Quantcast
Viewing all articles
Browse latest Browse all 2341

Extensions in Development • Re: [3.2][3.3][RC] AI Labs with Midjourney, ChatGPT, DALL-E, Gemini, Gemini Vision and Stable Diffusion support

Here is some output from the log after I made a bit of a prefix for Gemini:

Code:

{  "start": "2024-04-04 08:54:48",  "history.pattern": "/<QUOTE\\sauthor=\"Sucky\"\\spost_id=\"(.*)\"\\stime=\"(.*)\"\\suser_id=\"13015\">/",  "request.request_tokens": {    "totalTokens": 35  },  "request.request_tokens.codes": [    200  ],  "request.json": {    "contents": [      {        "role": "user",        "parts": [          {            "text": <my prefix>          },          {            "text": <my question>          }        ]      }    ],    "safety_settings": [      {        "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",        "threshold": "BLOCK_NONE"      },      {        "category": "HARM_CATEGORY_HATE_SPEECH",        "threshold": "BLOCK_NONE"      },      {        "category": "HARM_CATEGORY_HARASSMENT",        "threshold": "BLOCK_NONE"      },      {        "category": "HARM_CATEGORY_DANGEROUS_CONTENT",        "threshold": "BLOCK_NONE"      }    ],    "generation_config": {      "temperature": 0.3,      "topK": 40,      "topP": 0.95,      "candidateCount": 1,      "maxOutputTokens": 30720    }  },  "response": {    "candidates": [      {        "content": {          "parts": [            {              "text": <responce from gemini>"            }          ],          "role": "model"        },        "finishReason": "STOP",        "index": 0,        "safetyRatings": [          {            "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",            "probability": "NEGLIGIBLE"          },          {            "category": "HARM_CATEGORY_HATE_SPEECH",            "probability": "NEGLIGIBLE"          },          {            "category": "HARM_CATEGORY_HARASSMENT",            "probability": "NEGLIGIBLE"          },          {            "category": "HARM_CATEGORY_DANGEROUS_CONTENT",            "probability": "NEGLIGIBLE"          }        ]      }    ],    "promptFeedback": {      "safetyRatings": [        {          "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",          "probability": "NEGLIGIBLE"        },        {          "category": "HARM_CATEGORY_HATE_SPEECH",          "probability": "NEGLIGIBLE"        },        {          "category": "HARM_CATEGORY_HARASSMENT",          "probability": "NEGLIGIBLE"        },        {          "category": "HARM_CATEGORY_DANGEROUS_CONTENT",          "probability": "NEGLIGIBLE"        }      ]    }  },  "response.codes": [    200  ],  "response.response_tokens": {    "totalTokens": 308  },  "response.response_tokens.codes": [    200  ],  "finish": "2024-04-04 08:54:56"}
So what am I looking for exactly? Image may be NSFW.
Clik here to view.
😅


I also have another report which may be a little obscure - I am using the excellent QuickReply reloaded on my forum: https://boardtools.ru/QuickReply/

Which supports AJAX posting, very neat. But not for AI Labs, the response will be posted before the bot request is being made. Well, sometimes - sometimes it does work but more often not.

Anything that can be done there? For now I just turn off AJAX posting in the forums where AI bots are active but it's a bit of a shame.

Thanks!

Statistics: Posted by nou nou — Thu Apr 04, 2024 4:10 pm



Viewing all articles
Browse latest Browse all 2341

Trending Articles