app en gradio

.env

@@ -0,0 +1,2 @@
+GEAI_API_KEY = "default_PMzB2IbcL3OWamWX0XYsUtR8SCOcLFPZ3cAmokIbchcYwK6KbQBtX1eJ5BLrCfsFqxRnJ0CgyM2yiLVnPzHh9Q"
+GEAI_API_BASE_URL = "https://api.saia.ai/chat"

.gitignore

@@ -0,0 +1,2 @@
+.gradiotest
+.gradiotest/lib/python3.12/site-packages/aiofiles/base.py

app.py

@@ -1,10 +1,19 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from openai import OpenAI
+import os
+from dotenv import load_dotenv
+
+# Load environment variables from .env file
+load_dotenv()
 
 """
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+OpenAI Chat Completion API integration
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+GEAI_API_KEY = os.getenv("GEAI_API_KEY")
+GEAI_API_BASE_URL = os.getenv("GEAI_API_BASE_URL")
+
+client = OpenAI(api_key=GEAI_API_KEY, base_url=GEAI_API_BASE_URL)
 
 
 def respond(
@@ -27,17 +36,18 @@ def respond(
 
     response = ""
 
-    for message in client.chat_completion(
-        messages,
+    for chunk in client.chat.completions.create(
+        model="openai/gpt-4o-mini",
+        messages=messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+        if chunk.choices[0].delta.content is not None:
+            token = chunk.choices[0].delta.content
+            response += token
+            yield response
 
 
 """

requirements.txt

@@ -1 +1,4 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+openai
+python-dotenv
+gradio