Update app.py

app.py

@@ -1,63 +1,88 @@
 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 requests, json
 
+public_ip = '71.202.66.108'
+
+model = 'llama3.1:latest' #You can replace the model name if needed
+context = [] 
+
+
+import gradio as gr
+
+# ollama_serve = f"http://{mac_pro_ip}:11434/api/generate"
+ollama_serve = f"http://{public_ip}:11434/api/generate"
+
+#Call Ollama API
+def generate(prompt, context, top_k, top_p, temp):
+    r = requests.post(ollama_serve,
+                     json={
+                         'model': model,
+                         'prompt': prompt,
+                         'context': context,
+                         'options':{
+                             'top_k': top_k,
+                             'temperature':top_p,
+                             'top_p': temp
+                         }
+                     },
+                     stream=True)
+    r.raise_for_status()
+
+ 
+    response = ""  
+
+    for line in r.iter_lines():
+        body = json.loads(line)
+        response_part = body.get('response', '')
+        print(response_part)
+        if 'error' in body:
+            raise Exception(body['error'])
+
+        response += response_part
+
+        if body.get('done', False):
+            context = body.get('context', [])
+            return response, context
+
+
+
+def chat(input, chat_history, top_k, top_p, temp):
+
+    chat_history = chat_history or []
+
+    global context
+    output, context = generate(input, context, top_k, top_p, temp)
+
+    chat_history.append((input, output))
+
+    return chat_history, chat_history
+  #the first history in return history, history is meant to update the 
+  #chatbot widget, and the second history is meant to update the state 
+  #(which is used to maintain conversation history across interactions)
+
+
+#########################Gradio Code##########################
+block = gr.Blocks()
+
+
+with block:
+
+    gr.Markdown("""<h1><center> Trashcan AI </center></h1>
+    """)
+
+    chatbot = gr.Chatbot()
+    message = gr.Textbox(placeholder="Type here")
+
+    state = gr.State()
+    with gr.Row():
+        top_k = gr.Slider(0.0,100.0, label="top_k", value=40, info="Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)")
+        top_p = gr.Slider(0.0,1.0, label="top_p", value=0.9, info=" Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)")
+        temp = gr.Slider(0.0,2.0, label="temperature", value=0.8, info="The temperature of the model. Increasing the temperature will make the model answer more creatively. (Default: 0.8)")
+
+
+    submit = gr.Button("SEND")
+
+    submit.click(chat, inputs=[message, state, top_k, top_p, temp], outputs=[chatbot, state])
 
 if __name__ == "__main__":
-    demo.launch()
+    block.launch()