import pgml

client= pgml.OpenSourceAI()

results= client.chat_completions_create(

"mistralai/Mistral-7B-Instruct-v0.1",

"HuggingFaceH4/zephyr-7b-beta",

[

{

"role":"system",

constpgml=require("pgml");

constclient=pgml.newOpenSourceAI();

constresults=client.chat_completions_create(

"mistralai/Mistral-7B-Instruct-v0.1",

"HuggingFaceH4/zephyr-7b-beta",

[

{

role:"system",

],

"created":1701291672,

"id":"abf042d2-9159-49cb-9fd3-eef16feb246c",

"model":"mistralai/Mistral-7B-Instruct-v0.1",

"model":"HuggingFaceH4/zephyr-7b-beta",

"object":"chat.completion",

"system_fingerprint":"eecec9d4-c28b-5a27-f90b-66c3fb6cee46",

"usage": {

We don't charge per token, so OpenAI “usage” metrics are not particularly relevant. We'll be extending this data with more direct CPU/GPU resource utilization measurements for users who are interested, or need to pass real usage based pricing on to their own customers.

{% endhint %}

The above is an example using our open-source AI SDK withmistral, an incredibly popular and highly efficient 7 billion parameter model.

The above is an example using our open-source AI SDK withzephyr-7b-beta, an incredibly popular and highly efficient 7 billion parameter model.

Notice there is near one to one relation between the parameters and return type of OpenAI’s`chat.completions.create` and our`chat_completion_create`.