Update app.py

app.py

@@ -1,63 +1,51 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    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)",
-        ),
-    ],
-)
-
+import os
+from openai import OpenAI
+import time
+read_key = os.environ.get('passw_gaidio', None)
+
+assistant_id = os.environ.get('asst_id', None)
+client = OpenAI(organization=os.environ.get('AI_org', None), api_key=os.environ.get('AI_key', None))
+
+# Create a thread
+thread = client.beta.threads.create()
+print(thread.id)
+
+def main(query,history):
+    # Add a message to a Thread
+    message = client.beta.threads.messages.create(
+        thread_id=thread.id,
+        role="user",
+        content=query
+    )
+
+    # Run the assistant
+    run = client.beta.threads.runs.create(
+        thread_id=thread.id,
+        assistant_id=assistant_id,
+    )
+
+    while True:
+        time.sleep(3)
+
+        run_status = client.beta.threads.runs.retrieve(
+            thread_id=thread.id,
+            run_id=run.id
+        )
+
+        if run_status.status == 'completed':
+            messages = client.beta.threads.messages.list(
+                thread_id=thread.id
+            )
+            response = ""
+            for msg in messages.data:
+                role = msg.role
+                content = msg.content[0].text.value
+                response += f"{role.capitalize()}: {content}\n\n"
+                break
+            return response+ "\n\n"
+        else:
+            continue
 
 if __name__ == "__main__":
-    demo.launch()
+    iface = gr.ChatInterface(fn=main, title="Gaidio (Proof of concept)", description="Fråga mig om uppgiftskrav!").launch(auth=("user", read_key))