataset will retain only the required fields indicated in the [schema for the corresponding Dataset type](https://docs.cohere.com/docs/datasets#dataset-types). For example, Datasets of type `embed-input` will drop all fields other than the required `text` field. If any of the fields in `optional_fields` are missing from the uploaded file, Dataset validation will pass.
	OptionalFields []*string `json:"-" url:"optional_fields,omitempty"`
	// Raw .txt uploads will be split into entries using the text_separator value.
	TextSeparator *string `json:"-" url:"text_separator,omitempty"`
	// The delimiter used for .csv uploads.
	CsvDelimiter *string `json:"-" url:"csv_delimiter,omitempty"`
	// flag to enable dry_run mode
	DryRun *bool `json:"-" url:"dry_run,omitempty"`
}

type DatasetsCreateResponse struct {
	// The dataset ID
	Id *string `json:"id,omitempty" url:"id,omitempty"`
	// contains filtered or unexported fields
}

type DatasetsCreateResponseDatasetPartsItem struct {
	// the name of the dataset part
	Name *string `json:"name,omitempty" url:"name,omitempty"`
	// the number of rows in the dataset part
	NumRows *float64 `json:"num_rows,omitempty" url:"num_rows,omitempty"`
	Samples []string `json:"samples,omitempty" url:"samples,omitempty"`
	// the kind of dataset part
	PartKind *string `json:"part_kind,omitempty" url:"part_kind,omitempty"`
	// contains filtered or unexported fields
}

type DatasetsGetResponse struct {
	Dataset *Dataset `json:"dataset,omitempty" url:"dataset,omitempty"`
	// contains filtered or unexported fields
}

type DatasetsGetUsageResponse struct {
	// The total number of bytes used by the organization.
	OrganizationUsage *string `json:"organization_usage,omitempty" url:"organization_usage,omitempty"`
	// contains filtered or unexported fields
}

type DatasetsListRequest struct {
	// optional filter by dataset type
	DatasetType *string `json:"-" url:"datasetType,omitempty"`
	// optional filter before a date
	Before *time.Time `json:"-" url:"before,omitempty"`
	// optional filter after a date
	After *time.Time `json:"-" url:"after,omitempty"`
	// optional limit to number of results
	Limit *float64 `json:"-" url:"limit,omitempty"`
	// optional offset to start of results
	Offset *float64 `json:"-" url:"offset,omitempty"`
	// optional filter by validation status
	ValidationStatus *DatasetValidationStatus `json:"-" url:"validationStatus,omitempty"`
}

type DatasetsListResponse struct {
	Datasets []*Dataset `json:"datasets,omitempty" url:"datasets,omitempty"`
	// contains filtered or unexported fields
}

type DeleteConnectorResponse = map[string]interface{}

type DetokenizeRequest struct {
	// The list of tokens to be detokenized.
	Tokens []int `json:"tokens,omitempty" url:"tokens,omitempty"`
	// An optional parameter to provide the model name. This will ensure that the detokenization is done by the tokenizer used by that model.
	Model string `json:"model" url:"model"`
}

type DetokenizeResponse struct {
	// A string representing the list of tokens.
	Text string   `json:"text" url:"text"`
	Meta *ApiMeta `json:"meta,omitempty" url:"meta,omitempty"`
	// contains filtered or unexported fields
}

type EmbedByTypeResponse struct {
	Id string `json:"id" url:"id"`
	// An object with different embedding types. The length of each embedding type array will be the same as the length of the original `texts` array.
	Embeddings *EmbedByTypeResponseEmbeddings `json:"embeddings,omitempty" url:"embeddings,omitempty"`
	// The text entries for which embeddings were returned.
	Texts []string `json:"texts,omitempty" url:"texts,omitempty"`
	Meta  *ApiMeta `json:"meta,omitempty" url:"meta,omitempty"`
	// contains filtered or unexported fields
}

type EmbedByTypeResponseEmbeddings struct {
	// An array of float embeddings.
	Float [][]float64 `json:"float,omitempty" url:"float,omitempty"`
	// An array of signed int8 embeddings. Each value is between -128 and 127.
	Int8 [][]int `json:"int8,omitempty" url:"int8,omitempty"`
	// An array of unsigned int8 embeddings. Each value is between 0 and 255.
	Uint8 [][]int `json:"uint8,omitempty" url:"uint8,omitempty"`
	// An array of packed signed binary embeddings. The length of each binary embedding is 1/8 the length of the float embeddings of the provided model. Each value is between -128 and 127.
	Binary [][]int `json:"binary,omitempty" url:"binary,omitempty"`
	// An array of packed unsigned binary embeddings. The length of each binary embedding is 1/8 the length of the float embeddings of the provided model. Each value is between 0 and 255.
	Ubinary [][]int `json:"ubinary,omitempty" url:"ubinary,omitempty"`
	// contains filtered or unexported fields
}

type EmbedFloatsResponse struct {
	Id string `json:"id" url:"id"`
	// An array of embeddings, where each embedding is an array of floats. The length of the `embeddings` array will be the same as the length of the original `texts` array.
	Embeddings [][]float64 `json:"embeddings,omitempty" url:"embeddings,omitempty"`
	// The text entries for which embeddings were returned.
	Texts []string `json:"texts,omitempty" url:"texts,omitempty"`
	Meta  *ApiMeta `json:"meta,omitempty" url:"meta,omitempty"`
	// contains filtered or unexported fields
}

