Unrecognized request argument supplied: top_k

[tazztone]

Hi. i think your google API update broke openAI API ? it was working before the update a few days ago.

setup

error:

terminal:

WARNING:[auto-llm]:[][AutoLLM][getReq][llm_text_ur_prompt]beautiful otherwordly place
WARNING:[auto-llm]:[][AutoLLM][getReq][Header]{'Content-Type': 'application/json', 'Authorization': 'Bearer sk-REDACTED API KEY'}
WARNING:[auto-llm]:[Auto-LLM][][]Req URL=> https://api.openai.com/v1/chat/completions
WARNING:[auto-llm]:[X][Auto-LLM][][]Missing LLM Server? err='choices' response={
  "error": {
    "message": "Unrecognized request argument supplied: top_k",
    "type": "invalid_request_error",
    "param": null,
    "code": null
  }
}

thank you :) cheers.

[xxlinxx]

i want help u debug, but i didnt have enought Credit on openai... Usage limits

• accroding openai manual, that suggest use temp or top_p not both
• i will disable top_k on openai request
• okay, let me try try: https://console.groq.com/keys

--------------- https://platform.openai.com/docs/api-reference/chat/create

temperature number or null

Optional Defaults to 1 What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

We generally recommend altering this or top_p but not both.

top_p number or null

Optional Defaults to 1 An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering this or temperature but not both.

[tazztone]

i didnt have enought Credit on openai.

try https://console.groq.com/keys it it free and has openAI compatible api key just put: URL: https://api.groq.com/openai/v1 MODEL: llama-3.1-8b-instant or llama-3.1-70b-versatile

[tazztone]

works again. thanks very much!