Hello we have been using the proxy integration so far without any issue, now we would like to explore the async integration. going through the documentation provided in the page :
https://docs.helicone.ai/getting-started/integration-method/openaiWe are using the curl method, however we were not able to to make it work for some reason. most likely we are doing something wrong in terms of passing the data in format expected. i will really appreciate if you can assist and give me a sample curl format that we need to pass to helicone end
point to make it work using the following request and response body from chatgpt API. 🙏
{
"model": "gpt-3.5-turbo-0125",
"messages": [
{
"role": "system",
"content": "you are helpful assistant."
},
{
"role": "user",
"content": "what is AI"
}
],
"temperature": 0.2,
"max_tokens": 4095,
"top_p": 1,
"frequency_penalty": 0,
"presence_penalty": 0,
"user": "9"
}{
"id": "chatcmpl-98fzFsC4tezpBQFfoHpNKJus90suy",
"object": "chat.completion",
"created": 1711855049,
"model": "gpt-3.5-turbo-0125",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Ai stands for artificial intelligence, which refers to the simulation of human intelligence processes by machines, especially computer systems. This includes learning, reasoning, problem-solving, perception, and language understanding. Ai is used in a wide range of applications, from virtual assistants like Siri and Alexa to self-driving cars and medical diagnosis systems."
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 127,
"completion_tokens": 60,
"total_tokens": 187
},
"system_fingerprint": "fp_3bc1b5746c"
}