type EmbedInputType string

type EmbedJob struct {
	// ID of the embed job
	JobId string `json:"job_id" url:"job_id"`
	// The name of the embed job
	Name *string `json:"name,omitempty" url:"name,omitempty"`
	// The status of the embed job
	Status EmbedJobStatus `json:"status" url:"status"`
	// The creation date of the embed job
	CreatedAt time.Time `json:"created_at" url:"created_at"`
	// ID of the input dataset
	InputDatasetId string `json:"input_dataset_id" url:"input_dataset_id"`
	// ID of the resulting output dataset
	OutputDatasetId *string `json:"output_dataset_id,omitempty" url:"output_dataset_id,omitempty"`
	// ID of the model used to embed
	Model string `json:"model" url:"model"`
	// The truncation option used
	Truncate EmbedJobTruncate `json:"truncate" url:"truncate"`
	Meta     *ApiMeta         `json:"meta,omitempty" url:"meta,omitempty"`
	// contains filtered or unexported fields
}

type EmbedJobStatus string

type EmbedJobTruncate string

type EmbedRequest struct {
	// An array of strings for the model to embed. Maximum number of texts per call is `96`. We recommend reducing the length of each text to be under `512` tokens for optimal quality.
	Texts []string `json:"texts,omitempty" url:"texts,omitempty"`
	// Defaults to embed-english-v2.0
	//
	// The identifier of the model. Smaller "light" models are faster, while larger models will perform better. [Custom models](/docs/training-custom-models) can also be supplied with their full ID.
	//
	// Available models and corresponding embedding dimensions:
	//
	// * `embed-english-v3.0`  1024
	// * `embed-multilingual-v3.0`  1024
	// * `embed-english-light-v3.0`  384
	// * `embed-multilingual-light-v3.0`  384
	//
	// * `embed-english-v2.0`  4096
	// * `embed-english-light-v2.0`  1024
	// * `embed-multilingual-v2.0`  768
	Model     *string         `json:"model,omitempty" url:"model,omitempty"`
	InputType *EmbedInputType `json:"input_type,omitempty" url:"input_type,omitempty"`
	// Specifies the types of embeddings you want to get back. Not required and default is None, which returns the Embed Floats response type. Can be one or more of the following types.
	//
	// * `"float"`: Use this when you want to get back the default float embeddings. Valid for all models.
	// * `"int8"`: Use this when you want to get back signed int8 embeddings. Valid for only v3 models.
	// * `"uint8"`: Use this when you want to get back unsigned int8 embeddings. Valid for only v3 models.
	// * `"binary"`: Use this when you want to get back signed binary embeddings. Valid for only v3 models.
	// * `"ubinary"`: Use this when you want to get back unsigned binary embeddings. Valid for only v3 models.
	EmbeddingTypes []EmbeddingType `json:"embedding_types,omitempty" url:"embedding_types,omitempty"`
	// One of `NONE|START|END` to specify how the API will handle inputs longer than the maximum token length.
	//
	// Passing `START` will discard the start of the input. `END` will discard the end of the input. In both cases, input is discarded until the remaining input is exactly the maximum input token length for the model.
	//
	// If `NONE` is selected, when the input exceeds the maximum input token length an error will be returned.
	Truncate *EmbedRequestTruncate `json:"truncate,omitempty" url:"truncate,omitempty"`
}

type EmbedRequestTruncate string

type EmbedResponse struct {
	ResponseType     string
	EmbeddingsFloats *EmbedFloatsResponse
	EmbeddingsByType *EmbedByTypeResponse
}

type EmbedResponseVisitor interface {
	VisitEmbeddingsFloats(*EmbedFloatsResponse) error
	VisitEmbeddingsByType(*EmbedByTypeResponse) error
}

type EmbeddingType string

type FinetuneDatasetMetrics struct {
	// The number of tokens of valid examples that can be used for training.
	TrainableTokenCount *string `json:"trainable_token_count,omitempty" url:"trainable_token_count,omitempty"`
	// The overall number of examples.
	TotalExamples *string `json:"total_examples,omitempty" url:"total_examples,omitempty"`
	// The number of training examples.
	TrainExamples *string `json:"train_examples,omitempty" url:"train_examples,omitempty"`
	// The size in bytes of all training examples.
	TrainSizeBytes *string `json:"train_size_bytes,omitempty" url:"train_size_bytes,omitempty"`
	// Number of evaluation examples.
	EvalExamples *string `json:"eval_examples,omitempty" url:"eval_examples,omitempty"`
	// The size in bytes of all eval examples.
	EvalSizeBytes *string `json:"eval_size_bytes,omitempty" url:"eval_size_bytes,omitempty"`
	// contains filtered or unexported fields
}

type FinetuningListEventsRequest struct {
	// Maximum number of results to be returned by the server. If 0, defaults to 50.
	PageSize *int `json:"-" url:"page_size,omitempty"`
	// Request a specific page of the list results.
	PageToken *string `json:"-" url:"page_token,omitempty"`
	// Comma separated list of fields. For example: "created_at,name". The default
	// sorting order is ascending. To specify descending order for a field, append
	// " desc" to the field name. For example: "created_at desc,name".
	//
	// Supported sorting fields:
	//
	// - created_at (default)
	OrderBy *string `json:"-" url:"order_by,omitempty"`
}

type FinetuningListFinetunedModelsRequest struct {
	// Maximum number of results to be returned by the server. If 0, defaults to 50.
	PageSize *int `json:"-" url:"page_size,omitempty"`
	// Request a specific page of the list results.
	PageToken *string `json:"-" url:"page_token,omitempty"`
	// Comma separated list of fields. For example: "created_at,name". The default
	// sorting order is ascending. To specify descending order for a field, append
	// " desc" to the field name. For example: "created_at desc,name".
	//
	// Supported sorting fields:
	//
	// - created_at (default)
	OrderBy *string `json:"-" url:"order_by,omitempty"`
}

