Upload app.py

app.py

@@ -6,14 +6,15 @@ import gradio as gr
 from sentence_transformers import SentenceTransformer
 from langchain_community.vectorstores import FAISS
 from langchain.embeddings.base import Embeddings
+from gradio_client import Client
 from tqdm import tqdm
 
 # Configuration
-QWEN_API_URL = os.getenv("QWEN_API_URL", "Qwen/Qwen2.5-Max-Demo")  # Environment variable for Qwen API URL
+QWEN_API_URL = os.getenv("QWEN_API_URL", "https://huggingface.co/spaces/Qwen/Qwen2.5-Max-Demo")  # Ensure this URL points to the correct Gradio Space API endpoint.
 CHUNK_SIZE = 800
 TOP_K_RESULTS = 150
 SIMILARITY_THRESHOLD = 0.4
-PASSWORD_HASH = os.getenv("PASSWORD_HASH", "abc12345")  # Environment variable for password
+PASSWORD_HASH = os.getenv("PASSWORD_HASH", "abc12345")  # Use an environment variable for security
 
 BASE_SYSTEM_PROMPT = """
 Répondez en français selon ces règles :
@@ -104,13 +105,9 @@ def create_new_database(file_content: str, db_name: str, password: str, progress
             return "No valid chunks generated. Database creation failed.", []
 
         logging.info(f"Creating {len(chunks)} chunks...")
-        progress(0, desc="Starting embedding process...")
         
         # Create embeddings with progress tracking
-        embeddings_list = []
-        for i, chunk in enumerate(chunks):
-            progress(i / len(chunks), desc=f"Embedding chunk {i+1}/{len(chunks)}")
-            embeddings_list.append(embeddings.embed_query(chunk))
+        embeddings_list = [embeddings.embed_query(chunk) for chunk in tqdm(chunks)]
         
         # Create FAISS database
         vector_store = FAISS.from_embeddings(
@@ -121,13 +118,6 @@ def create_new_database(file_content: str, db_name: str, password: str, progress
         # Save FAISS database locally
         vector_store.save_local(".")
         
-        # Verify files were created successfully
-        if not os.path.exists(faiss_file) or not os.path.exists(pkl_file):
-            return "Failed to save FAISS database files. Please check file permissions.", []
-        
-        logging.info(f"FAISS database files created: {faiss_file}, {pkl_file}")
-
-        # Update the list of available databases
         db_list = [os.path.splitext(f)[0].replace("-index", "") for f in os.listdir(".") if f.endswith(".faiss")]
         
         return f"Database '{db_name}' created successfully.", db_list
@@ -137,7 +127,7 @@ def create_new_database(file_content: str, db_name: str, password: str, progress
         return f"Error creating database: {str(e)}", []
 
 def generate_response(user_input: str, db_name: str) -> str:
-    """Generate response using Qwen2.5 MAX"""
+    """Generate response using Qwen2.5-Max Demo API"""
     try:
         if not db_name:
             return "Please select a database to chat with."
@@ -148,18 +138,11 @@ def generate_response(user_input: str, db_name: str) -> str:
         if not os.path.exists(faiss_file) or not os.path.exists(pkl_file):
             return f"Database '{db_name}' does not exist."
 
-        vector_store = FAISS.load_local(".", embeddings, allow_dangerous_deserialization=True)
+        vector_store = FAISS.load_local(".", embeddings)
 
-        # Perform contextual search in the database
-        docs_scores = vector_store.similarity_search_with_score(
-            user_input, 
-            k=TOP_K_RESULTS * 3
-        )
+        docs_scores = vector_store.similarity_search_with_score(user_input, k=TOP_K_RESULTS * 3)
         
-        filtered_docs = [
-            (doc, score) for doc, score in docs_scores 
-            if score < SIMILARITY_THRESHOLD
-        ]
+        filtered_docs = [(doc, score) for doc, score in docs_scores if score < SIMILARITY_THRESHOLD]
         
         filtered_docs.sort(key=lambda x: x[1])
         
@@ -168,12 +151,9 @@ def generate_response(user_input: str, db_name: str) -> str:
         
         best_docs = [doc for doc, _ in filtered_docs[:TOP_K_RESULTS]]
         
-        context = "\n".join(
-            f"=== Source {i+1} ===\n{doc.page_content}\n" 
-            for i, doc in enumerate(best_docs)
-        )
+        context = "\n".join(f"=== Source {i+1} ===\n{doc.page_content}\n" for i, doc in enumerate(best_docs))
         
-        client = Client(QWEN_API_URL, verbose=False)
+        client = Client(QWEN_API_URL)
         
         response = client.predict(
             query=user_input,
@@ -190,27 +170,20 @@ def generate_response(user_input: str, db_name: str) -> str:
         return "Réponse indisponible - Veuillez reformuler votre question."
 
     except Exception as e:
-        logging.error(f"Generation error: {str(e)}", exc_info=True)
-        return "Erreur de génération - Veuillez réessayer."
+        logging.error(f"Error generating response: {str(e)}")
+        return "Erreur de génération."
 
-# Initialize models and vector store
+# Initialize models and Gradio app
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model = SentenceTransformer("cnmoro/snowflake-arctic-embed-m-v2.0-cpu", device=device, trust_remote_code=True)
+model = SentenceTransformer("cnmoro/snowflake-arctic-embed-m-v2.0-cpu", device=device)
 embeddings = LocalEmbeddings(model)
 
-# Gradio interface setup remains unchanged from your original code.
 with gr.Blocks() as app:
-    gr.Markdown("# Local Tech Knowledge Assistant")
-
-    # Shared state for database list
-    db_list_state = gr.State([])
-
-    def update_db_list():
-        """Update the list of available databases"""
-        return [os.path.splitext(f)[0].replace("-index", "") for f in os.listdir(".") if f.endswith(".faiss")]
-
+    gr.Markdown("# Knowledge Assistant")
+    
     with gr.Tab("Create Database"):
-        gr.Markdown("## Create a New FAISS Database")
-        
+      # Database creation UI setup
+    
 if __name__ == "__main__":
     app.launch(server_name="0.0.0.0", server_port=7860)
+