Upload app.py

app.py

@@ -8,6 +8,7 @@ import requests
 import logging
 import subprocess
 from llama_cpp import Llama  # Import Llama from llama_cpp
+import spacy
 
 # Configure logging
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
@@ -20,9 +21,21 @@ def install_requirements():
     except subprocess.CalledProcessError as e:
         logging.error(f"Failed to install requirements: {e}")
 
+# Function to download the spaCy model
+def download_spacy_model(model_name):
+    try:
+        subprocess.check_call([os.sys.executable, '-m', 'spacy', 'download', model_name])
+        logging.info(f"SpaCy model {model_name} downloaded successfully.")
+    except subprocess.CalledProcessError as e:
+        logging.error(f"Failed to download SpaCy model {model_name}: {e}")
+
 # Install requirements
 install_requirements()
 
+# Download the spaCy model if it doesn't exist
+if not spacy.util.is_package('en_core_web_lg'):
+    download_spacy_model('en_core_web_lg')
+
 # Create the directory if it doesn't exist
 local_dir = "models"
 os.makedirs(local_dir, exist_ok=True)
@@ -67,8 +80,8 @@ def respond(
     # Load the model with the maximum context length and control the maximum tokens in the response
     llm = Llama(
         model_path=model_path,
-        n_ctx=5000,  # Set the maximum context length
-        max_tokens=512  # Control the maximum number of tokens generated in the response
+        n_ctx=500,  # Set the maximum context length
+        max_tokens=500  # Control the maximum number of tokens generated in the response
     )
 
     agent = Agent(llm, db_path, system_prompt)
@@ -88,4 +101,4 @@ demo = gr.ChatInterface(
 )
 
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860)
+    demo.launch()