type FinetuningListTrainingStepMetricsRequest struct {
	// Maximum number of results to be returned by the server. If 0, defaults to 50.
	PageSize *int `json:"-" url:"page_size,omitempty"`
	// Request a specific page of the list results.
	PageToken *string `json:"-" url:"page_token,omitempty"`
}

type FinetuningUpdateFinetunedModelRequest struct {
	// FinetunedModel name (e.g. `foobar`).
	Name string `json:"name" url:"name"`
	// User ID of the creator.
	CreatorId *string `json:"creator_id,omitempty" url:"creator_id,omitempty"`
	// Organization ID.
	OrganizationId *string `json:"organization_id,omitempty" url:"organization_id,omitempty"`
	// FinetunedModel settings such as dataset, hyperparameters...
	Settings *finetuning.Settings `json:"settings,omitempty" url:"settings,omitempty"`
	// Current stage in the life-cycle of the fine-tuned model.
	Status *finetuning.Status `json:"status,omitempty" url:"status,omitempty"`
	// Creation timestamp.
	CreatedAt *time.Time `json:"created_at,omitempty" url:"created_at,omitempty"`
	// Latest update timestamp.
	UpdatedAt *time.Time `json:"updated_at,omitempty" url:"updated_at,omitempty"`
	// Timestamp for the completed fine-tuning.
	CompletedAt *time.Time `json:"completed_at,omitempty" url:"completed_at,omitempty"`
	// Timestamp for the latest request to this fine-tuned model.
	LastUsed *time.Time `json:"last_used,omitempty" url:"last_used,omitempty"`
}

type FinishReason string

type ForbiddenError struct {
	*core.APIError
	Body interface{}
}

type GenerateRequest struct {
	// The input text that serves as the starting point for generating the response.
	// Note: The prompt will be pre-processed and modified before reaching the model.
	Prompt string `json:"prompt" url:"prompt"`
	// The identifier of the model to generate with. Currently available models are `command` (default), `command-nightly` (experimental), `command-light`, and `command-light-nightly` (experimental).
	// Smaller, "light" models are faster, while larger models will perform better. [Custom models](/docs/training-custom-models) can also be supplied with their full ID.
	Model *string `json:"model,omitempty" url:"model,omitempty"`
	// The maximum number of generations that will be returned. Defaults to `1`, min value of `1`, max value of `5`.
	NumGenerations *int `json:"num_generations,omitempty" url:"num_generations,omitempty"`
	// The maximum number of tokens the model will generate as part of the response. Note: Setting a low value may result in incomplete generations.
	//
	// This parameter is off by default, and if it's not specified, the model will continue generating until it emits an EOS completion token. See [BPE Tokens](/bpe-tokens-wiki) for more details.
	//
	// Can only be set to `0` if `return_likelihoods` is set to `ALL` to get the likelihood of the prompt.
	MaxTokens *int `json:"max_tokens,omitempty" url:"max_tokens,omitempty"`
	// One of `NONE|START|END` to specify how the API will handle inputs longer than the maximum token length.
	//
	// Passing `START` will discard the start of the input. `END` will discard the end of the input. In both cases, input is discarded until the remaining input is exactly the maximum input token length for the model.
	//
	// If `NONE` is selected, when the input exceeds the maximum input token length an error will be returned.
	Truncate *GenerateRequestTruncate `json:"truncate,omitempty" url:"truncate,omitempty"`
	// A non-negative float that tunes the degree of randomness in generation. Lower temperatures mean less random generations. See [Temperature](/temperature-wiki) for more details.
	// Defaults to `0.75`, min value of `0.0`, max value of `5.0`.
	Temperature *float64 `json:"temperature,omitempty" url:"temperature,omitempty"`
	// If specified, the backend will make a best effort to sample tokens deterministically, such that repeated requests with the same seed and parameters should return the same result. However, determinsim cannot be totally guaranteed.
	Seed *float64 `json:"seed,omitempty" url:"seed,omitempty"`
	// Identifier of a custom preset. A preset is a combination of parameters, such as prompt, temperature etc. You can create presets in the [playground](https://dashboard.cohere.ai/playground/generate).
	// When a preset is specified, the `prompt` parameter becomes optional, and any included parameters will override the preset's parameters.
	Preset *string `json:"preset,omitempty" url:"preset,omitempty"`
	// The generated text will be cut at the beginning of the earliest occurrence of an end sequence. The sequence will be excluded from the text.
	EndSequences []string `json:"end_sequences,omitempty" url:"end_sequences,omitempty"`
	// The generated text will be cut at the end of the earliest occurrence of a stop sequence. The sequence will be included the text.
	StopSequences []string `json:"stop_sequences,omitempty" url:"stop_sequences,omitempty"`
	// Ensures only the top `k` most likely tokens are considered for generation at each step.
	// Defaults to `0`, min value of `0`, max value of `500`.
	K *int `json:"k,omitempty" url:"k,omitempty"`
	// Ensures that only the most likely tokens, with total probability mass of `p`, are considered for generation at each step. If both `k` and `p` are enabled, `p` acts after `k`.
	// Defaults to `0.75`. min value of `0.01`, max value of `0.99`.
	P *float64 `json:"p,omitempty" url:"p,omitempty"`
	// Used to reduce repetitiveness of generated tokens. The higher the value, the stronger a penalty is applied to previously present tokens, proportional to how many times they have already appeared in the prompt or prior generation.
	//
	// Using `frequency_penalty` in combination with `presence_penalty` is not supported on newer models.
	FrequencyPenalty *float64 `json:"frequency_penalty,omitempty" url:"frequency_penalty,omitempty"`
	// Defaults to `0.0`, min value of `0.0`, max value of `1.0`.
	//
	// Can be used to reduce repetitiveness of generated tokens. Similar to `frequency_penalty`, except that this penalty is applied equally to all tokens that have already appeared, regardless of their exact frequencies.
	//
	// Using `frequency_penalty` in combination with `presence_penalty` is not supported on newer models.
	PresencePenalty *float64 `json:"presence_penalty,omitempty" url:"presence_penalty,omitempty"`
	// One of `GENERATION|ALL|NONE` to specify how and if the token likelihoods are returned with the response. Defaults to `NONE`.
	//
	// If `GENERATION` is selected, the token likelihoods will only be provided for generated text.
	//
	// If `ALL` is selected, the token likelihoods will be provided both for the prompt and the generated text.
	ReturnLikelihoods *GenerateRequestReturnLikelihoods `json:"return_likelihoods,omitempty" url:"return_likelihoods,omitempty"`
	// When enabled, the user's prompt will be sent to the model without any pre-processing.
	RawPrompting *bool `json:"raw_prompting,omitempty" url:"raw_prompting,omitempty"`
	// contains filtered or unexported fields
}

