@huggingface/tasks 0.9.1 → 0.10.1

package/src/tasks/chat-completion/spec/input.json

@@ -1,63 +1,227 @@
 {
-	"title": "ChatCompletionInput",
 	"$id": "/inference/schemas/chat-completion/input.json",
 	"$schema": "http://json-schema.org/draft-06/schema#",
-	"description": "Inputs for ChatCompletion inference",
+	"description": "Chat Completion Input.\n\nAuto-generated from TGI specs.\nFor more details, check out https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.",
+	"title": "ChatCompletionInput",
 	"type": "object",
+	"required": ["model", "messages"],
 	"properties": {
-		"messages": {
+		"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",
-			"title": "ChatCompletionInputMessage",
 			"items": {
-				"type": "object",
-				"properties": {
-					"role": {
-						"$ref": "#/definitions/Role"
-					},
-					"content": {
-						"type": "string",
-						"description": "The content of the message."
-					}
-				},
-				"required": ["role", "content"]
-			}
+				"type": "number",
+				"format": "float"
+			},
+			"description": "UNUSED\nModify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens\n(specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically,\nthe bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model,\nbut values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should\nresult in a ban or exclusive selection of the relevant token.",
+			"nullable": true
 		},
-		"frequency_penalty": {
-			"type": "number",
-			"description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim."
+		"logprobs": {
+			"type": "boolean",
+			"description": "Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each\noutput token returned in the content of message.",
+			"example": "false",
+			"nullable": true
 		},
 		"max_tokens": {
 			"type": "integer",
-			"description": "The maximum number of tokens that can be generated in the chat completion."
+			"format": "int32",
+			"description": "The maximum number of tokens that can be generated in the chat completion.",
+			"example": "32",
+			"nullable": true,
+			"minimum": 0
+		},
+		"messages": {
+			"type": "array",
+			"items": {
+				"$ref": "#/$defs/ChatCompletionInputMessage"
+			},
+			"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"
+		},
+		"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
 		},
 		"seed": {
 			"type": "integer",
-			"description": "The random sampling seed."
+			"format": "int64",
+			"example": 42,
+			"nullable": true,
+			"minimum": 0
 		},
 		"stop": {
-			"oneOf": [{ "type": "string" }, { "type": "array", "items": { "type": "string" } }],
-			"title": "ChatCompletionInputStopReason",
-			"description": "Stop generating tokens if a stop token is generated."
+			"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",
-			"description": "If set, partial message deltas will be sent."
+			"type": "boolean"
 		},
 		"temperature": {
 			"type": "number",
-			"description": "The value used to modulate the logits distribution."
+			"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,
+			"nullable": true
+		},
+		"tool_choice": {
+			"allOf": [
+				{
+					"$ref": "#/$defs/ChatCompletionInputToolType"
+				}
+			],
+			"nullable": true
+		},
+		"tool_prompt": {
+			"type": "string",
+			"description": "A prompt to be appended before the tools",
+			"example": "\"You will be presented with a JSON schema representing a set of tools.\nIf the user request lacks of sufficient information to make a precise tool selection: Do not invent any tool's properties, instead notify with an error message.\n\nJSON Schema:\n\"",
+			"nullable": true
+		},
+		"tools": {
+			"type": "array",
+			"items": {
+				"$ref": "#/$defs/ChatCompletionInputTool"
+			},
+			"description": "A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of\nfunctions the model may generate JSON inputs for.",
+			"example": "null",
+			"nullable": true
+		},
+		"top_logprobs": {
+			"type": "integer",
+			"format": "int32",
+			"description": "An integer between 0 and 5 specifying the number of most likely tokens to return at each token position, each with\nan associated log probability. logprobs must be set to true if this parameter is used.",
+			"example": "5",
+			"nullable": true,
+			"minimum": 0
 		},
 		"top_p": {
 			"type": "number",
-			"description": "If set to < 1, only the smallest set of most probable tokens with probabilities that add up to `top_p` or higher are kept for generation."
+			"format": "float",
+			"description": "An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the\ntokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.",
+			"example": 0.95,
+			"nullable": true
 		}
 	},
-	"required": ["messages"],
-	"definitions": {
-		"Role": {
-			"oneOf": [{ "const": "assistant" }, { "const": "system" }, { "const": "user" }],
-			"title": "ChatCompletionMessageRole",
-			"description": "The role of the message author."
