Update app.py

app.py

@@ -1,63 +1,30 @@
 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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+from langserve import RemoteRunnable
+from pprint import pprint
+
+def get_response(input_text):
+    app = RemoteRunnable("https://sop-api-server.onrender.com/speckle_chat/")
+    for output in app.stream({"input": input_text}):
+        for key, value in output.items():
+            # Node
+            pprint(f"Node '{key}':")
+            # Optional: print full state at each node
+            # pprint.pprint(value["keys"], indent=2, width=80, depth=None)
+        pprint("\n---\n")
+    output = value['generation']
+    return output   
+
+# Create the UI In Gradio
+iface = gr.Interface(fn=get_response, 
+          inputs=gr.Textbox(
+          value="Enter your question"), 
+          outputs="textbox",  
+          title="Q&A over SOP docs",
+          description="Ask a question about SOP docs and get an answer from the AI assistant. This assistant looks up relevant documents and answers your code-related question.",
+          examples=[["How to fill out Form 3602A?"], 
+                  ["Give out cases for VR-based surgical procedures."],["Elaborate cases or indications for VR-based rehabiliations."]
+                  ],
+          theme=gr.themes.Soft(),
+          allow_flagging="never",)
+
+iface.launch(share=True) # put share equal to True for public URL