Delete spelling_grammar_checker.py

spelling_grammar_checker.py

@@ -1,96 +0,0 @@
-import json
-import logging
-from huggingface_hub import hf_hub_download
-from llama_cpp import Llama
-from cv_prompt import get_spelling_grammar_prompt
-from ocr_utils import combine_ocr_results, extract_text_aws, extract_text_doctr, extract_text_easyocr, extract_text_paddleocr, load_models, detect_language
-from config import weights
-
-# Configure logging
-logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
-
-def load_model():
-    try:
-        model_path = hf_hub_download("TheBloke/Mistral-7B-Instruct-v0.2-GGUF", filename="mistral-7b-instruct-v0.2.Q4_K_M.gguf")
-        return Llama(model_path=model_path, n_ctx=32768, n_gpu_layers=2)
-    except Exception as e:
-        logging.error(f"Error loading model: {str(e)}")
-        return None
-
-llm = load_model()
-
-def load_error_scoring():
-    try:
-        with open('error_scoring.json', 'r') as file:
-            return json.load(file)
-    except Exception as e:
-        logging.error(f"Error loading error scoring: {str(e)}")
-        return None
-
-error_scoring = load_error_scoring()
-
-def get_error_score(error_percentage):
-    if error_scoring is None:
-        logging.error("Error scoring data not loaded")
-        return 0
-    
-    for score_range in error_scoring['error_scores']:
-        if score_range['min'] <= error_percentage < score_range['max']:
-            return score_range['score']
-    return error_scoring['error_scores'][-1]['score']  # Return the last score if percentage is 100%
-
-def check_spelling_and_grammar(text):
-    if llm is None:
-        logging.error("LLM model not loaded")
-        return 0, 0
-    
-    prompt = get_spelling_grammar_prompt(text)
-    try:
-        response = llm(prompt, max_tokens=50)
-        response_text = response['choices'][0]['text'].strip()
-        error_percentage = float(response_text)
-        return get_error_score(error_percentage), error_percentage
-    except ValueError:
-        logging.error("Failed to parse error percentage from LLM response")
-        return 0, 0
-    except Exception as e:
-        logging.error(f"Error in spelling and grammar check: {str(e)}")
-        return 0, 0
-
-def evaluate_cv_text(file_path):
-    try:
-        # Extract text using OCR
-        with open(file_path, 'rb') as f:
-            file_content = f.read()
-        
-        # Detect language
-        detected_language = detect_language(file_content)
-        
-        # Load OCR models
-        doctr_model, easyocr_reader, paddleocr_reader = load_models(detected_language)
-        
-        # Extract text using different OCR methods
-        results = {
-            "aws": extract_text_aws(file_content),
-            "doctr": extract_text_doctr(file_path, doctr_model),
-            "easyocr": extract_text_easyocr(file_path, easyocr_reader),
-            "paddleocr": extract_text_paddleocr(file_path, paddleocr_reader),
-        }
-        
-        # Combine OCR results
-        cv_text = combine_ocr_results(results, weights)
-        
-        # Check spelling and grammar
-        score, error_percentage = check_spelling_and_grammar(cv_text)
-        
-        return {
-            "score": score,
-            "error_percentage": error_percentage
-        }
-    except Exception as e:
-        logging.error(f"Error in CV text evaluation: {str(e)}")
-        return {
-            "score": 0,
-            "error_percentage": 0,
-            "error": str(e)
-        }