chat(hash) to also return raw response + header object

[drnic]

Currently chat(messages) returns a hash {role: "assistant", content: "Welcome"} and there is no way to access the raw response object which contains usage data:

"usage":{"prompt_tokens":163,"prompt_time":0.059,"completion_tokens":481,"completion_time":1.591,"total_tokens":644,"total_time":1.65}

Nor does it return the HTTP header information that contains rate limit stats:

x-ratelimit-limit-requests: "14400"
x-ratelimit-limit-tokens: "7000"
x-ratelimit-remaining-requests: "14399"
x-ratelimit-remaining-tokens: "6818"
x-ratelimit-reset-requests: "6s"
x-ratelimit-reset-tokens: "1.559999999s"
x-request-id: "req_01hwe17kc9efg93xtwk30d5tx4"

Can we change chat() to return multiple response objects?

message, response, headers = @client.chat("Hello?")
# if you just want one
message, _ = @client.chat("Hello?)

Perhaps this mode is enabled via config @client.chat("Hello?", metadata: true)

[inspire22]

I'd love this too! Currently struggling to stay inside their rate limits & it's hard without better ability to show their headers. I think it should be enabled by default, or just auto-log with metadata: true., but better to return it as the other result imo.