+	"$defs": {
+		"ChatCompletionInputMessage": {
+			"type": "object",
+			"required": ["role"],
+			"properties": {
+				"content": {
+					"type": "string",
+					"example": "My name is David and I",
+					"nullable": true
+				},
+				"name": {
+					"type": "string",
+					"example": "\"David\"",
+					"nullable": true
+				},
+				"role": {
+					"type": "string",
+					"example": "user"
+				},
+				"tool_calls": {
+					"type": "array",
+					"items": {
+						"$ref": "#/$defs/ChatCompletionInputToolCall"
+					},
+					"nullable": true
+				}
+			},
+			"title": "ChatCompletionInputMessage"
+		},
+		"ChatCompletionInputToolCall": {
+			"type": "object",
+			"required": ["id", "type", "function"],
+			"properties": {
+				"function": {
+					"$ref": "#/$defs/ChatCompletionInputFunctionDefinition"
+				},
+				"id": {
+					"type": "integer",
+					"format": "int32",
+					"minimum": 0
+				},
+				"type": {
+					"type": "string"
+				}
+			},
+			"title": "ChatCompletionInputToolCall"
+		},
+		"ChatCompletionInputFunctionDefinition": {
+			"type": "object",
+			"required": ["name", "arguments"],
+			"properties": {
+				"arguments": {},
+				"description": {
+					"type": "string",
+					"nullable": true
+				},
+				"name": {
+					"type": "string"
+				}
+			},
+			"title": "ChatCompletionInputFunctionDefinition"
+		},
+		"ChatCompletionInputToolType": {
+			"oneOf": [
+				{
+					"type": "object",
+					"required": ["FunctionName"],
+					"properties": {
+						"FunctionName": {
+							"type": "string"
+						}
+					}
+				},
+				{
+					"type": "string",
+					"enum": ["OneOf"]
+				}
+			],
+			"title": "ChatCompletionInputToolType"
+		},
+		"ChatCompletionInputTool": {
+			"type": "object",
+			"required": ["type", "function"],
+			"properties": {
+				"function": {
+					"$ref": "#/$defs/ChatCompletionInputFunctionDefinition"
+				},
+				"type": {
+					"type": "string",
+					"example": "function"
+				}
+			},
+			"title": "ChatCompletionInputTool"
 		}
 	}
 }

package/src/tasks/chat-completion/spec/output.json

@@ -1,58 +1,196 @@
 {
 	"$id": "/inference/schemas/chat-completion/output.json",
 	"$schema": "http://json-schema.org/draft-06/schema#",
-	"description": "Outputs for Chat Completion inference",
+	"description": "Chat Completion Output.\n\nAuto-generated from TGI specs.\nFor more details, check out https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.",
 	"title": "ChatCompletionOutput",
 	"type": "object",
+	"required": ["id", "object", "created", "model", "system_fingerprint", "choices", "usage"],
 	"properties": {
 		"choices": {
 			"type": "array",
-			"description": "A list of chat completion choices.",
-			"title": "ChatCompletionOutputChoice",
 			"items": {
-				"type": "object",
-				"properties": {
-					"finish_reason": {
-						"$ref": "#/definitions/FinishReason",
-						"description": "The reason why the generation was stopped."
-					},
-					"index": {
-						"type": "integer",
-						"description": "The index of the choice in the list of choices."
-					},
-					"message": {
-						"type": "object",
-						"properties": {
-							"role": {
-								"$ref": "/inference/schemas/chat-completion/input.json#/definitions/Role"
-							},
-							"content": {
-								"type": "string",
-								"description": "The content of the chat completion message."
-							}
-						},
-						"title": "ChatCompletionOutputChoiceMessage",
-						"required": ["content", "role"]
-					}
-				},
-				"required": ["finish_reason", "index", "message"]
+				"$ref": "#/$defs/ChatCompletionOutputComplete"
 			}
 		},
 		"created": {
 			"type": "integer",
-			"description": "The Unix timestamp (in seconds) of when the chat completion was created."
