Update app.py

app.py

@@ -1,70 +1,65 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+from fastapi import FastAPI, Request
+from pydantic import BaseModel
+from openai import OpenAI
+import requests
+import time
 
+app = FastAPI()
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    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")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
+# -----------------------
+# API Keys & Config
+# -----------------------
+OPENROUTER_API_KEY = "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"
+PULSE_BEARER_TOKEN = "3673|1Cg9jkntwA0827JLsmIoUoR4E2hOj2sLkMwEYF8dcdd9ed59"
+COMPANY_ID = "4"
+BASE_URL = "https://pulse-survey.ospreyibs.com/api/v1"
 
-    messages.append({"role": "user", "content": message})
+client = OpenAI(
+    base_url="https://openrouter.ai/api/v1",
+    api_key=OPENROUTER_API_KEY
+)
 
-    response = ""
+headers = {
+    "Authorization": f"Bearer {PULSE_BEARER_TOKEN}",
+    "Company-Id": COMPANY_ID,
+    "Accept": "application/json",
+    "Content-Type": "application/json"
+}
 
-    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
 
-        response += token
-        yield response
+class QuestionRequest(BaseModel):
+    question_text: str
 
 
-"""
-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"),
-        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)",
-        ),
-    ],
-)
+@app.post("/generate_feedback/")
+async def generate_feedback(request: QuestionRequest):
+    """
+    Endpoint to generate answer + recommendation for a question.
+    """
+    question = request.question_text
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+    # Generate Answer
+    prompt = f"Answer this question positively: {question}"
+    answer_response = client.chat.completions.create(
+        model="meta-llama/llama-3.3-70b-instruct",
+        messages=[
+            {"role": "system", "content": "You are a helpful AI survey assistant."},
+            {"role": "user", "content": prompt}
+        ]
+    )
+    answer = answer_response.choices[0].message.content.strip()
 
+    # Generate Recommendation
+    recommendation_prompt = f"Based on this answer: {answer}, write one professional recommendation or reflection tip."
+    rec_response = client.chat.completions.create(
+        model="meta-llama/llama-3.3-70b-instruct",
+        messages=[
+            {"role": "user", "content": recommendation_prompt}
+        ]
+    )
+    recommendation = rec_response.choices[0].message.content.strip()
 
-if __name__ == "__main__":
-    demo.launch()
+    return {
+        "answer": answer,
+        "recommendation": recommendation
+    }