Upload app.py

app.py

@@ -1,44 +1,69 @@
+# app.py
 import gradio as gr
-from huggingface_hub import InferenceClient
+from src.agent import Agent
+from src.create_database import load_and_process_dataset  # Import from create_database.py
+import os
+import uuid
+import requests
+import logging
+from llama_cpp import Llama
 
-"""
-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")
+# Configure logging
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+
+# Create the directory if it doesn't exist
+local_dir = "models"
+os.makedirs(local_dir, exist_ok=True)
+
+# Specify the filename for the model
+filename = "unsloth.Q4_K_M.gguf"
+model_path = os.path.join(local_dir, filename)
+
+# Function to download the model file
+def download_model(repo_id, filename, save_path):
+    # Construct the URL for the model file
+    url = f"https://huggingface.co/{repo_id}/resolve/main/{filename}"
 
+    # Download the model file
+    response = requests.get(url)
+    if response.status_code == 200:
+        with open(save_path, 'wb') as f:
+            f.write(response.content)
+        print(f"Model downloaded to {save_path}")
+    else:
+        print(f"Failed to download model: {response.status_code}")
+
+# Download the model if it doesn't exist
+if not os.path.exists(model_path):
+    download_model("PurpleAILAB/Llama3.2-3B-uncensored-SQLi-Q4_K_M-GGUF", filename, model_path)
 
 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]})
+    model_path = "models/unsloth.Q4_K_M.gguf"  # Path to the downloaded model
+    db_path = "agent.db"
+    system_prompt = system_message
 
-    messages.append({"role": "user", "content": message})
+    # Check if the database exists, if not, initialize it
+    if not os.path.exists(db_path):
+        data_update_path = "data-update.txt"
+        keyword_dir = "keyword"  # Updated keyword directory
+        load_and_process_dataset(data_update_path, keyword_dir, db_path)
 
-    response = ""
+    # Load the model with the maximum context length and control the maximum tokens in the response
+    llm = Llama(
+        model_path=model_path,
+        n_ctx=5072,  # Set the maximum context length
+        max_tokens=512  # Control the maximum number of tokens generated in the 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
+    agent = Agent(llm, db_path, system_prompt)
+    user_id = str(uuid.uuid4())  # Generate a unique user ID for each session
 
+    response = agent.process_query(user_id, message)
+    return response
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
@@ -46,19 +71,9 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 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)",
-        ),
+        gr.Textbox(value="Vous êtes l'assistant intelligent de Les Chronique MTC. Votre rôle est d'aider les visiteurs en expliquant le contenu des Chroniques, Flash Infos et Chronique-FAQ de Michel Thomas. Utilisez le contexte fourni pour améliorer vos réponses et veillez à ce qu'elles soient précises et pertinentes.", label="System message"),
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(server_name="0.0.0.0", server_port=7860)