+			"format": "int64",
+			"example": "1706270835",
+			"minimum": 0
+		},
+		"id": {
+			"type": "string"
+		},
+		"model": {
+			"type": "string",
+			"example": "mistralai/Mistral-7B-Instruct-v0.2"
+		},
+		"object": {
+			"type": "string"
+		},
+		"system_fingerprint": {
+			"type": "string"
+		},
+		"usage": {
+			"$ref": "#/$defs/ChatCompletionOutputUsage"
 		}
 	},
-	"required": ["choices", "created"],
-	"definitions": {
-		"FinishReason": {
-			"type": "string",
-			"title": "ChatCompletionFinishReason",
-			"oneOf": [
-				{ "const": "length", "description": "The generated sequence reached the maximum allowed length" },
-				{ "const": "eos_token", "description": "The model generated an end-of-sentence (EOS) token" },
-				{ "const": "stop_sequence", "description": "One of the sequence in stop_sequences was generated" }
-			]
+	"$defs": {
+		"ChatCompletionOutputComplete": {
+			"type": "object",
+			"required": ["index", "message", "finish_reason"],
+			"properties": {
+				"finish_reason": {
+					"type": "string"
+				},
+				"index": {
+					"type": "integer",
+					"format": "int32",
+					"minimum": 0
+				},
+				"logprobs": {
+					"allOf": [
+						{
+							"$ref": "#/$defs/ChatCompletionOutputLogprobs"
+						}
+					],
+					"nullable": true
+				},
+				"message": {
+					"$ref": "#/$defs/ChatCompletionOutputMessage"
+				}
+			},
+			"title": "ChatCompletionOutputComplete"
+		},
+		"ChatCompletionOutputLogprobs": {
+			"type": "object",
+			"required": ["content"],
+			"properties": {
+				"content": {
+					"type": "array",
+					"items": {
+						"$ref": "#/$defs/ChatCompletionOutputLogprob"
+					}
+				}
+			},
+			"title": "ChatCompletionOutputLogprobs"
+		},
+		"ChatCompletionOutputLogprob": {
+			"type": "object",
+			"required": ["token", "logprob", "top_logprobs"],
+			"properties": {
+				"logprob": {
+					"type": "number",
+					"format": "float"
+				},
+				"token": {
+					"type": "string"
+				},
+				"top_logprobs": {
+					"type": "array",
+					"items": {
+						"$ref": "#/$defs/ChatCompletionOutputTopLogprob"
+					}
+				}
+			},
+			"title": "ChatCompletionOutputLogprob"
+		},
+		"ChatCompletionOutputTopLogprob": {
+			"type": "object",
+			"required": ["token", "logprob"],
+			"properties": {
+				"logprob": {
+					"type": "number",
+					"format": "float"
+				},
+				"token": {
+					"type": "string"
+				}
+			},
+			"title": "ChatCompletionOutputTopLogprob"
+		},
+		"ChatCompletionOutputMessage": {
+			"type": "object",
+			"required": ["role"],
+			"properties": {
+				"content": {
+					"type": "string",
+					"example": "My name is David and I",
+					"nullable": true
+				},
+				"name": {
+					"type": "string",
+					"example": "\"David\"",
+					"nullable": true
+				},
+				"role": {
+					"type": "string",
+					"example": "user"
+				},
+				"tool_calls": {
+					"type": "array",
+					"items": {
+						"$ref": "#/$defs/ChatCompletionOutputToolCall"
+					},
+					"nullable": true
+				}
+			},
+			"title": "ChatCompletionOutputMessage"
+		},
+		"ChatCompletionOutputToolCall": {
+			"type": "object",
+			"required": ["id", "type", "function"],
+			"properties": {
+				"function": {
+					"$ref": "#/$defs/ChatCompletionOutputFunctionDefinition"
+				},
+				"id": {
+					"type": "integer",
+					"format": "int32",
+					"minimum": 0
+				},
+				"type": {
+					"type": "string"
+				}
+			},
+			"title": "ChatCompletionOutputToolCall"
+		},
+		"ChatCompletionOutputFunctionDefinition": {
+			"type": "object",
+			"required": ["name", "arguments"],
+			"properties": {
+				"arguments": {},
+				"description": {
+					"type": "string",
+					"nullable": true
+				},
+				"name": {
+					"type": "string"
+				}
+			},
+			"title": "ChatCompletionOutputFunctionDefinition"
+		},
+		"ChatCompletionOutputUsage": {
+			"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
+				}
+			},
+			"title": "ChatCompletionOutputUsage"
 		}
 	}
 }

