| import gradio as gr |
| from openai import OpenAI |
|
|
| api_key = "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" |
| client = OpenAI(api_key=api_key, base_url="https://api.perplexity.ai") |
|
|
| def predict(message, history): |
| history_openai_format = [] |
| |
| |
| |
| |
| |
| history_openai_format.append({"role": "user", "content": message}) |
| |
| response = client.chat.completions.create(model='sonar-small-chat', |
| messages= history_openai_format, |
| temperature=1.0, |
| stream=True) |
|
|
| partial_message = "" |
| for chunk in response: |
| if chunk.choices[0].delta.content is not None: |
| partial_message = partial_message + chunk.choices[0].delta.content |
| yield partial_message |
| |
| gr.ChatInterface(predict).launch() |
