openapi: 3.0.0 info: title: Salesforce LLM Open Connector API description: >- The LLM Open Connector API allows Salesforce customers and partners to provide access to LLMs in a standard way so that they can be consumed by the Einstein 1 platform. This API is based on OpenAI's API with significant modifications to accommodate Salesforce use cases. version: v1 termsOfService: '' contact: name: Einstein Foundations url: https://www.salesforce.com/artificial-intelligence/ license: name: MIT url: >- https://github.com/salesforce/generic-llm-connector-openapi/blob/master/LICENSE servers: - url: https://bring-your-own-llm.example.com tags: - name: Chat description: >- Given a list of messages comprising a conversation, the model will return a response. paths: /chat/completions: post: operationId: createChatCompletion tags: - Chat summary: Creates a model response for the given chat conversation. security: - ApiKeyAuth: [] requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CreateChatCompletionRequest' responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/CreateChatCompletionResponse' components: securitySchemes: ApiKeyAuth: type: apiKey in: header name: api-key description: API key required to access the API, passed in the header. schemas: Error: type: object properties: code: type: string nullable: true message: type: string nullable: false param: type: string nullable: true type: type: string nullable: false required: - type - message - param - code ErrorResponse: type: object properties: error: $ref: '#/components/schemas/Error' required: - error CompletionUsage: type: object description: Usage statistics for the completion request. properties: completion_tokens: type: integer description: Number of tokens in the generated completion. prompt_tokens: type: integer description: Number of tokens in the prompt. total_tokens: type: integer description: Total number of tokens used in the request (prompt + completion). required: - prompt_tokens - completion_tokens - total_tokens CreateChatCompletionRequest: type: object properties: messages: description: A list of messages comprising the conversation so far. type: array minItems: 1 items: $ref: '#/components/schemas/ChatCompletionRequestMessage' model: description: ID of the model to use. example: gpt-4-turbo type: string max_tokens: description: > The maximum number of [tokens](/tokenizer) that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length. type: integer nullable: true 'n': type: integer minimum: 1 maximum: 128 default: 1 example: 1 nullable: true description: >- How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs. temperature: type: number minimum: 0 maximum: 2 default: 1 example: 1 nullable: true description: >- What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. parameters: description: >- Dictionary of any other parameters that are required by the provider. Values are passed as is to the provider so that the request can include parameters that are unique to a provider. type: object additionalProperties: true example: top_p: 0.5 required: - model - messages CreateChatCompletionResponse: type: object description: >- Represents a chat completion response returned by model, based on the provided input. properties: id: type: string description: A unique identifier for the chat completion. choices: type: array description: >- A list of chat completion choices. Can be more than one if `n` is greater than 1. items: type: object required: - finish_reason - index - message properties: finish_reason: type: string description: > The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function. enum: - stop - length - tool_calls - content_filter - function_call index: type: integer description: The index of the choice in the list of choices. message: $ref: '#/components/schemas/ChatCompletionResponseMessage' created: type: integer description: >- The Unix timestamp (in seconds) of when the chat completion was created. Model endpoints that pass timestamps in milliseconds must be converted to seconds. model: type: string description: The model used for the chat completion. object: type: string description: The object type, which is always `chat.completion`. enum: - chat.completion usage: $ref: '#/components/schemas/CompletionUsage' required: - choices - created - id - model - object ChatCompletionRequestMessage: type: object title: Chat Completion Message properties: content: description: The contents of the message. type: string role: type: string enum: - system - user - assistant description: The role of the messages author. name: type: string description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. required: - content - role ChatCompletionResponseMessage: type: object title: A chat completion message generated by the model. properties: content: type: string description: The contents of the message. nullable: true role: type: string enum: - assistant description: The role of the author of this message. required: - role - content