feat: Change AI model API dependency to GROQ

.gitignore

@@ -0,0 +1,11 @@
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv
+.env

.python-version

@@ -0,0 +1 @@
+3.10

app.py

@@ -1,51 +1,57 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+from openai import OpenAI
+from dotenv import load_dotenv
 
+load_dotenv()
 
 def respond(
     message,
-    history: list[dict[str, str]],
+    history,
     system_message,
     max_tokens,
     temperature,
     top_p,
-    hf_token: gr.OAuthToken,
 ):
-    """
-    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
-    """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
+    api_key = os.getenv("GROQ_API_KEY")
+    if not api_key:
+        raise RuntimeError("GROQ_API_KEY is not set")
 
-    messages = [{"role": "system", "content": system_message}]
+    client = OpenAI(
+        api_key=api_key,
+        base_url="https://api.groq.com/openai/v1",
+    )
 
-    messages.extend(history)
+    def sanitize_messages(history):
+        return [
+            {"role": m["role"], "content": m["content"]}
+            for m in history
+        ]
 
+    messages = [{"role": "system", "content": system_message}]
+    messages.extend(sanitize_messages(history))
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    response_text = ""
 
-    for message in client.chat_completion(
-        messages,
+    stream = client.chat.completions.create(
+        model="qwen/qwen3-32b",
+        messages=messages,
         max_tokens=max_tokens,
-        stream=True,
         temperature=temperature,
         top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+        stream=True,
+    )
+
+    for chunk in stream:
+        if chunk.choices[0].delta.content:
+            response_text += chunk.choices[0].delta.content
+            yield response_text
 
-        response += token
-        yield response
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 chatbot = gr.ChatInterface(
     respond,
-    type="messages",
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
@@ -60,11 +66,5 @@ chatbot = gr.ChatInterface(
     ],
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
 if __name__ == "__main__":
-    demo.launch()
+    chatbot.launch()

pyproject.toml

@@ -0,0 +1,11 @@
+[project]
+name = "chatbot"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "dotenv>=0.9.9",
+    "gradio[oauth]>=6.4.0",
+    "openai>=2.15.0",
+]