Upload app.py

app.py

@@ -15,22 +15,6 @@ logger = logging.getLogger(__name__)
 repo_id = "QuantFactory/Meta-Llama-3-8B-Instruct-GGUF"
 filename = "Meta-Llama-3-8B-Instruct.Q8_0.gguf"
 
-def chunk_text(text, chunk_size=5000):
-    """
-    Splits the input text into chunks of specified size.
-
-    Args:
-        text (str): The input text to be chunked.
-        chunk_size (int): The size of each chunk in tokens.
-
-    Returns:
-        list: A list of text chunks.
-    """
-    words = text.split()
-    chunks = [' '.join(words[i:i + chunk_size]) for i in range(0, len(words), chunk_size)]
-    return chunks
-
-
 try:
         start_time = time.time()
         logger.info("Downloading Model....")
@@ -112,14 +96,11 @@ def respond(message, history, temperature, max_tokens):
 
     end_time = time.time()
     logger.info(f"Provider settings updated. Prompt Loaded.Time taken : {end_time - start_time} seconds.")
-    
-    chunks = chunk_text(message)
 
     start_time = time.time()
     logger.info("Generating responses...")
-    for chunk in chunks:
-        response = agent.get_chat_response(
-            chunk,
+    response = agent.get_chat_response(
+            message,
             llm_sampling_settings=settings,
             returns_streaming_generator = False, #generate streamer
             print_output = False