Update app.py

app.py

@@ -1,43 +1,41 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import os
+import requests
 
+CHAT_URL = os.getenv("CHAT_URL")
+PROJECT_ID = os.getenv("PROJECT_ID")
 
 def respond(
     message,
     history: list[dict[str, str]],
     system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
+    token,
+    # 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")
 
-    messages = [{"role": "system", "content": system_message}]
+    print("[UPDATE VAR]", UPDATE_VAR)
 
-    messages.extend(history)
+    req = requests.post(
+        CHAT_URL,
+        json={
+            "project_id": PROJECT_ID,
+            "session_id":system_message,
+            "user_input":message,
+            "output_variables": ["results"]
+        },
+        headers={"Authorization" : f"Bearer {token}"}
+    )
 
-    messages.append({"role": "user", "content": message})
+    print("[REQ CONTENT]", req.content)
 
-    response = ""
+    out = req.json()["data"]["results"]
 
-    for message in client.chat_completion(
-        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
+    print("[OUT]",out)
 
-        response += token
-        yield response
+    return out.encode('utf-8').decode('unicode_escape')
 
 
 """
@@ -47,23 +45,23 @@ 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"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+        gr.Textbox(value="<TEST_123>", label="session_id"),
+        gr.Textbox(value="[TOKEN]", label="token"),
+        # gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        # gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        # gr.Slider(
+        #     minimum=0.1,
+        #     maximum=1.0,
+        #     value=0.95,
+        #     step=0.05,
+        #     label="Top-p (nucleus sampling)",
+        # ),
     ],
 )
 
 with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
     chatbot.render()
+    title = gr.HTML("<h3>Use #ai to ask the ai</h3>")
 
 
 if __name__ == "__main__":