hf_text-generation-inference/docs/openapi.json

2119 lines
57 KiB
JSON

{
"openapi": "3.0.3",
"info": {
"title": "Text Generation Inference",
"description": "Text Generation Webserver",
"contact": {
"name": "Olivier Dehaene"
},
"license": {
"name": "Apache 2.0",
"url": "https://www.apache.org/licenses/LICENSE-2.0"
},
"version": "2.2.1-dev0"
},
"paths": {
"/": {
"post": {
"tags": [
"Text Generation Inference"
],
"summary": "Generate tokens if `stream == false` or a stream of token if `stream == true`",
"operationId": "compat_generate",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/CompatGenerateRequest"
}
}
},
"required": true
},
"responses": {
"200": {
"description": "Generated Text",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/GenerateResponse"
}
},
"text/event-stream": {
"schema": {
"$ref": "#/components/schemas/StreamResponse"
}
}
}
},
"422": {
"description": "Input validation error",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Input validation error"
}
}
}
},
"424": {
"description": "Generation Error",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Request failed during generation"
}
}
}
},
"429": {
"description": "Model is overloaded",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Model is overloaded"
}
}
}
},
"500": {
"description": "Incomplete generation",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Incomplete generation"
}
}
}
}
}
}
},
"/generate": {
"post": {
"tags": [
"Text Generation Inference"
],
"summary": "Generate tokens",
"operationId": "generate",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/GenerateRequest"
}
}
},
"required": true
},
"responses": {
"200": {
"description": "Generated Text",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/GenerateResponse"
}
}
}
},
"422": {
"description": "Input validation error",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Input validation error"
}
}
}
},
"424": {
"description": "Generation Error",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Request failed during generation"
}
}
}
},
"429": {
"description": "Model is overloaded",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Model is overloaded"
}
}
}
},
"500": {
"description": "Incomplete generation",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Incomplete generation"
}
}
}
}
}
}
},
"/generate_stream": {
"post": {
"tags": [
"Text Generation Inference"
],
"summary": "Generate a stream of token using Server-Sent Events",
"operationId": "generate_stream",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/GenerateRequest"
}
}
},
"required": true
},
"responses": {
"200": {
"description": "Generated Text",
"content": {
"text/event-stream": {
"schema": {
"$ref": "#/components/schemas/StreamResponse"
}
}
}
},
"422": {
"description": "Input validation error",
"content": {
"text/event-stream": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Input validation error"
}
}
}
},
"424": {
"description": "Generation Error",
"content": {
"text/event-stream": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Request failed during generation"
}
}
}
},
"429": {
"description": "Model is overloaded",
"content": {
"text/event-stream": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Model is overloaded"
}
}
}
},
"500": {
"description": "Incomplete generation",
"content": {
"text/event-stream": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Incomplete generation"
}
}
}
}
}
}
},
"/health": {
"get": {
"tags": [
"Text Generation Inference"
],
"summary": "Health check method",
"operationId": "health",
"responses": {
"200": {
"description": "Everything is working fine"
},
"503": {
"description": "Text generation inference is down",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "unhealthy",
"error_type": "healthcheck"
}
}
}
}
}
}
},
"/info": {
"get": {
"tags": [
"Text Generation Inference"
],
"summary": "Text Generation Inference endpoint info",
"operationId": "get_model_info",
"responses": {
"200": {
"description": "Served model info",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Info"
}
}
}
}
}
}
},
"/metrics": {
"get": {
"tags": [
"Text Generation Inference"