type GenerateRequestReturnLikelihoods string

type GenerateRequestTruncate string

type GenerateStreamEnd struct {
	IsFinished   bool                       `json:"is_finished" url:"is_finished"`
	FinishReason *FinishReason              `json:"finish_reason,omitempty" url:"finish_reason,omitempty"`
	Response     *GenerateStreamEndResponse `json:"response,omitempty" url:"response,omitempty"`
	// contains filtered or unexported fields
}

type GenerateStreamEndResponse struct {
	Id          string                      `json:"id" url:"id"`
	Prompt      *string                     `json:"prompt,omitempty" url:"prompt,omitempty"`
	Generations []*SingleGenerationInStream `json:"generations,omitempty" url:"generations,omitempty"`
	// contains filtered or unexported fields
}

type GenerateStreamError struct {
	// Refers to the nth generation. Only present when `num_generations` is greater than zero.
	Index        *int         `json:"index,omitempty" url:"index,omitempty"`
	IsFinished   bool         `json:"is_finished" url:"is_finished"`
	FinishReason FinishReason `json:"finish_reason" url:"finish_reason"`
	// Error message
	Err string `json:"err" url:"err"`
	// contains filtered or unexported fields
}

type GenerateStreamEvent struct {
	// contains filtered or unexported fields
}

type GenerateStreamRequest struct {
	// The input text that serves as the starting point for generating the response.
	// Note: The prompt will be pre-processed and modified before reaching the model.
	Prompt string `json:"prompt" url:"prompt"`
	// The identifier of the model to generate with. Currently available models are `command` (default), `command-nightly` (experimental), `command-light`, and `command-light-nightly` (experimental).
	// Smaller, "light" models are faster, while larger models will perform better. [Custom models](/docs/training-custom-models) can also be supplied with their full ID.
	Model *string `json:"model,omitempty" url:"model,omitempty"`
	// The maximum number of generations that will be returned. Defaults to `1`, min value of `1`, max value of `5`.
	NumGenerations *int `json:"num_generations,omitempty" url:"num_generations,omitempty"`
	// The maximum number of tokens the model will generate as part of the response. Note: Setting a low value may result in incomplete generations.
	//
	// This parameter is off by default, and if it's not specified, the model will continue generating until it emits an EOS completion token. See [BPE Tokens](/bpe-tokens-wiki) for more details.
	//
	// Can only be set to `0` if `return_likelihoods` is set to `ALL` to get the likelihood of the prompt.
	MaxTokens *int `json:"max_tokens,omitempty" url:"max_tokens,omitempty"`
	// One of `NONE|START|END` to specify how the API will handle inputs longer than the maximum token length.
	//
	// Passing `START` will discard the start of the input. `END` will discard the end of the input. In both cases, input is discarded until the remaining input is exactly the maximum input token length for the model.
	//
	// If `NONE` is selected, when the input exceeds the maximum input token length an error will be returned.
	Truncate *GenerateStreamRequestTruncate `json:"truncate,omitempty" url:"truncate,omitempty"`
	// A non-negative float that tunes the degree of randomness in generation. Lower temperatures mean less random generations. See [Temperature](/temperature-wiki) for more details.
	// Defaults to `0.75`, min value of `0.0`, max value of `5.0`.
	Temperature *float64 `json:"temperature,omitempty" url:"temperature,omitempty"`
	// If specified, the backend will make a best effort to sample tokens deterministically, such that repeated requests with the same seed and parameters should return the same result. However, determinsim cannot be totally guaranteed.
	Seed *float64 `json:"seed,omitempty" url:"seed,omitempty"`
	// Identifier of a custom preset. A preset is a combination of parameters, such as prompt, temperature etc. You can create presets in the [playground](https://dashboard.cohere.ai/playground/generate).
	// When a preset is specified, the `prompt` parameter becomes optional, and any included parameters will override the preset's parameters.
	Preset *string `json:"preset,omitempty" url:"preset,omitempty"`
	// The generated text will be cut at the beginning of the earliest occurrence of an end sequence. The sequence will be excluded from the text.
	EndSequences []string `json:"end_sequences,omitempty" url:"end_sequences,omitempty"`
	// The generated text will be cut at the end of the earliest occurrence of a stop sequence. The sequence will be included the text.
	StopSequences []string `json:"stop_sequences,omitempty" url:"stop_sequences,omitempty"`
	// Ensures only the top `k` most likely tokens are considered for generation at each step.
	// Defaults to `0`, min value of `0`, max value of `500`.
	K *int `json:"k,omitempty" url:"k,omitempty"`
	// Ensures that only the most likely tokens, with total probability mass of `p`, are considered for generation at each step. If both `k` and `p` are enabled, `p` acts after `k`.
	// Defaults to `0.75`. min value of `0.01`, max value of `0.99`.
	P *float64 `json:"p,omitempty" url:"p,omitempty"`
	// Used to reduce repetitiveness of generated tokens. The higher the value, the stronger a penalty is applied to previously present tokens, proportional to how many times they have already appeared in the prompt or prior generation.
	//
	// Using `frequency_penalty` in combination with `presence_penalty` is not supported on newer models.
	FrequencyPenalty *float64 `json:"frequency_penalty,omitempty" url:"frequency_penalty,omitempty"`
	// Defaults to `0.0`, min value of `0.0`, max value of `1.0`.
	//
	// Can be used to reduce repetitiveness of generated tokens. Similar to `frequency_penalty`, except that this penalty is applied equally to all tokens that have already appeared, regardless of their exact frequencies.
	//
	// Using `frequency_penalty` in combination with `presence_penalty` is not supported on newer models.
	PresencePenalty *float64 `json:"presence_penalty,omitempty" url:"presence_penalty,omitempty"`
	// One of `GENERATION|ALL|NONE` to specify how and if the token likelihoods are returned with the response. Defaults to `NONE`.
	//
	// If `GENERATION` is selected, the token likelihoods will only be provided for generated text.
	//
	// If `ALL` is selected, the token likelihoods will be provided both for the prompt and the generated text.
	ReturnLikelihoods *GenerateStreamRequestReturnLikelihoods `json:"return_likelihoods,omitempty" url:"return_likelihoods,omitempty"`
	// When enabled, the user's prompt will be sent to the model without any pre-processing.
	RawPrompting *bool `json:"raw_prompting,omitempty" url:"raw_prompting,omitempty"`
	// contains filtered or unexported fields
}

