Generate sentences according to the prompts.
| key required | string API Key |
| model | string Default: "modelv2" Value: "modelv2" |
| prompt required | string prompt |
| max_tokens | number Default: 128 |
| temperature | number Default: 0.1 |
{- "model": "modelv2",
- "prompt": "string",
- "max_tokens": 128,
- "temperature": 0.1
}{- "result": "string"
}Generate sentences according to the content of the chat.
| key required | string API Key |
| model | string Default: "modelv2" Value: "modelv2" |
required | Array of objects |
| max_tokens | number Default: 128 |
| temperature | number Default: 0.1 |
{- "model": "modelv2",
- "messages": [
- {
- "role": "system",
- "content": "string"
}
], - "max_tokens": 128,
- "temperature": 0.1
}{- "result": "string"
}Measures the accuracy of LLM generated results.
| question | string Question text to LLM |
| response | string Generated result text from LLM |
{- "question": "string",
- "response": "string"
}{- "result": {
- "score": 0,
- "reasons": [
- "string"
]
}
}Start generating sentences according to the prompts.
| key required | string API Key |
| prompt required | string prompt |
{- "prompt": "string"
}{- "executionArn": "executionId",
- "startDate": 1685072261.784
}Get the result of generating sentences
| executionArn | string executionArn obtained from /lhtm-2/execution |
{- "executionArn": "string"
}{- "result": "string",
- "startDate": 1685072261.784,
- "status": "RUNNING"
}The translation engine used by AI GIJIROKU. It is also possible to localize services and build automatic interpretation applications in combination with speech recognition.
| key required | string API Key |
| source required | string source language |
| target required | string target language |
| text required | string source text |
{- "result": "string"
}Converts text to speech.
| key required | string API Key |
| text required | string Text tailored to the language specified by lang |
| lang | string Default: "ja-JP" BCP-47 |
{- "text": "string",
- "lang": "ja-JP"
}