Update app.py

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 from gradio_client import Client
-import os
+from huggingface_hub import HfApi
 import logging
 import time  # Import time module for adding delays
 
@@ -27,38 +27,32 @@ def call_api(prompt):
         logger.error(f"API call failed: {e}")
         raise gr.Error(f"API call failed: {str(e)}")
 
-# Function to segment the text file into chunks of 1500 words
-def segment_text(file_path):
-    try:
-        logger.info(f"Reading file: {file_path}")
-        # Try reading with UTF-8 encoding first
-        with open(file_path, "r", encoding="utf-8") as f:
-            text = f.read()
-        logger.info("File read successfully with UTF-8 encoding.")
-    except UnicodeDecodeError:
-        logger.warning("UTF-8 encoding failed. Trying latin-1 encoding.")
-        # Fallback to latin-1 encoding if UTF-8 fails
-        with open(file_path, "r", encoding="latin-1") as f:
-            text = f.read()
-        logger.info("File read successfully with latin-1 encoding.")
-    except Exception as e:
-        logger.error(f"Failed to read file: {e}")
-        raise gr.Error(f"Failed to read file: {str(e)}")
-    
+# Function to segment the text into chunks of 1500 words
+def segment_text(text):
     # Split the text into chunks of 1500 words
     words = text.split()
     chunks = [" ".join(words[i:i + 1500]) for i in range(0, len(words), 1250)]
     logger.info(f"Segmented text into {len(chunks)} chunks.")
     return chunks
 
-# Function to process the text file and make API calls with rate limiting
+# Function to process the text and make API calls with rate limiting
 def process_text(file, prompt):
     try:
         logger.info("Starting text processing...")
         
-        # Segment the text file into chunks
-        file_path = file.name if hasattr(file, "name") else file
-        chunks = segment_text(file_path)
+        # Read the text directly from the uploaded file
+        text = file.decode('utf-8')  # Assuming the file is encoded in UTF-8
+        
+        # Segment the text into chunks
+        chunks = segment_text(text)
+        
+        # Initialize Hugging Face API
+        hf_api = HfApi(token=os.environ.get("HUGGINGFACE_TOKEN"))
+        if not hf_api.token:
+            raise ValueError("Hugging Face token not found in environment variables.")
+        
+        # Repository name on Hugging Face Hub
+        repo_name = "TeacherPuffy/book2"
         
         # Process each chunk with a 15-second delay between API calls
         results = []
@@ -70,6 +64,20 @@ def process_text(file, prompt):
                 results.append(result)
                 logger.info(f"Chunk {idx + 1} processed successfully.")
                 
+                # Upload the chunk directly to Hugging Face
+                try:
+                    logger.info(f"Uploading chunk {idx + 1} to Hugging Face...")
+                    hf_api.upload_file(
+                        path_or_fileobj=result.encode('utf-8'),  # Convert result to bytes
+                        path_in_repo=f"output_{idx}.txt",  # File name in the repository
+                        repo_id=repo_name,
+                        repo_type="dataset",
+                    )
+                    logger.info(f"Chunk {idx + 1} uploaded to Hugging Face successfully.")
+                except Exception as e:
+                    logger.error(f"Failed to upload chunk {idx + 1} to Hugging Face: {e}")
+                    raise gr.Error(f"Failed to upload chunk {idx + 1} to Hugging Face: {str(e)}")
+                
                 # Wait 15 seconds before the next API call
                 if idx < len(chunks) - 1:  # No need to wait after the last chunk
                     logger.info("Waiting 15 seconds before the next API call...")
@@ -79,7 +87,7 @@ def process_text(file, prompt):
                 logger.error(f"Failed to process chunk {idx + 1}: {e}")
                 raise gr.Error(f"Failed to process chunk {idx + 1}: {str(e)}")
         
-        return "All chunks processed successfully."
+        return "All chunks processed and uploaded to Hugging Face."
     
     except Exception as e:
         logger.error(f"An error occurred during processing: {e}")