type GenerateStreamRequestReturnLikelihoods string

type GenerateStreamRequestTruncate string

type GenerateStreamText struct {
	// A segment of text of the generation.
	Text string `json:"text" url:"text"`
	// Refers to the nth generation. Only present when `num_generations` is greater than zero, and only when text responses are being streamed.
	Index      *int `json:"index,omitempty" url:"index,omitempty"`
	IsFinished bool `json:"is_finished" url:"is_finished"`
	// contains filtered or unexported fields
}

type GenerateStreamedResponse struct {
	EventType      string
	TextGeneration *GenerateStreamText
	StreamEnd      *GenerateStreamEnd
	StreamError    *GenerateStreamError
}

type GenerateStreamedResponseVisitor interface {
	VisitTextGeneration(*GenerateStreamText) error
	VisitStreamEnd(*GenerateStreamEnd) error
	VisitStreamError(*GenerateStreamError) error
}

type Generation struct {
	Id string `json:"id" url:"id"`
	// Prompt used for generations.
	Prompt *string `json:"prompt,omitempty" url:"prompt,omitempty"`
	// List of generated results
	Generations []*SingleGeneration `json:"generations,omitempty" url:"generations,omitempty"`
	Meta        *ApiMeta            `json:"meta,omitempty" url:"meta,omitempty"`
	// contains filtered or unexported fields
}

type GetConnectorResponse struct {
	Connector *Connector `json:"connector,omitempty" url:"connector,omitempty"`
	// contains filtered or unexported fields
}

type GetModelResponse struct {
	// Specify this name in the `model` parameter of API requests to use your chosen model.
	Name *string `json:"name,omitempty" url:"name,omitempty"`
	// The API endpoints that the model is compatible with.
	Endpoints []CompatibleEndpoint `json:"endpoints,omitempty" url:"endpoints,omitempty"`
	// Whether the model has been fine-tuned or not.
	Finetuned *bool `json:"finetuned,omitempty" url:"finetuned,omitempty"`
	// The maximum number of tokens that the model can process in a single request. Note that not all of these tokens are always available due to special tokens and preambles that Cohere has added by default.
	ContextLength *float64 `json:"context_length,omitempty" url:"context_length,omitempty"`
	// Public URL to the tokenizer's configuration file.
	TokenizerUrl *string `json:"tokenizer_url,omitempty" url:"tokenizer_url,omitempty"`
	// The API endpoints that the model is default to.
	DefaultEndpoints []CompatibleEndpoint `json:"default_endpoints,omitempty" url:"default_endpoints,omitempty"`
	// contains filtered or unexported fields
}

type InternalServerError struct {
	*core.APIError
	Body interface{}
}

type LabelMetric struct {
	// Total number of examples for this label
	TotalExamples *string `json:"total_examples,omitempty" url:"total_examples,omitempty"`
	// value of the label
	Label *string `json:"label,omitempty" url:"label,omitempty"`
	// samples for this label
	Samples []string `json:"samples,omitempty" url:"samples,omitempty"`
	// contains filtered or unexported fields
}

type ListConnectorsResponse struct {
	Connectors []*Connector `json:"connectors,omitempty" url:"connectors,omitempty"`
	// Total number of connectors.
	TotalCount *float64 `json:"total_count,omitempty" url:"total_count,omitempty"`
	// contains filtered or unexported fields
}

type ListEmbedJobResponse struct {
	EmbedJobs []*EmbedJob `json:"embed_jobs,omitempty" url:"embed_jobs,omitempty"`
	// contains filtered or unexported fields
}

