Update app.py

app.py

@@ -1,63 +1,125 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import cohere
+import os
+import re
+import uuid
+import secrets
 
-"""
-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}]
+cohere_api_key = os.getenv("OrLcCzgoAtSg8TkG4VMB5G33H84Znq2kj3JjNIk9")
+co = cohere.Client(cohere_api_key, client_name="huggingface-rp")
 
-    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})
+def trigger_example(example):
+    chat, updated_history = generate_response(example)
+    return chat, updated_history
+        
+def generate_response(user_message, cid, token, history=None):
 
-    response = ""
+    if not token:
+        raise gr.Error("Error loading.")
+        
+    if history is None:
+        history = []
+    if cid == "" or None:    
+        cid = str(uuid.uuid4())
 
-    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
+    print(f"cid: {cid} prompt:{user_message}")
+    
+    history.append(user_message)
+    
+    stream = co.chat_stream(message=user_message, conversation_id=cid, model='command-r-plus', connectors=[], temperature=0.3)
+    
+    output = ""
+    
+    for idx, response in enumerate(stream):
+        if response.event_type == "text-generation":
+            output += response.text
+        if idx == 0:
+            history.append(" " + output)
+        else:
+            history[-1] = output
+        chat = [
+            (history[i].strip(), history[i + 1].strip())
+            for i in range(0, len(history) - 1, 2)
+        ] 
+        yield chat, history, cid
+        
+    return chat, history, cid
+    
 
-        response += token
-        yield response
+def clear_chat():
+    return [], [], str(uuid.uuid4())
 
+
+examples = [
+    "Pouvez-vous expliquer les règles relatives aux heures supplémentaires selon le Code du travail ?",
+    "Quels sont les droits et obligations concernant les congés payés selon le Code du travail ?",
+    "Quelles sont les conditions requises pour un licenciement pour motif économique en vertu du Code du travail ?",
+    "Quelles sont les mesures prévues par le Code du travail en cas de harcèlement au travail ?",
+   
+]
+
+custom_css = """
+#logo-img {
+    border: none !important;
+}
+#chat-message {
+    font-size: 14px;
+    min-height: 300px;
+}
 """
-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)",
-        ),
-    ],
-)
 
+with gr.Blocks(analytics_enabled=False, css=custom_css) as demo:
+    cid = gr.State("")
+    token = gr.State(value=None)
+    
+    with gr.Row():
+        with gr.Column(scale=1):
+            #gr.Image("logoplus.png", elem_id="logo-img", show_label=False, show_share_button=False, show_download_button=False)
+        with gr.Column(scale=3):
+            #gr.Markdown(""" """)
+            
+    with gr.Column():
+        with gr.Row():
+            chatbot = gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True)
+        
+        with gr.Row():
+            user_message = gr.Textbox(lines=1, placeholder="Question ...", label="Input", show_label=False)
+
+      
+        with gr.Row():
+            submit_button = gr.Button("Envoyer")
+            clear_button = gr.Button("Clear chat")
+
+                        
+        history = gr.State([])
+        
+        user_message.submit(fn=generate_response, inputs=[user_message, cid, token, history], outputs=[chatbot, history, cid], concurrency_limit=32)
+        submit_button.click(fn=generate_response, inputs=[user_message, cid, token, history], outputs=[chatbot, history, cid], concurrency_limit=32)
+        
+        clear_button.click(fn=clear_chat, inputs=None, outputs=[chatbot, history, cid], concurrency_limit=32)
+
+        user_message.submit(lambda x: gr.update(value=""), None, [user_message], queue=False)
+        submit_button.click(lambda x: gr.update(value=""), None, [user_message], queue=False)
+        clear_button.click(lambda x: gr.update(value=""), None, [user_message], queue=False)
+        
+        with gr.Row():
+            gr.Examples(
+                examples=examples,
+                inputs=user_message,
+                cache_examples=False,
+                fn=trigger_example,
+                outputs=[chatbot],
+                examples_per_page=100
+            )
+
+    demo.load(lambda: secrets.token_hex(16), None, token)
 
 if __name__ == "__main__":
-    demo.launch()
+    # demo.launch(debug=True)
+    try:
+        demo.queue(api_open=False, max_size=40).launch(show_api=False)
+    except Exception as e:
+        print(f"Error: {e}")