],
"summary": "Prometheus metrics scrape endpoint",
"operationId": "metrics",
"responses": {
"200": {
"description": "Prometheus Metrics",
"content": {
"text/plain": {
"schema": {
"type": "string"
}
}
}
}
}
}
},
"/tokenize": {
"post": {
"tags": [
"Text Generation Inference"
],
"summary": "Tokenize inputs",
"operationId": "tokenize",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/GenerateRequest"
}
}
},
"required": true
},
"responses": {
"200": {
"description": "Tokenized ids",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/TokenizeResponse"
}
}
}
},
"404": {
"description": "No tokenizer found",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "No fast tokenizer available"
}
}
}
}
}
}
},
"/v1/chat/completions": {
"post": {
"tags": [
"Text Generation Inference"
],
"summary": "Generate tokens",
"operationId": "chat_completions",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ChatRequest"
}
}
},
"required": true
},
"responses": {
"200": {
"description": "Generated Chat Completion",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ChatCompletion"
}
},
"text/event-stream": {
"schema": {
"$ref": "#/components/schemas/ChatCompletionChunk"
}
}
}
},
"422": {
"description": "Input validation error",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Input validation error"
}
}
}
},
"424": {
"description": "Generation Error",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Request failed during generation"
}
}
}
},
"429": {
"description": "Model is overloaded",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Model is overloaded"
}
}
}
},
"500": {
"description": "Incomplete generation",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Incomplete generation"
}
}
}
}
}
}
},
"/v1/completions": {
"post": {
"tags": [
"Text Generation Inference"
],
"summary": "Generate tokens",
"operationId": "completions",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/CompletionRequest"
}
}
},
"required": true
},
"responses": {
"200": {
"description": "Generated Chat Completion",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/CompletionFinal"
}
},
"text/event-stream": {
"schema": {
"$ref": "#/components/schemas/Chunk"
}
}
}
},
"422": {
"description": "Input validation error",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Input validation error"
}
}
}
},
"424": {
"description": "Generation Error",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Request failed during generation"
}
}
}
},
"429": {
"description": "Model is overloaded",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Model is overloaded"
}
}
}
},
"500": {
"description": "Incomplete generation",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ErrorResponse"
},
"example": {
"error": "Incomplete generation"
}
}
}
}
}
}
}
},
"components": {
"schemas": {
"BestOfSequence": {
"type": "object",
"required": [
"generated_text",
"finish_reason",
"generated_tokens",
"prefill",
"tokens"
],
"properties": {
"finish_reason": {
"$ref": "#/components/schemas/FinishReason"
},
"generated_text": {
"type": "string",
"example": "test"
},
"generated_tokens": {
"type": "integer",
"format": "int32",
"example": 1,
"minimum": 0
},
"prefill": {
"type": "array",
"items": {
"$ref": "#/components/schemas/PrefillToken"
}
},
"seed": {
"type": "integer",
"format": "int64",
"example": 42,
"nullable": true,
"minimum": 0
},
"tokens": {
"type": "array",
"items": {
"$ref": "#/components/schemas/Token"
}
},
"top_tokens": {
"type": "array",
"items": {
"type": "array",
"items": {
"$ref": "#/components/schemas/Token"
}
}
}
}
},
"ChatCompletion": {
"type": "object",
"required": [
"id",
"created",
"model",
"system_fingerprint",
"choices",
"usage"
],
"properties": {
"choices": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ChatCompletionComplete"
}
},
"created": {
"type": "integer",
"format": "int64",
"example": "1706270835",
"minimum": 0
},
"id": {
"type": "string"
},
"model": {
"type": "string",
"example": "mistralai/Mistral-7B-Instruct-v0.2"
},
"system_fingerprint": {
"type": "string"
},
"usage": {
"$ref": "#/components/schemas/Usage"
}
}
},
"ChatCompletionChoice": {