type ListModelsResponse struct {
	Models []*GetModelResponse `json:"models,omitempty" url:"models,omitempty"`
	// A token to retrieve the next page of results. Provide in the page_token parameter of the next request.
	NextPageToken *string `json:"next_page_token,omitempty" url:"next_page_token,omitempty"`
	// contains filtered or unexported fields
}

type Metrics struct {
	FinetuneDatasetMetrics *FinetuneDatasetMetrics `json:"finetune_dataset_metrics,omitempty" url:"finetune_dataset_metrics,omitempty"`
	EmbedData              *MetricsEmbedData       `json:"embed_data,omitempty" url:"embed_data,omitempty"`
	// contains filtered or unexported fields
}

type MetricsEmbedData struct {
	// the fields in the dataset
	Fields []*MetricsEmbedDataFieldsItem `json:"fields,omitempty" url:"fields,omitempty"`
	// contains filtered or unexported fields
}

type MetricsEmbedDataFieldsItem struct {
	// the name of the field
	Name *string `json:"name,omitempty" url:"name,omitempty"`
	// the number of times the field appears in the dataset
	Count *float64 `json:"count,omitempty" url:"count,omitempty"`
	// contains filtered or unexported fields
}

type ModelsListRequest struct {
	// Maximum number of models to include in a page
	// Defaults to `20`, min value of `1`, max value of `1000`.
	PageSize *float64 `json:"-" url:"page_size,omitempty"`
	// Page token provided in the `next_page_token` field of a previous response.
	PageToken *string `json:"-" url:"page_token,omitempty"`
	// When provided, filters the list of models to only those that are compatible with the specified endpoint.
	Endpoint *CompatibleEndpoint `json:"-" url:"endpoint,omitempty"`
	// When provided, filters the list of models to only the default model to the endpoint. This parameter is only valid when `endpoint` is provided.
	DefaultOnly *bool `json:"-" url:"default_only,omitempty"`
}

type NonStreamedChatResponse struct {
	// Contents of the reply generated by the model.
	Text string `json:"text" url:"text"`
	// Unique identifier for the generated reply. Useful for submitting feedback.
	GenerationId *string `json:"generation_id,omitempty" url:"generation_id,omitempty"`
	// Inline citations for the generated reply.
	Citations []*ChatCitation `json:"citations,omitempty" url:"citations,omitempty"`
	// Documents seen by the model when generating the reply.
	Documents []ChatDocument `json:"documents,omitempty" url:"documents,omitempty"`
	// Denotes that a search for documents is required during the RAG flow.
	IsSearchRequired *bool `json:"is_search_required,omitempty" url:"is_search_required,omitempty"`
	// Generated search queries, meant to be used as part of the RAG flow.
	SearchQueries []*ChatSearchQuery `json:"search_queries,omitempty" url:"search_queries,omitempty"`
	// Documents retrieved from each of the conducted searches.
	SearchResults []*ChatSearchResult `json:"search_results,omitempty" url:"search_results,omitempty"`
	FinishReason  *FinishReason       `json:"finish_reason,omitempty" url:"finish_reason,omitempty"`
	ToolCalls     []*ToolCall         `json:"tool_calls,omitempty" url:"tool_calls,omitempty"`
	// A list of previous messages between the user and the model, meant to give the model conversational context for responding to the user's `message`.
	ChatHistory []*ChatMessage `json:"chat_history,omitempty" url:"chat_history,omitempty"`
	// The prompt that was used. Only present when `return_prompt` in the request is set to true.
	Prompt *string  `json:"prompt,omitempty" url:"prompt,omitempty"`
	Meta   *ApiMeta `json:"meta,omitempty" url:"meta,omitempty"`
	// contains filtered or unexported fields
}

type NotFoundError struct {
	*core.APIError
	Body interface{}
}

type OAuthAuthorizeResponse struct {
	// The OAuth 2.0 redirect url. Redirect the user to this url to authorize the connector.
	RedirectUrl *string `json:"redirect_url,omitempty" url:"redirect_url,omitempty"`
	// contains filtered or unexported fields
}

type ParseInfo struct {
	Separator *string `json:"separator,omitempty" url:"separator,omitempty"`
	Delimiter *string `json:"delimiter,omitempty" url:"delimiter,omitempty"`
	// contains filtered or unexported fields
}

type RerankRequest struct {
	// The identifier of the model to use, one of : `rerank-english-v3.0`, `rerank-multilingual-v3.0`, `rerank-english-v2.0`, `rerank-multilingual-v2.0`
	Model *string `json:"model,omitempty" url:"model,omitempty"`
	// The search query
	Query string `json:"query" url:"query"`
	// A list of document objects or strings to rerank.
	// If a document is provided the text fields is required and all other fields will be preserved in the response.
	//
	// The total max chunks (length of documents * max_chunks_per_doc) must be less than 10000.
	//
	// We recommend a maximum of 1,000 documents for optimal endpoint performance.
	Documents []*RerankRequestDocumentsItem `json:"documents,omitempty" url:"documents,omitempty"`
	// The number of most relevant documents or indices to return, defaults to the length of the documents
	TopN *int `json:"top_n,omitempty" url:"top_n,omitempty"`
	// If a JSON object is provided, you can specify which keys you would like to have considered for reranking. The model will rerank based on order of the fields passed in (i.e. rank_fields=['title','author','text'] will rerank using the values in title, author, text  sequentially. If the length of title, author, and text exceeds the context length of the model, the chunking will not re-consider earlier fields). If not provided, the model will use the default text field for ranking.
	RankFields []string `json:"rank_fields,omitempty" url:"rank_fields,omitempty"`
	// - If false, returns results without the doc text - the api will return a list of {index, relevance score} where index is inferred from the list passed into the request.
	// - If true, returns results with the doc text passed in - the api will return an ordered list of {index, text, relevance score} where index + text refers to the list passed into the request.
	ReturnDocuments *bool `json:"return_documents,omitempty" url:"return_documents,omitempty"`
	// The maximum number of chunks to produce internally from a document
	MaxChunksPerDoc *int `json:"max_chunks_per_doc,omitempty" url:"max_chunks_per_doc,omitempty"`
}

