basePath: / definitions: config.Gallery: properties: name: type: string url: type: string type: object functions.Function: properties: description: type: string name: type: string parameters: additionalProperties: true type: object strict: type: boolean type: object functions.Item: properties: properties: additionalProperties: true type: object type: type: string type: object functions.JSONFunctionStructure: properties: $defs: additionalProperties: true type: object anyOf: items: $ref: '#/definitions/functions.Item' type: array oneOf: items: $ref: '#/definitions/functions.Item' type: array type: object functions.Tool: properties: function: $ref: '#/definitions/functions.Function' type: type: string type: object gallery.File: properties: filename: type: string sha256: type: string uri: type: string type: object gallery.GalleryModel: properties: config_file: additionalProperties: true description: config_file is read in the situation where URL is blank - and therefore this is a base config. type: object description: type: string files: description: AdditionalFiles are used to add additional files to the model items: $ref: '#/definitions/gallery.File' type: array gallery: allOf: - $ref: '#/definitions/config.Gallery' description: Gallery is a reference to the gallery which contains the model icon: type: string installed: description: Installed is used to indicate if the model is installed or not type: boolean license: type: string name: type: string overrides: additionalProperties: true description: Overrides are used to override the configuration of the model located at URL type: object tags: items: type: string type: array url: type: string urls: items: type: string type: array type: object gallery.GalleryOpStatus: properties: deletion: description: Deletion is true if the operation is a deletion type: boolean downloaded_size: type: string error: {} file_name: type: string file_size: type: string gallery_model_name: type: string message: type: string processed: type: boolean progress: type: number type: object localai.GalleryModel: properties: config_file: additionalProperties: true description: config_file is read in the situation where URL is blank - and therefore this is a base config. type: object config_url: type: string description: type: string files: description: AdditionalFiles are used to add additional files to the model items: $ref: '#/definitions/gallery.File' type: array gallery: allOf: - $ref: '#/definitions/config.Gallery' description: Gallery is a reference to the gallery which contains the model icon: type: string id: type: string installed: description: Installed is used to indicate if the model is installed or not type: boolean license: type: string name: type: string overrides: additionalProperties: true description: Overrides are used to override the configuration of the model located at URL type: object tags: items: type: string type: array url: type: string urls: items: type: string type: array type: object openai.Assistant: properties: created: description: The time at which the assistant was created. type: integer description: description: The description of the assistant. type: string file_ids: description: A list of file IDs attached to this assistant. items: type: string type: array id: description: The unique identifier of the assistant. type: string instructions: description: The system instructions that the assistant uses. type: string metadata: additionalProperties: type: string description: Set of key-value pairs attached to the assistant. type: object model: description: The model ID used by the assistant. type: string name: description: The name of the assistant. type: string object: description: Object type, which is "assistant". type: string tools: description: A list of tools enabled on the assistant. items: $ref: '#/definitions/openai.Tool' type: array type: object openai.AssistantRequest: properties: description: type: string file_ids: items: type: string type: array instructions: type: string metadata: additionalProperties: type: string type: object model: type: string name: type: string tools: items: $ref: '#/definitions/openai.Tool' type: array type: object openai.DeleteStatus: properties: deleted: type: boolean id: type: string object: type: string type: object openai.Tool: properties: type: $ref: '#/definitions/openai.ToolType' type: object openai.ToolType: enum: - code_interpreter - retrieval - function type: string x-enum-varnames: - CodeInterpreter - Retrieval - Function p2p.NodeData: properties: id: type: string lastSeen: type: string name: type: string tunnelAddress: type: string type: object proto.MemoryUsageData: properties: breakdown: additionalProperties: type: integer type: object total: type: integer type: object