"type": "object",
"required": [
"index",
"delta"
],
"properties": {
"delta": {
"$ref": "#/components/schemas/ChatCompletionDelta"
},
"finish_reason": {
"type": "string",
"nullable": true
},
"index": {
"type": "integer",
"format": "int32",
"minimum": 0
},
"logprobs": {
"allOf": [
{
"$ref": "#/components/schemas/ChatCompletionLogprobs"
}
],
"nullable": true
}
}
},
"ChatCompletionChunk": {
"type": "object",
"required": [
"id",
"created",
"model",
"system_fingerprint",
"choices"
],
"properties": {
"choices": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ChatCompletionChoice"
}
},
"created": {
"type": "integer",
"format": "int64",
"example": "1706270978",
"minimum": 0
},
"id": {
"type": "string"
},
"model": {
"type": "string",
"example": "mistralai/Mistral-7B-Instruct-v0.2"
},
"system_fingerprint": {
"type": "string"
}
}
},
"ChatCompletionComplete": {
"type": "object",
"required": [
"index",
"message",
"finish_reason"
],
"properties": {
"finish_reason": {
"type": "string"
},
"index": {
"type": "integer",
"format": "int32",
"minimum": 0
},
"logprobs": {
"allOf": [
{
"$ref": "#/components/schemas/ChatCompletionLogprobs"
}
],
"nullable": true
},
"message": {
"$ref": "#/components/schemas/OutputMessage"
}
}
},
"ChatCompletionDelta": {
"oneOf": [
{
"$ref": "#/components/schemas/TextMessage"
},
{
"$ref": "#/components/schemas/ToolCallDelta"
}
]
},
"ChatCompletionLogprob": {
"type": "object",
"required": [
"token",
"logprob",
"top_logprobs"
],
"properties": {
"logprob": {
"type": "number",
"format": "float"
},
"token": {
"type": "string"
},
"top_logprobs": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ChatCompletionTopLogprob"
}
}
}
},
"ChatCompletionLogprobs": {
"type": "object",
"required": [
"content"
],
"properties": {
"content": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ChatCompletionLogprob"
}
}
}
},
"ChatCompletionTopLogprob": {
"type": "object",
"required": [
"token",
"logprob"
],
"properties": {
"logprob": {
"type": "number",
"format": "float"
},
"token": {
"type": "string"
}
}
},
"ChatRequest": {
"type": "object",
"required": [
"messages"
],
"properties": {
"frequency_penalty": {
"type": "number",
"format": "float",
"description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far,\ndecreasing the model's likelihood to repeat the same line verbatim.",
"example": "1.0",
"nullable": true
},
"logit_bias": {
"type": "array",
"items": {
"type": "number",
"format": "float"
},
"description": "UNUSED\nModify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens\n(specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically,\nthe bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model,\nbut values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should\nresult in a ban or exclusive selection of the relevant token.",
"nullable": true
},
"logprobs": {
"type": "boolean",
"description": "Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each\noutput token returned in the content of message.",
"example": "false",
"nullable": true
},
"max_tokens": {
"type": "integer",
"format": "int32",
"description": "The maximum number of tokens that can be generated in the chat completion.",
"example": "32",
"nullable": true,
"minimum": 0
},
"messages": {
"type": "array",
"items": {
"$ref": "#/components/schemas/Message"
},
"description": "A list of messages comprising the conversation so far.",
"example": "[{\"role\": \"user\", \"content\": \"What is Deep Learning?\"}]"
},
"model": {
"type": "string",
"description": "[UNUSED] ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.",
"example": "mistralai/Mistral-7B-Instruct-v0.2",
"nullable": true
},
"n": {
"type": "integer",
"format": "int32",
"description": "UNUSED\nHow many chat completion choices to generate for each input message. Note that you will be charged based on the\nnumber of generated tokens across all of the choices. Keep n as 1 to minimize costs.",
"example": "2",
"nullable": true,
"minimum": 0
},
"presence_penalty": {
"type": "number",
"format": "float",
"description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far,\nincreasing the model's likelihood to talk about new topics",