type RerankRequestDocumentsItem struct {
	String                         string
	RerankRequestDocumentsItemText *RerankRequestDocumentsItemText
}

type RerankRequestDocumentsItemText struct {
	// The text of the document to rerank.
	Text string `json:"text" url:"text"`
	// contains filtered or unexported fields
}

type RerankRequestDocumentsItemVisitor interface {
	VisitString(string) error
	VisitRerankRequestDocumentsItemText(*RerankRequestDocumentsItemText) error
}

type RerankResponse struct {
	Id *string `json:"id,omitempty" url:"id,omitempty"`
	// An ordered list of ranked documents
	Results []*RerankResponseResultsItem `json:"results,omitempty" url:"results,omitempty"`
	Meta    *ApiMeta                     `json:"meta,omitempty" url:"meta,omitempty"`
	// contains filtered or unexported fields
}

type RerankResponseResultsItem struct {
	// If `return_documents` is set as `false` this will return none, if `true` it will return the documents passed in
	Document *RerankResponseResultsItemDocument `json:"document,omitempty" url:"document,omitempty"`
	// Corresponds to the index in the original list of documents to which the ranked document belongs. (i.e. if the first value in the `results` object has an `index` value of 3, it means in the list of documents passed in, the document at `index=3` had the highest relevance)
	Index int `json:"index" url:"index"`
	// Relevance scores are normalized to be in the range `[0, 1]`. Scores close to `1` indicate a high relevance to the query, and scores closer to `0` indicate low relevance. It is not accurate to assume a score of 0.9 means the document is 2x more relevant than a document with a score of 0.45
	RelevanceScore float64 `json:"relevance_score" url:"relevance_score"`
	// contains filtered or unexported fields
}

type RerankResponseResultsItemDocument struct {
	// The text of the document to rerank
	Text string `json:"text" url:"text"`
	// contains filtered or unexported fields
}

type RerankerDataMetrics struct {
	// The number of training queries.
	NumTrainQueries *string `json:"num_train_queries,omitempty" url:"num_train_queries,omitempty"`
	// The sum of all relevant passages of valid training examples.
	NumTrainRelevantPassages *string `json:"num_train_relevant_passages,omitempty" url:"num_train_relevant_passages,omitempty"`
	// The sum of all hard negatives of valid training examples.
	NumTrainHardNegatives *string `json:"num_train_hard_negatives,omitempty" url:"num_train_hard_negatives,omitempty"`
	// The number of evaluation queries.
	NumEvalQueries *string `json:"num_eval_queries,omitempty" url:"num_eval_queries,omitempty"`
	// The sum of all relevant passages of valid eval examples.
	NumEvalRelevantPassages *string `json:"num_eval_relevant_passages,omitempty" url:"num_eval_relevant_passages,omitempty"`
	// The sum of all hard negatives of valid eval examples.
	NumEvalHardNegatives *string `json:"num_eval_hard_negatives,omitempty" url:"num_eval_hard_negatives,omitempty"`
	// contains filtered or unexported fields
}

type ServiceUnavailableError struct {
	*core.APIError
	Body *finetuning.Error
}

type SingleGeneration struct {
	Id   string `json:"id" url:"id"`
	Text string `json:"text" url:"text"`
	// Refers to the nth generation. Only present when `num_generations` is greater than zero.
	Index      *int     `json:"index,omitempty" url:"index,omitempty"`
	Likelihood *float64 `json:"likelihood,omitempty" url:"likelihood,omitempty"`
	// Only returned if `return_likelihoods` is set to `GENERATION` or `ALL`. The likelihood refers to the average log-likelihood of the entire specified string, which is useful for [evaluating the performance of your model](likelihood-eval), especially if you've created a [custom model](/docs/training-custom-models). Individual token likelihoods provide the log-likelihood of each token. The first token will not have a likelihood.
	TokenLikelihoods []*SingleGenerationTokenLikelihoodsItem `json:"token_likelihoods,omitempty" url:"token_likelihoods,omitempty"`
	// contains filtered or unexported fields
}

type SingleGenerationInStream struct {
	Id string `json:"id" url:"id"`
	// Full text of the generation.
	Text string `json:"text" url:"text"`
	// Refers to the nth generation. Only present when `num_generations` is greater than zero.
	Index        *int         `json:"index,omitempty" url:"index,omitempty"`
	FinishReason FinishReason `json:"finish_reason" url:"finish_reason"`
	// contains filtered or unexported fields
}

type SingleGenerationTokenLikelihoodsItem struct {
	Token      string  `json:"token" url:"token"`
	Likelihood float64 `json:"likelihood" url:"likelihood"`
	// contains filtered or unexported fields
}

type StreamedChatResponse struct {
	EventType               string
	StreamStart             *ChatStreamStartEvent
	SearchQueriesGeneration *ChatSearchQueriesGenerationEvent
	SearchResults           *ChatSearchResultsEvent
	TextGeneration          *ChatTextGenerationEvent
	CitationGeneration      *ChatCitationGenerationEvent
	ToolCallsGeneration     *ChatToolCallsGenerationEvent
	StreamEnd               *ChatStreamEndEvent
}

