The documentation is missing some details: <a href="https://docs.lambdalabs.com/public-cloud/lambda-chat-api/" rel="nofollow">https://docs.lambdalabs.com/public-cloud/lambda-chat-api/</a><p>When I run a prompt through it I get this back:<p><pre><code> {
"id": "chat-dea5c8eddcfa4ad08d488f2501f1b3b4",
"object": "chat.completion",
"created": 1730717593,
"model": "hermes3-405b",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "The 2020 World Series was played at Globe Life Field in Arlington, Texas. Due to the COVID-19 pandemic, the entire series was held at this neutral site to reduce travel and potential exposure to the virus."
},
"finish_reason": "stop",
"content_filter_results": {
"hate": {
"filtered": false
},
"self_harm": {
"filtered": false
},
"sexual": {
"filtered": false
},
"violence": {
"filtered": false
},
"jailbreak": {
"filtered": false,
"detected": false
},
"profanity": {
"filtered": false,
"detected": false
}
}
}
],
"usage": {
"prompt_tokens": 65,
"completion_tokens": 45,
"total_tokens": 110,
"prompt_tokens_details": null,
"completion_tokens_details": null
},
"system_fingerprint": ""
}
</code></pre>
Those content_filter_results look interesting - especially if I can turn those options on or off (I'd like to experiment with the jailbreak one for example) - but they aren't mentioned in the documentation at the moment.