"description":"A list of messages comprising the conversation so far."
"description":"A list of messages comprising the conversation so far.",
"example":"[{\"role\": \"user\", \"content\": \"What is Deep Learning?\"}]"
},
},
"model":{
"model":{
"type":"string",
"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.",
"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"
"example":"mistralai/Mistral-7B-Instruct-v0.2"
},
},
"n":{
"n":{
...
@@ -806,6 +900,15 @@
...
@@ -806,6 +900,15 @@
"nullable":true,
"nullable":true,
"minimum":0
"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":{
"stream":{
"type":"boolean"
"type":"boolean"
},
},
...
@@ -816,6 +919,29 @@
...
@@ -816,6 +919,29 @@
"example":1.0,
"example":1.0,
"nullable":true
"nullable":true
},
},
"tool_choice":{
"allOf":[
{
"$ref":"#/components/schemas/ToolType"
}
],
"nullable":true
},
"tool_prompt":{
"type":"string",
"description":"A prompt to be appended before the tools",
"example":"\"Based on the conversation, please choose the most appropriate tool to use: \"",
"nullable":true
},
"tools":{
"type":"array",
"items":{
"$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":{
"top_logprobs":{
"type":"integer",
"type":"integer",
"format":"int32",
"format":"int32",
...
@@ -852,6 +978,164 @@
...
@@ -852,6 +978,164 @@
}
}
}
}
},
},
"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"
}
}
},
"CompletionCompleteChunk":{
"type":"object",
"required":[
"id",
"object",
"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"
},
"object":{
"type":"string"
},
"system_fingerprint":{
"type":"string"
}
}
},
"CompletionRequest":{
"type":"object",
"required":[
"model",
"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"
},
"prompt":{
"type":"string",
"description":"The prompt to generate completions for.",
"example":"What is Deep Learning?"
},
"repetition_penalty":{
"type":"number",
"format":"float",
"nullable":true
},
"seed":{
"type":"integer",
"format":"int64",
"example":42,
"nullable":true,
"minimum":0
},
"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.",