"example": 0.1,
"nullable": true
},
"response_format": {
"allOf": [
{
"$ref": "#/components/schemas/GrammarType"
}
],
"default": "null",
"nullable": true
},
"seed": {
"type": "integer",
"format": "int64",
"example": 42,
"nullable": true,
"minimum": 0
},
"stop": {
"type": "array",
"items": {
"type": "string"
},
"description": "Up to 4 sequences where the API will stop generating further tokens.",
"example": "null",
"nullable": true
},
"stream": {
"type": "boolean"
},
"temperature": {
"type": "number",
"format": "float",
"description": "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while\nlower values like 0.2 will make it more focused and deterministic.\n\nWe generally recommend altering this or `top_p` but not both.",
"example": 1.0,
"nullable": true
},
"tool_choice": {
"allOf": [
{
"$ref": "#/components/schemas/ToolChoice"
}
],
"nullable": true
},
"tool_prompt": {
"type": "string",
"description": "A prompt to be appended before the tools",
"example": "\"You will be presented with a JSON schema representing a set of tools.\nIf the user request lacks of sufficient information to make a precise tool selection: Do not invent any tool's properties, instead notify with an error message.\n\nJSON Schema:\n\"",
"nullable": true
},
"tools": {
"type": "array",
"items": {
"$ref": "#/components/schemas/Tool"
},
"description": "A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of\nfunctions the model may generate JSON inputs for.",
"example": "null",
"nullable": true
},
"top_logprobs": {
"type": "integer",
"format": "int32",
"description": "An integer between 0 and 5 specifying the number of most likely tokens to return at each token position, each with\nan associated log probability. logprobs must be set to true if this parameter is used.",
"example": "5",
"nullable": true,
"minimum": 0
},
"top_p": {
"type": "number",
"format": "float",
"description": "An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the\ntokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.",
"example": 0.95,
"nullable": true
}
}
},
"Chunk": {
"type": "object",
"required": [
"id",
"created",
"choices",
"model",
"system_fingerprint"
],
"properties": {
"choices": {
"type": "array",
"items": {
"$ref": "#/components/schemas/CompletionComplete"
}
},
"created": {
"type": "integer",
"format": "int64",
"minimum": 0
},
"id": {
"type": "string"
},
"model": {
"type": "string"
},
"system_fingerprint": {
"type": "string"
}
}
},
"CompatGenerateRequest": {
"type": "object",
"required": [
"inputs"
],
"properties": {
"inputs": {
"type": "string",
"example": "My name is Olivier and I"
},
"parameters": {
"$ref": "#/components/schemas/GenerateParameters"
},
"stream": {
"type": "boolean",
"default": "false"
}
}
},
"Completion": {
"oneOf": [
{
"allOf": [
{
"$ref": "#/components/schemas/Chunk"
},
{
"type": "object",
"required": [
"object"
],
"properties": {
"object": {
"type": "string",
"enum": [
"text_completion"
]
}
}
}
]
},
{
"allOf": [
{
"$ref": "#/components/schemas/CompletionFinal"
},
{
"type": "object",
"required": [
"object"
],
"properties": {
"object": {
"type": "string",
"enum": [
"text_completion"
]
}
}
}
]
}
],
"discriminator": {
"propertyName": "object"
}
},
"CompletionComplete": {
"type": "object",
"required": [
"index",
"text",
"finish_reason"
],
"properties": {
"finish_reason": {
"type": "string"
},
"index": {
"type": "integer",
"format": "int32",
"minimum": 0
},
"logprobs": {
"type": "array",
"items": {
"type": "number",
"format": "float"
},
"nullable": true
},
"text": {
"type": "string"
}
}
},
"CompletionFinal": {
"type": "object",
"required": [
"id",
"created",
"model",
"system_fingerprint",
"choices",
"usage"
],
"properties": {
"choices": {
"type": "array",
"items": {
"$ref": "#/components/schemas/CompletionComplete"
}
},
"created": {
"type": "integer",
"format": "int64",
"example": "1706270835",
"minimum": 0
},
"id": {
"type": "string"
},
"model": {
"type": "string",
"example": "mistralai/Mistral-7B-Instruct-v0.2"
},
"system_fingerprint": {
"type": "string"
},
"usage": {
"$ref": "#/components/schemas/Usage"
}
}
},
"CompletionRequest": {
