Update extract_text_from_pdf.py

extract_text_from_pdf.py

@@ -28,8 +28,8 @@ class PDFTextExtractor:
             model_name (str): Name of the model to use for text processing.
         """
 
-        model_name="bartowski/Llama-3.2-1B-Instruct-GGUF"
-        filename = "Llama-3.2-1B-Instruct-Q5_K_S.gguf"
+        model_name="meta-llama/Llama-3.2-1B-Instruct"
+
         self.pdf_path = pdf_path
         self.output_path = output_path
         self.max_chars = 100000
@@ -38,17 +38,30 @@ class PDFTextExtractor:
         
         # Initialize model and tokenizer
         self.accelerator = Accelerator()
-        self.model = AutoModelForCausalLM.from_pretrained(model_name, gguf_file=filename, torch_dtype=torch.bfloat16).to(self.device)
-        self.tokenizer = AutoTokenizer.from_pretrained(model_name, gguf_file=filename)
+        self.model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16,use_safetensors=True,device_map=device)
+        self.tokenizer = AutoTokenizer.from_pretrained(model_name, use_safetensors=True)
         self.model, self.tokenizer = self.accelerator.prepare(self.model, self.tokenizer)
+
         
         # System prompt for text processing
         self.system_prompt = """
         You are a world class text pre-processor, here is the raw data from a PDF, please parse and return it in a way that is crispy and usable to send to a podcast writer.
+
+        The raw data is messed up with new lines, Latex math and you will see fluff that we can remove completely. Basically take away any details that you think might be useless in a podcast author's transcript.
         
-        Be smart and aggressive with removing details; you're only cleaning up the text without summarizing.
-        Here is the text:
-        """
+        Remember, the podcast could be on any topic whatsoever so the issues listed above are not exhaustive
+        
+        Please be smart with what you remove and be creative ok?
+        
+        Remember DO NOT START SUMMARIZING THIS, YOU ARE ONLY CLEANING UP THE TEXT AND RE-WRITING WHEN NEEDED
+        
+        Be very smart and aggressive with removing details, you will get a running portion of the text and keep returning the processed text.
+        
+        PLEASE DO NOT ADD MARKDOWN FORMATTING, STOP ADDING SPECIAL CHARACTERS THAT MARKDOWN CAPATILISATION ETC LIKES
+        
+        ALWAYS start your response directly with processed text and NO ACKNOWLEDGEMENTS about my questions ok?
+        Here is the text:"""
+    
     #@spaces.GPU
     def validate_pdf(self):
         """Check if the file exists and is a valid PDF."""
@@ -130,6 +143,8 @@ class PDFTextExtractor:
         
         processed_text = self.tokenizer.decode(output[0], skip_special_tokens=True)[len(prompt):].strip()
         return processed_text
+
+        
     #@spaces.GPU
     def clean_and_save_text(self):
         """Extract, clean, and save processed text to a file."""