proto.StatusResponse: properties: memory: $ref: '#/definitions/proto.MemoryUsageData' state: $ref: '#/definitions/proto.StatusResponse_State' type: object proto.StatusResponse_State: enum: - 0 - 1 - 2 - -1 type: integer x-enum-varnames: - StatusResponse_UNINITIALIZED - StatusResponse_BUSY - StatusResponse_READY - StatusResponse_ERROR schema.BackendMonitorRequest: properties: model: type: string type: object schema.Choice: properties: delta: $ref: '#/definitions/schema.Message' finish_reason: type: string index: type: integer message: $ref: '#/definitions/schema.Message' text: type: string type: object schema.DeleteAssistantResponse: properties: deleted: type: boolean id: type: string object: type: string type: object schema.File: properties: bytes: description: Size of the file in bytes type: integer created_at: description: The time at which the file was created type: string filename: description: The name of the file type: string id: description: Unique identifier for the file type: string object: description: Type of the object (e.g., "file") type: string purpose: description: The purpose of the file (e.g., "fine-tune", "classifications", etc.) type: string type: object schema.FunctionCall: properties: arguments: type: string name: type: string type: object schema.GalleryResponse: properties: status: type: string uuid: type: string type: object schema.Item: properties: b64_json: type: string embedding: items: type: number type: array index: type: integer object: type: string url: description: Images type: string type: object schema.JINADocumentResult: properties: document: $ref: '#/definitions/schema.JINAText' index: type: integer relevance_score: type: number type: object schema.JINARerankRequest: properties: documents: items: type: string type: array model: type: string query: type: string top_n: type: integer type: object schema.JINARerankResponse: properties: model: type: string results: items: $ref: '#/definitions/schema.JINADocumentResult' type: array usage: $ref: '#/definitions/schema.JINAUsageInfo' type: object schema.JINAText: properties: text: type: string type: object schema.JINAUsageInfo: properties: prompt_tokens: type: integer total_tokens: type: integer type: object schema.ListFiles: properties: data: items: $ref: '#/definitions/schema.File' type: array object: type: string type: object schema.Message: properties: content: description: The message content function_call: description: A result of a function call name: description: The message name (used for tools calls) type: string role: description: The message role type: string string_content: type: string string_images: items: type: string type: array tool_calls: items: $ref: '#/definitions/schema.ToolCall' type: array type: object schema.ModelsDataResponse: properties: data: items: $ref: '#/definitions/schema.OpenAIModel' type: array object: type: string type: object schema.OpenAIModel: properties: id: type: string object: type: string type: object schema.OpenAIRequest: properties: backend: type: string batch: description: Custom parameters - not present in the OpenAI API type: integer clip_skip: description: Diffusers type: integer echo: type: boolean file: description: whisper type: string frequency_penalty: type: number function_call: description: might be a string or an object functions: description: A list of available functions to call items: $ref: '#/definitions/functions.Function' type: array grammar: description: A grammar to constrain the LLM output type: string grammar_json_functions: $ref: '#/definitions/functions.JSONFunctionStructure' ignore_eos: type: boolean input: {} instruction: description: Edit endpoint type: string language: description: Also part of the OpenAI official spec type: string max_tokens: type: integer messages: description: Messages is read only by chat/completion API calls items: $ref: '#/definitions/schema.Message' type: array mode: description: Image (not supported by OpenAI) type: integer model: description: Also part of the OpenAI official spec type: string model_base_name: description: AutoGPTQ type: string "n": description: Also part of the OpenAI official spec. use it for returning multiple results type: integer n_keep: type: integer negative_prompt: type: string negative_prompt_scale: type: number presence_penalty: type: number prompt: description: Prompt is read only by completion/image API calls repeat_last_n: type: integer repeat_penalty: type: number response_format: description: whisper/image rope_freq_base: type: number rope_freq_scale: type: number seed: type: integer size: description: image type: string step: type: integer stop: {} stream: type: boolean temperature: type: number tfz: type: number tokenizer: description: RWKV (?) type: string tool_choice: {} tools: items: $ref: '#/definitions/functions.Tool' type: array top_k: type: integer top_p: description: Common options between all the API calls, part of the OpenAI spec type: number translate: description: Only for audio transcription type: boolean typical_p: type: number use_fast_tokenizer: description: AutoGPTQ type: boolean required: - file type: object schema.OpenAIResponse: properties: choices: items: $ref: '#/definitions/schema.Choice' type: array created: type: integer data: items: $ref: '#/definitions/schema.Item' type: array id: type: string model: type: string object: type: string usage: $ref: '#/definitions/schema.OpenAIUsage' type: object schema.OpenAIUsage: properties: completion_tokens: type: integer prompt_tokens: type: integer total_tokens: type: integer type: object schema.P2PNodesResponse: properties: federated_nodes: items: $ref: '#/definitions/p2p.NodeData' type: array nodes: items: $ref: '#/definitions/p2p.NodeData' type: array type: object schema.TTSRequest: description: TTS request body properties: backend: type: string input: description: text input type: string language: description: (optional) language to use with TTS model type: string model: description: model name or full path type: string voice: description: voice audio file or speaker id type: string type: object schema.ToolCall: properties: function: $ref: '#/definitions/schema.FunctionCall' id: type: string index: type: integer type: type: string type: object info: contact: name: LocalAI url: https://localai.io description: The LocalAI Rest API. license: name: MIT url: https://raw.githubusercontent.com/mudler/LocalAI/master/LICENSE title: LocalAI API version: 2.0.0 paths: /api/p2p: get: responses: "200": description: Response schema: items: $ref: '#/definitions/schema.P2PNodesResponse' type: array summary: Returns available P2P nodes /api/p2p/token: get: responses: "200": description: Response schema: type: string summary: Show the P2P token /backend/monitor: get: parameters: - description: Backend statistics request in: body name: request required: true schema: $ref: '#/definitions/schema.BackendMonitorRequest' responses: "200": description: Response schema: $ref: '#/definitions/proto.StatusResponse' summary: Backend monitor endpoint /backend/shutdown: post: parameters: - description: Backend statistics request in: body name: request required: true schema: $ref: '#/definitions/schema.BackendMonitorRequest' responses: {} summary: Backend monitor endpoint /metrics: get: parameters: - description: Gallery details in: body name: request required: true schema: $ref: '#/definitions/config.Gallery' responses: {} summary: Prometheus metrics endpoint /models/apply: post: parameters: - description: query params in: body name: request required: true schema: $ref: '#/definitions/localai.GalleryModel' responses: "200": description: Response schema: $ref: '#/definitions/schema.GalleryResponse' summary: Install models to LocalAI. /models/available: get: responses: "200": description: Response schema: items: $ref: '#/definitions/gallery.GalleryModel' type: array summary: List installable models. /models/delete/{name}: post: parameters: - description: Model name in: path name: name required: true type: string responses: "200": description: Response schema: $ref: '#/definitions/schema.GalleryResponse' summary: delete models to LocalAI. /models/galleries: delete: parameters: - description: Gallery details in: body name: request required: true schema: $ref: '#/definitions/config.Gallery' responses: "200": description: Response schema: items: $ref: '#/definitions/config.Gallery' type: array summary: removes a gallery from LocalAI get: responses: "200": description: Response schema: items: $ref: '#/definitions/config.Gallery' type: array summary: List all Galleries post: parameters: - description: Gallery details in: body name: request required: true schema: $ref: '#/definitions/config.Gallery' responses: "200": description: Response schema: items: $ref: '#/definitions/config.Gallery' type: array summary: Adds a gallery in LocalAI /models/jobs: get: responses: "200": description: Response schema: additionalProperties: $ref: '#/definitions/gallery.GalleryOpStatus' type: object summary: Returns all the jobs status progress /models/jobs/{uuid}: get: responses: "200": description: Response schema: $ref: '#/definitions/gallery.GalleryOpStatus' summary: Returns the job status /tts: post: consumes: - application/json parameters: - description: query params in: body name: request required: true schema: $ref: '#/definitions/schema.TTSRequest' produces: - audio/x-wav responses: "200": description: generated audio/wav file schema: type: string summary: Generates audio from the input text. /v1/assistants: get: parameters: - description: Limit the number of assistants returned in: query name: limit type: integer - description: Order of assistants returned in: query name: order type: string - description: Return assistants created after the given ID in: query name: after type: string - description: Return assistants created before the given ID in: query name: before type: string responses: "200": description: Response schema: items: $ref: '#/definitions/openai.Assistant' type: array summary: List available assistents post: parameters: - description: query params in: body name: request required: true schema: $ref: '#/definitions/openai.AssistantRequest' responses: "200": description: Response schema: $ref: '#/definitions/openai.Assistant' summary: Create an assistant with a model and instructions. /v1/assistants/{assistant_id}: delete: responses: "200": description: Response schema: $ref: '#/definitions/schema.DeleteAssistantResponse' summary: Delete assistents get: responses: "200": description: Response schema: $ref: '#/definitions/openai.Assistant' summary: Get assistent data /v1/audio/speech: post: consumes: - application/json parameters: - description: query params in: body name: request required: true schema: $ref: '#/definitions/schema.TTSRequest' produces: - audio/x-wav responses: "200": description: generated audio/wav file schema: type: string summary: Generates audio from the input text. /v1/audio/transcriptions: post: consumes: - multipart/form-data parameters: - description: model in: formData name: model required: true type: string - description: file in: formData name: file required: true type: file responses: "200": description: Response schema: additionalProperties: type: string type: object summary: Transcribes audio into the input language. /v1/chat/completions: post: parameters: - description: query params in: body name: request required: true schema: $ref: '#/definitions/schema.OpenAIRequest' responses: "200": description: Response schema: $ref: '#/definitions/schema.OpenAIResponse' summary: Generate a chat completions for a given prompt and model. /v1/completions: post: parameters: - description: query params in: body name: request required: true schema: $ref: '#/definitions/schema.OpenAIRequest' responses: "200": description: Response schema: $ref: '#/definitions/schema.OpenAIResponse' summary: Generate completions for a given prompt and model. /v1/edits: post: parameters: - description: query params in: body name: request required: true schema: $ref: '#/definitions/schema.OpenAIRequest' responses: "200": description: Response schema: $ref: '#/definitions/schema.OpenAIResponse' summary: OpenAI edit endpoint /v1/embeddings: post: parameters: - description: query params in: body name: request required: true schema: $ref: '#/definitions/schema.OpenAIRequest' responses: "200": description: Response schema: $ref: '#/definitions/schema.OpenAIResponse' summary: Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms. /v1/files: get: responses: "200": description: Response schema: $ref: '#/definitions/schema.ListFiles' summary: List files. /v1/files/{file_id}: delete: responses: "200": description: Response schema: $ref: '#/definitions/openai.DeleteStatus' summary: Delete a file. get: responses: "200": description: Response schema: $ref: '#/definitions/schema.File' summary: Returns information about a specific file. /v1/files/{file_id}/content: get: responses: "200": description: file schema: type: string summary: Returns information about a specific file. /v1/images/generations: post: parameters: - description: query params in: body name: request required: true schema: $ref: '#/definitions/schema.OpenAIRequest' responses: "200": description: Response schema: $ref: '#/definitions/schema.OpenAIResponse' summary: Creates an image given a prompt. /v1/models: get: responses: "200": description: Response schema: $ref: '#/definitions/schema.ModelsDataResponse' summary: List and describe the various models available in the API. /v1/rerank: post: parameters: - description: query params in: body name: request required: true schema: $ref: '#/definitions/schema.JINARerankRequest' responses: "200": description: Response schema: $ref: '#/definitions/schema.JINARerankResponse' summary: Reranks a list of phrases by relevance to a given text query. /v1/text-to-speech/{voice-id}: post: parameters: - description: Account ID in: path name: voice-id required: true type: string - description: query params in: body name: request required: true schema: $ref: '#/definitions/schema.TTSRequest' responses: "200": description: Response schema: type: string summary: Generates audio from the input text. securityDefinitions: BearerAuth: in: header name: Authorization type: apiKey swagger: "2.0"