"type": "object",
"required": [
"prompt"
],
"properties": {
"frequency_penalty": {
"type": "number",
"format": "float",
"description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far,\ndecreasing the model's likelihood to repeat the same line verbatim.",
"example": "1.0",
"nullable": true
},
"max_tokens": {
"type": "integer",
"format": "int32",
"description": "The maximum number of tokens that can be generated in the chat completion.",
"default": "32",
"nullable": true,
"minimum": 0
},
"model": {
"type": "string",
"description": "UNUSED\nID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.",
"example": "mistralai/Mistral-7B-Instruct-v0.2",
"nullable": true
},
"prompt": {
"$ref": "#/components/schemas/Prompt"
},
"repetition_penalty": {
"type": "number",
"format": "float",
"nullable": true
},
"seed": {
"type": "integer",
"format": "int64",
"example": 42,
"nullable": true,
"minimum": 0
},
"stop": {
"type": "array",
"items": {
"type": "string"
},
"description": "Up to 4 sequences where the API will stop generating further tokens.",
"example": "null",
"nullable": true
},
"stream": {
"type": "boolean"
},
"suffix": {
"type": "string",
"description": "The text to append to the prompt. This is useful for completing sentences or generating a paragraph of text.\nplease see the completion_template field in the model's tokenizer_config.json file for completion template.",
"nullable": true
},
"temperature": {
"type": "number",
"format": "float",
"description": "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while\nlower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.",
"example": 1.0,
"nullable": true
},
"top_p": {
"type": "number",
"format": "float",
"description": "An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the\ntokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.",
"example": 0.95,
"nullable": true
}
}
},
"DeltaToolCall": {
"type": "object",
"required": [
"index",
"id",
"type",
"function"
],
"properties": {
"function": {
"$ref": "#/components/schemas/Function"
},
"id": {
"type": "string"
},
"index": {
"type": "integer",
"format": "int32",
"minimum": 0
},
"type": {
"type": "string"
}
}
},
"Details": {
"type": "object",
"required": [
"finish_reason",
"generated_tokens",
"prefill",
"tokens"
],
"properties": {
"best_of_sequences": {
"type": "array",
"items": {
"$ref": "#/components/schemas/BestOfSequence"
},
"nullable": true
},
"finish_reason": {
"$ref": "#/components/schemas/FinishReason"
},
"generated_tokens": {
"type": "integer",
"format": "int32",
"example": 1,
"minimum": 0
},
"prefill": {
"type": "array",
"items": {
"$ref": "#/components/schemas/PrefillToken"
}
},
"seed": {
"type": "integer",
"format": "int64",
"example": 42,
"nullable": true,
"minimum": 0
},
"tokens": {
"type": "array",
"items": {
"$ref": "#/components/schemas/Token"
}
},
"top_tokens": {
"type": "array",
"items": {
"type": "array",
"items": {
"$ref": "#/components/schemas/Token"
}
}
}
}
},
"ErrorResponse": {
"type": "object",
"required": [
"error",
"error_type"
],
"properties": {
"error": {
"type": "string"
},
"error_type": {
"type": "string"
}
}
},
"FinishReason": {
"type": "string",
"enum": [
"length",
"eos_token",
"stop_sequence"
],
"example": "Length"
},
"Function": {
"type": "object",
"required": [
"arguments"
],
"properties": {
"arguments": {
"type": "string"
},
"name": {
"type": "string",
"nullable": true
}
}
},
"FunctionDefinition": {
"type": "object",
"required": [
"name",
"arguments"
],
"properties": {
"arguments": {},
"description": {
"type": "string",
"nullable": true
},
"name": {
"type": "string"
}
}
},
"FunctionName": {
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string"
}
}
},
"GenerateParameters": {
"type": "object",
"properties": {
"adapter_id": {
"type": "string",
"description": "Lora adapter id",
"default": "null",
"example": "null",
"nullable": true
},
"best_of": {
"type": "integer",
"description": "Generate best_of sequences and return the one if the highest token logprobs.",
"default": "null",
"example": 1,
"nullable": true,
"minimum": 0,
"exclusiveMinimum": 0
},
"decoder_input_details": {
"type": "boolean",