type StreamedChatResponseVisitor interface {
	VisitStreamStart(*ChatStreamStartEvent) error
	VisitSearchQueriesGeneration(*ChatSearchQueriesGenerationEvent) error
	VisitSearchResults(*ChatSearchResultsEvent) error
	VisitTextGeneration(*ChatTextGenerationEvent) error
	VisitCitationGeneration(*ChatCitationGenerationEvent) error
	VisitToolCallsGeneration(*ChatToolCallsGenerationEvent) error
	VisitStreamEnd(*ChatStreamEndEvent) error
}

type SummarizeRequest struct {
	// The text to generate a summary for. Can be up to 100,000 characters long. Currently the only supported language is English.
	Text string `json:"text" url:"text"`
	// One of `short`, `medium`, `long`, or `auto` defaults to `auto`. Indicates the approximate length of the summary. If `auto` is selected, the best option will be picked based on the input text.
	Length *SummarizeRequestLength `json:"length,omitempty" url:"length,omitempty"`
	// One of `paragraph`, `bullets`, or `auto`, defaults to `auto`. Indicates the style in which the summary will be delivered - in a free form paragraph or in bullet points. If `auto` is selected, the best option will be picked based on the input text.
	Format *SummarizeRequestFormat `json:"format,omitempty" url:"format,omitempty"`
	// The identifier of the model to generate the summary with. Currently available models are `command` (default), `command-nightly` (experimental), `command-light`, and `command-light-nightly` (experimental). Smaller, "light" models are faster, while larger models will perform better.
	Model *string `json:"model,omitempty" url:"model,omitempty"`
	// One of `low`, `medium`, `high`, or `auto`, defaults to `auto`. Controls how close to the original text the summary is. `high` extractiveness summaries will lean towards reusing sentences verbatim, while `low` extractiveness summaries will tend to paraphrase more. If `auto` is selected, the best option will be picked based on the input text.
	Extractiveness *SummarizeRequestExtractiveness `json:"extractiveness,omitempty" url:"extractiveness,omitempty"`
	// Ranges from 0 to 5. Controls the randomness of the output. Lower values tend to generate more “predictable” output, while higher values tend to generate more “creative” output. The sweet spot is typically between 0 and 1.
	Temperature *float64 `json:"temperature,omitempty" url:"temperature,omitempty"`
	// A free-form instruction for modifying how the summaries get generated. Should complete the sentence "Generate a summary _". Eg. "focusing on the next steps" or "written by Yoda"
	AdditionalCommand *string `json:"additional_command,omitempty" url:"additional_command,omitempty"`
}

type SummarizeRequestExtractiveness string

type SummarizeRequestFormat string

type SummarizeRequestLength string

type SummarizeResponse struct {
	// Generated ID for the summary
	Id *string `json:"id,omitempty" url:"id,omitempty"`
	// Generated summary for the text
	Summary *string  `json:"summary,omitempty" url:"summary,omitempty"`
	Meta    *ApiMeta `json:"meta,omitempty" url:"meta,omitempty"`
	// contains filtered or unexported fields
}

type TokenizeRequest struct {
	// The string to be tokenized, the minimum text length is 1 character, and the maximum text length is 65536 characters.
	Text string `json:"text" url:"text"`
	// An optional parameter to provide the model name. This will ensure that the tokenization uses the tokenizer used by that model.
	Model string `json:"model" url:"model"`
}

type TokenizeResponse struct {
	// An array of tokens, where each token is an integer.
	Tokens       []int    `json:"tokens,omitempty" url:"tokens,omitempty"`
	TokenStrings []string `json:"token_strings,omitempty" url:"token_strings,omitempty"`
	Meta         *ApiMeta `json:"meta,omitempty" url:"meta,omitempty"`
	// contains filtered or unexported fields
}

type TooManyRequestsError struct {
	*core.APIError
	Body *TooManyRequestsErrorBody
}

type TooManyRequestsErrorBody struct {
	Data *string `json:"data,omitempty" url:"data,omitempty"`
	// contains filtered or unexported fields
}

type Tool struct {
	// The name of the tool to be called. Valid names contain only the characters `a-z`, `A-Z`, `0-9`, `_` and must not begin with a digit.
	Name string `json:"name" url:"name"`
	// The description of what the tool does, the model uses the description to choose when and how to call the function.
	Description string `json:"description" url:"description"`
	// The input parameters of the tool. Accepts a dictionary where the key is the name of the parameter and the value is the parameter spec. Valid parameter names contain only the characters `a-z`, `A-Z`, `0-9`, `_` and must not begin with a digit.
	//
	// “`
	//
	//	{
	//	  "my_param": {
	//	    "description": <string>,
	//	    "type": <string>, // any python data type, such as 'str', 'bool'
	//	    "required": <boolean>
	//	  }
	//	}
	//
	// “`
	ParameterDefinitions map[string]*ToolParameterDefinitionsValue `json:"parameter_definitions,omitempty" url:"parameter_definitions,omitempty"`
	// contains filtered or unexported fields
}

type ToolCall struct {
	// Name of the tool to call.
	Name string `json:"name" url:"name"`
	// The name and value of the parameters to use when invoking a tool.
	Parameters map[string]interface{} `json:"parameters,omitempty" url:"parameters,omitempty"`
	// contains filtered or unexported fields
}

type ToolParameterDefinitionsValue struct {
	// The description of the parameter.
	Description *string `json:"description,omitempty" url:"description,omitempty"`
	// The type of the parameter. Must be a valid Python type.
	Type string `json:"type" url:"type"`
	// Denotes whether the parameter is always present (required) or not. Defaults to not required.
	Required *bool `json:"required,omitempty" url:"required,omitempty"`
	// contains filtered or unexported fields
}