Update app.py

app.py

@@ -1,63 +1,82 @@
+import os
 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("emizemani/editlyai-gguf/editlyai.gguf")
-
-
-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)",
-        ),
-    ],
+from huggingface_hub import hf_hub_download
+from llama_cpp import Llama
+from llama_cpp_agent import LlamaCppAgent, MessagesFormatterType
+from llama_cpp_agent.providers import LlamaCppPythonProvider
+from llama_cpp_agent.chat_history import BasicChatHistory
+from llama_cpp_agent.chat_history.messages import Roles
+
+# Set the repository ID and the filename for the model
+repo_id = "emizemani/editlyai-gguf"
+model_filename = "editlyai.gguf"
+
+# Path to store the downloaded model
+model_path = f"./models/{model_filename}"
+
+# Download the model if it's not already downloaded
+if not os.path.exists(model_path):
+    hf_hub_download(
+        repo_id=repo_id,
+        filename=model_filename,
+        local_dir="./models"
+    )
+
+# Initialize the Llama model
+llm = Llama(
+    model_path=model_path,
+    flash_attn=True,
+    n_gpu_layers=81,  # Adjust based on your model's requirements
+    n_batch=1024,
+    n_ctx=8192,
 )
 
+def respond(message, system_message):
+    # Define the provider and agent for interaction
+    provider = LlamaCppPythonProvider(llm)
+    agent = LlamaCppAgent(
+        provider,
+        system_prompt=system_message,
+        predefined_messages_formatter_type=MessagesFormatterType.GEMMA_2,
+        debug_output=True
+    )
+
+    # Default settings for the model interaction
+    settings = provider.get_provider_default_settings()
+    messages = BasicChatHistory()
+    messages.add_message({'role': Roles.system, 'content': system_message})
+    messages.add_message({'role': Roles.user, 'content': message})
+
+    # Get responses as a stream from the model
+    stream = agent.get_chat_response(
+        message,
+        llm_sampling_settings=settings,
+        chat_history=messages,
+        returns_streaming_generator=True,
+        print_output=False
+    )
+
+    output = ""
+    for data in stream:
+        output += data
+        yield output
+
+# Define a comprehensive system prompt for Editly AI
+system_prompt = "Hello, I am Editly AI, your intelligent text editing assistant. " \
+                "I specialize in correcting grammar, enhancing clarity, and refining the style of your text. " \
+                "Please type the text you want edited, and I will provide suggestions to improve it."
+
+# Create the Gradio interface
+demo = gr.Interface(
+    fn=respond,
+    inputs=[
+        gr.Textbox(label="Enter your text here", placeholder="Type here..."),
+        gr.Textbox(default=system_prompt, label="System message", visible=False),
+    ],
+    outputs="text",
+    title="Editly AI - Text Editing Assistant",
+    description="Interact with Editly AI to refine and enhance your text."
+)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()