"description": "Whether to return decoder input token logprobs and ids.",
"default": "false"
},
"details": {
"type": "boolean",
"description": "Whether to return generation details.",
"default": "true"
},
"do_sample": {
"type": "boolean",
"description": "Activate logits sampling.",
"default": "false",
"example": true
},
"frequency_penalty": {
"type": "number",
"format": "float",
"description": "The parameter for frequency penalty. 1.0 means no penalty\nPenalize new tokens based on their existing frequency in the text so far,\ndecreasing the model's likelihood to repeat the same line verbatim.",
"default": "null",
"example": 0.1,
"nullable": true,
"exclusiveMinimum": -2
},
"grammar": {
"allOf": [
{
"$ref": "#/components/schemas/GrammarType"
}
],
"default": "null",
"nullable": true
},
"max_new_tokens": {
"type": "integer",
"format": "int32",
"description": "Maximum number of tokens to generate.",
"default": "100",
"example": "20",
"nullable": true,
"minimum": 0
},
"repetition_penalty": {
"type": "number",
"format": "float",
"description": "The parameter for repetition penalty. 1.0 means no penalty.\nSee [this paper](https://arxiv.org/pdf/1909.05858.pdf) for more details.",
"default": "null",
"example": 1.03,
"nullable": true,
"exclusiveMinimum": 0
},
"return_full_text": {
"type": "boolean",
"description": "Whether to prepend the prompt to the generated text",
"default": "null",
"example": false,
"nullable": true
},
"seed": {
"type": "integer",
"format": "int64",
"description": "Random sampling seed.",
"default": "null",
"example": "null",
"nullable": true,
"minimum": 0,
"exclusiveMinimum": 0
},
"stop": {
"type": "array",
"items": {
"type": "string"
},
"description": "Stop generating tokens if a member of `stop` is generated.",
"example": [
"photographer"
],
"maxItems": 4
},
"temperature": {
"type": "number",
"format": "float",
"description": "The value used to module the logits distribution.",
"default": "null",
"example": 0.5,
"nullable": true,
"exclusiveMinimum": 0
},
"top_k": {
"type": "integer",
"format": "int32",
"description": "The number of highest probability vocabulary tokens to keep for top-k-filtering.",
"default": "null",
"example": 10,
"nullable": true,
"exclusiveMinimum": 0
},
"top_n_tokens": {
"type": "integer",
"format": "int32",
"description": "The number of highest probability vocabulary tokens to keep for top-n-filtering.",
"default": "null",
"example": 5,
"nullable": true,
"minimum": 0,
"exclusiveMinimum": 0
},
"top_p": {
"type": "number",
"format": "float",
"description": "Top-p value for nucleus sampling.",
"default": "null",
"example": 0.95,
"nullable": true,
"maximum": 1,
"exclusiveMinimum": 0
},
"truncate": {
"type": "integer",
"description": "Truncate inputs tokens to the given size.",
"default": "null",
"example": "null",
"nullable": true,
"minimum": 0
},
"typical_p": {
"type": "number",
"format": "float",
"description": "Typical Decoding mass\nSee [Typical Decoding for Natural Language Generation](https://arxiv.org/abs/2202.00666) for more information.",
"default": "null",
"example": 0.95,
"nullable": true,
"maximum": 1,
"exclusiveMinimum": 0
},
"watermark": {
"type": "boolean",
"description": "Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226).",
"default": "false",
"example": true
}
}
},
"GenerateRequest": {
"type": "object",
"required": [
"inputs"
],
"properties": {
"inputs": {
"type": "string",
"example": "My name is Olivier and I"
},
"parameters": {
"$ref": "#/components/schemas/GenerateParameters"
}
}
},
"GenerateResponse": {
"type": "object",
"required": [
"generated_text"
],
"properties": {
"details": {
"allOf": [
{
"$ref": "#/components/schemas/Details"
}
],
"nullable": true
},
"generated_text": {
"type": "string",
"example": "test"
}
}
},
"GrammarType": {
"oneOf": [
{
"type": "object",
"required": [
"type",
"value"
],
"properties": {
"type": {
"type": "string",
"enum": [
"json"
]
},
"value": {
"description": "A string that represents a [JSON Schema](https://json-schema.org/).\n\nJSON Schema is a declarative language that allows to annotate JSON documents\nwith types and descriptions."