package/src/tasks/chat-completion/spec/stream_output.json

@@ -0,0 +1,170 @@
+{
+	"$id": "/inference/schemas/chat-completion/stream_output.json",
+	"$schema": "http://json-schema.org/draft-06/schema#",
+	"description": "Chat Completion Stream Output.\n\nAuto-generated from TGI specs.\nFor more details, check out https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.",
+	"title": "ChatCompletionStreamOutput",
+	"type": "object",
+	"required": ["id", "object", "created", "model", "system_fingerprint", "choices"],
+	"properties": {
+		"choices": {
+			"type": "array",
+			"items": {
+				"$ref": "#/$defs/ChatCompletionStreamOutputChoice"
+			}
+		},
+		"created": {
+			"type": "integer",
+			"format": "int64",
+			"example": "1706270978",
+			"minimum": 0
+		},
+		"id": {
+			"type": "string"
+		},
+		"model": {
+			"type": "string",
+			"example": "mistralai/Mistral-7B-Instruct-v0.2"
+		},
+		"object": {
+			"type": "string"
+		},
+		"system_fingerprint": {
+			"type": "string"
+		}
+	},
+	"$defs": {
+		"ChatCompletionStreamOutputChoice": {
+			"type": "object",
+			"required": ["index", "delta"],
+			"properties": {
+				"delta": {
+					"$ref": "#/$defs/ChatCompletionStreamOutputDelta"
+				},
+				"finish_reason": {
+					"type": "string",
+					"nullable": true
+				},
+				"index": {
+					"type": "integer",
+					"format": "int32",
+					"minimum": 0
+				},
+				"logprobs": {
+					"allOf": [
+						{
+							"$ref": "#/$defs/ChatCompletionStreamOutputLogprobs"
+						}
+					],
+					"nullable": true
+				}
+			},
+			"title": "ChatCompletionStreamOutputChoice"
+		},
+		"ChatCompletionStreamOutputDelta": {
+			"type": "object",
+			"required": ["role"],
+			"properties": {
+				"content": {
+					"type": "string",
+					"example": "What is Deep Learning?",
+					"nullable": true
+				},
+				"role": {
+					"type": "string",
+					"example": "user"
+				},
+				"tool_calls": {
+					"allOf": [
+						{
+							"$ref": "#/$defs/ChatCompletionStreamOutputDeltaToolCall"
+						}
+					],
+					"nullable": true
+				}
+			},
+			"title": "ChatCompletionStreamOutputDelta"
+		},
+		"ChatCompletionStreamOutputDeltaToolCall": {
+			"type": "object",
+			"required": ["index", "id", "type", "function"],
+			"properties": {
+				"function": {
+					"$ref": "#/$defs/ChatCompletionStreamOutputFunction"
+				},
+				"id": {
+					"type": "string"
+				},
+				"index": {
+					"type": "integer",
+					"format": "int32",
+					"minimum": 0
+				},
+				"type": {
+					"type": "string"
+				}
+			},
+			"title": "ChatCompletionStreamOutputDeltaToolCall"
+		},
+		"ChatCompletionStreamOutputFunction": {
+			"type": "object",
+			"required": ["arguments"],
+			"properties": {
+				"arguments": {
+					"type": "string"
+				},
+				"name": {
+					"type": "string",
+					"nullable": true
+				}
+			},
+			"title": "ChatCompletionStreamOutputFunction"
+		},
+		"ChatCompletionStreamOutputLogprobs": {
+			"type": "object",
+			"required": ["content"],
+			"properties": {
+				"content": {
+					"type": "array",
+					"items": {
+						"$ref": "#/$defs/ChatCompletionStreamOutputLogprob"
+					}
+				}
+			},
+			"title": "ChatCompletionStreamOutputLogprobs"
+		},
+		"ChatCompletionStreamOutputLogprob": {
+			"type": "object",
+			"required": ["token", "logprob", "top_logprobs"],
+			"properties": {
+				"logprob": {
+					"type": "number",
+					"format": "float"
+				},
+				"token": {
+					"type": "string"
+				},
+				"top_logprobs": {
+					"type": "array",
+					"items": {
+						"$ref": "#/$defs/ChatCompletionStreamOutputTopLogprob"
+					}
+				}
+			},
+			"title": "ChatCompletionStreamOutputLogprob"
+		},
+		"ChatCompletionStreamOutputTopLogprob": {
+			"type": "object",
+			"required": ["token", "logprob"],
+			"properties": {
+				"logprob": {
+					"type": "number",
+					"format": "float"
+				},
+				"token": {
+					"type": "string"
+				}
+			},
+			"title": "ChatCompletionStreamOutputTopLogprob"
+		}
+	}
+}