}
}
},
{
"type": "object",
"required": [
"type",
"value"
],
"properties": {
"type": {
"type": "string",
"enum": [
"regex"
]
},
"value": {
"type": "string"
}
}
}
],
"discriminator": {
"propertyName": "type"
}
},
"Info": {
"type": "object",
"required": [
"model_id",
"model_dtype",
"model_device_type",
"max_concurrent_requests",
"max_best_of",
"max_stop_sequences",
"max_input_tokens",
"max_total_tokens",
"waiting_served_ratio",
"max_batch_total_tokens",
"max_waiting_tokens",
"validation_workers",
"max_client_batch_size",
"router",
"version"
],
"properties": {
"docker_label": {
"type": "string",
"example": "null",
"nullable": true
},
"max_batch_size": {
"type": "integer",
"example": "null",
"nullable": true,
"minimum": 0
},
"max_batch_total_tokens": {
"type": "integer",
"format": "int32",
"example": "32000",
"minimum": 0
},
"max_best_of": {
"type": "integer",
"example": "2",
"minimum": 0
},
"max_client_batch_size": {
"type": "integer",
"example": "32",
"minimum": 0
},
"max_concurrent_requests": {
"type": "integer",
"description": "Router Parameters",
"example": "128",
"minimum": 0
},
"max_input_tokens": {
"type": "integer",
"example": "1024",
"minimum": 0
},
"max_stop_sequences": {
"type": "integer",
"example": "4",
"minimum": 0
},
"max_total_tokens": {
"type": "integer",
"example": "2048",
"minimum": 0
},
"max_waiting_tokens": {
"type": "integer",
"example": "20",
"minimum": 0
},
"model_device_type": {
"type": "string",
"example": "cuda"
},
"model_dtype": {
"type": "string",
"example": "torch.float16"
},
"model_id": {
"type": "string",
"description": "Model info",
"example": "bigscience/blomm-560m"
},
"model_pipeline_tag": {
"type": "string",
"example": "text-generation",
"nullable": true
},
"model_sha": {
"type": "string",
"example": "e985a63cdc139290c5f700ff1929f0b5942cced2",
"nullable": true
},
"router": {
"type": "string",
"description": "Router Info",
"example": "text-generation-router"
},
"sha": {
"type": "string",
"example": "null",
"nullable": true
},
"validation_workers": {
"type": "integer",
"example": "2",
"minimum": 0
},
"version": {
"type": "string",
"example": "0.5.0"
},
"waiting_served_ratio": {
"type": "number",
"format": "float",
"example": "1.2"
}
}
},
"Message": {
"type": "object",
"required": [
"role",
"content"
],
"properties": {
"content": {
"$ref": "#/components/schemas/MessageContent"
},
"name": {
"type": "string",
"example": "\"David\"",
"nullable": true
},
"role": {
"type": "string",
"example": "user"
}
}
},
"MessageChunk": {
"oneOf": [
{
"type": "object",
"required": [
"text",
"type"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"type": "string",
"enum": [
"text"
]
}
}
},
{
"type": "object",
"required": [
"image_url",
"type"
],
"properties": {
"image_url": {
"$ref": "#/components/schemas/Url"
},
"type": {
"type": "string",
"enum": [
"image_url"
]
}
}
}
],
"discriminator": {
"propertyName": "type"
}
},
"MessageContent": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"$ref": "#/components/schemas/MessageChunk"
}
}
]
},
"OutputMessage": {
"oneOf": [
{
"$ref": "#/components/schemas/TextMessage"
},
{
"$ref": "#/components/schemas/ToolCallMessage"
}
]
},
"PrefillToken": {
"type": "object",
"required": [
"id",
"text",
"logprob"
],
"properties": {
"id": {
"type": "integer",
"format": "int32",
"example": 0,
"minimum": 0
},
"logprob": {
"type": "number",
"format": "float",
"example": -0.34,
"nullable": true
},
"text": {
"type": "string",
"example": "test"
}
}
},
"Prompt": {
"type": "array",
"items": {
"type": "string"
}
},
"SimpleToken": {
"type": "object",
"required": [
"id",
"text",
"start",
"stop"
],
"properties": {
"id": {
"type": "integer",
"format": "int32",
"example": 0,
"minimum": 0
},
"start": {
"type": "integer",
"example": 0,
"minimum": 0
},
"stop": {
"type": "integer",
"example": 2,
"minimum": 0
},
"text": {
"type": "string",
"example": "test"
}
}
},
"StreamDetails": {
"type": "object",
"required": [
"finish_reason",
"generated_tokens"
],
"properties": {
"finish_reason": {
"$ref": "#/components/schemas/FinishReason"
},
"generated_tokens": {
"type": "integer",
"format": "int32",
"example": 1,
"minimum": 0
},
"seed": {
"type": "integer",
"format": "int64",
"example": 42,
"nullable": true,
"minimum": 0
}
}
},
"StreamResponse": {
"type": "object",
"required": [
"index",
"token"
],
"properties": {
"details": {
"allOf": [
{
"$ref": "#/components/schemas/StreamDetails"
}
],
"default": "null",
"nullable": true
},
"generated_text": {
"type": "string",
"default": "null",
"example": "test",
"nullable": true
},
"index": {
"type": "integer",
"format": "int32",
"minimum": 0
},
"token": {
"$ref": "#/components/schemas/Token"
},
"top_tokens": {
"type": "array",
"items": {
"$ref": "#/components/schemas/Token"
}
}
}
},
"TextMessage": {
"type": "object",
"required": [
"role",
"content"
],
"properties": {
"content": {
"type": "string",
"example": "My name is David and I"
},
"role": {
"type": "string",
"example": "user"
}
}
},
"Token": {
"type": "object",
"required": [
"id",
"text",
"logprob",
"special"
],
"properties": {
"id": {
"type": "integer",
"format": "int32",
"example": 0,
"minimum": 0
},
"logprob": {
"type": "number",
"format": "float",
"example": -0.34,
"nullable": true
},
"special": {
"type": "boolean",
"example": "false"
},
"text": {
"type": "string",
"example": "test"
}
}
},
"TokenizeResponse": {
"type": "array",
"items": {
"$ref": "#/components/schemas/SimpleToken"
}
},
"Tool": {
"type": "object",
"required": [
"type",
"function"
],
"properties": {
"function": {
"$ref": "#/components/schemas/FunctionDefinition"
},
"type": {
"type": "string",
"example": "function"
}
}
},
"ToolCall": {
"type": "object",
"required": [
"id",
"type",
"function"
],
"properties": {
"function": {
"$ref": "#/components/schemas/FunctionDefinition"
},
"id": {
"type": "string"
},
"type": {
"type": "string"
}
}
},
"ToolCallDelta": {
"type": "object",
"required": [
"role",
"tool_calls"
],
"properties": {
"role": {
"type": "string",
"example": "assistant"
},
"tool_calls": {
"$ref": "#/components/schemas/DeltaToolCall"
}
}
},
"ToolCallMessage": {
"type": "object",
"required": [
"role",
"tool_calls"
],
"properties": {
"role": {
"type": "string",
"example": "assistant"
},
"tool_calls": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ToolCall"
}
}
}
},
"ToolChoice": {
"allOf": [
{
"$ref": "#/components/schemas/ToolType"
}
],
"nullable": true
},
"ToolType": {
"oneOf": [
{
"type": "object",
"default": null,
"nullable": true
},
{
"type": "string"
},
{
"type": "object",
"required": [
"function"
],
"properties": {
"function": {
"$ref": "#/components/schemas/FunctionName"
}
}
},
{
"type": "object",
"default": null,
"nullable": true
}
]
},
"Url": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string"
}
}
},
"Usage": {
"type": "object",
"required": [
"prompt_tokens",
"completion_tokens",
"total_tokens"
],
"properties": {
"completion_tokens": {
"type": "integer",
"format": "int32",
"minimum": 0
},
"prompt_tokens": {
"type": "integer",
"format": "int32",
"minimum": 0
},
"total_tokens": {
"type": "integer",
"format": "int32",
"minimum": 0
}
}
}
}
},
"tags": [
{
"name": "Text Generation Inference",
"description": "Hugging Face Text Generation Inference API"
}
]
}