Merge branch 'main' into bug/rate-limit-error

.gitignore

@@ -12,4 +12,4 @@ generated_cv*
 chrome_profile
 answers.json
 virtual/*
-data_folder/*
+data*

README.md

@@ -105,6 +105,8 @@ LinkedIn_AIHawk steps in as a game-changing solution to these challenges. It's n
 
 ## Installation
 
+**Please watch this video to set up your LinkedIn_AIHawk: [How to set up LinkedIn_AIHawk](https://youtu.be/gdW9wogHEUM) - https://youtu.be/gdW9wogHEUM**
+0. **Confirmed succesfull runs OSs & Python**: Python 3.10, 3.11.9(64b), 3.12.5(64b) . Windows 10, Ubuntu 22
 1. **Download and Install Python:**
 
    Ensure you have the last Python version  installed. If not, download and install it from Python's official website. For detailed instructions, refer to the tutorials:
@@ -505,11 +507,16 @@ TODO ):
 
 ## Troubleshooting
 
+- **Carefully read logs and output :** Most of the errors are verbosely reflected just watch the output and try to find the root couse. 
+- **If nothing works by unknown reason:**  Use tested OS. Reboot and/or update OS.  Use new clean venv. Try update Python to the tested version.  
 - **ChromeDriver Issues:** Ensure ChromeDriver is compatible with your installed Chrome version.
 - **Missing Files:** Verify that all necessary files are present in the data folder.
-- **Invalid YAML:** Check your YAML files for syntax errors.
+- **Invalid YAML:** Check your YAML files for syntax errors . Try to use external YAML validators e.g. https://www.yamllint.com/
-
+- **OpenAI endpoint isues**: Try to check possible limits\blocking at their side 
-  If you encounter any issues, you can open an issue on [GitHub](https://github.com/feder-cr/linkedIn_auto_jobs_applier_with_AI/issues). I'll be more than happy to assist you!
+  
+If you encounter any issues, you can open an issue on [GitHub](https://github.com/feder-cr/linkedIn_auto_jobs_applier_with_AI/issues).
+  Please add valuable details to the subject and to the description. If you need new feature then please reflect this.  
+  I'll be more than happy to assist you!
 
 ## Conclusion
 

src/gpt.py

@@ -135,11 +135,7 @@ class LoggerChatModel:
 
 class GPTAnswerer:
     def __init__(self, openai_api_key):
-        self.llm_cheap = LoggerChatModel(
+        self.llm_cheap = LoggerChatModel(ChatOpenAI(model_name="gpt-4o-mini", openai_api_key=openai_api_key, temperature=0.4)
-            ChatOpenAI(
-                model_name="gpt-4o-mini", openai_api_key=openai_api_key, temperature=0.8
-            )
-        )
 
     @property
     def job_description(self):

src/linkedIn_easy_applier.py

@@ -30,7 +30,6 @@ class LinkedInEasyApplier:
         self.resume_generator_manager = resume_generator_manager
         self.all_data = self._load_questions_from_json()
 
-
     def _load_questions_from_json(self) -> List[dict]:
         output_file = 'answers.json'
         try:
@@ -49,7 +48,6 @@ class LinkedInEasyApplier:
             tb_str = traceback.format_exc()
             raise Exception(f"Error loading questions data from JSON file: \nTraceback:\n{tb_str}")
 
-
     def job_apply(self, job: Any):
         self.driver.get(job.link)
         time.sleep(random.uniform(3, 5))
@@ -91,7 +89,6 @@ class LinkedInEasyApplier:
             attempt += 1
         raise Exception("No clickable 'Easy Apply' button found")
     
-
     def _get_job_description(self) -> str:
         try:
             see_more_button = self.driver.find_element(By.XPATH, '//button[@aria-label="Click to see more description"]')
@@ -107,7 +104,6 @@ class LinkedInEasyApplier:
             tb_str = traceback.format_exc()
             raise Exception(f"Error getting Job description: \nTraceback:\n{tb_str}")
 
-
     def _get_job_recruiter(self):
         try:
             hiring_team_section = WebDriverWait(self.driver, 10).until(
@@ -253,16 +249,12 @@ class LinkedInEasyApplier:
         if radios:
             question_text = section.text.lower()
             options = [radio.text.lower() for radio in radios]
-            
             existing_answer = None
             for item in self.all_data:
                 if self._sanitize_text(question_text) in item['question'] and item['type'] == 'radio':
                     existing_answer = item
-                    break
+                    self._select_radio(radios, existing_answer['answer'])
-            if existing_answer:
+                    return True
-                self._select_radio(radios, existing_answer['answer'])
-                return True
-
             answer = self.gpt_answerer.answer_question_from_options(question_text, options)
             self._save_questions_to_json({'type': 'radio', 'question': question_text, 'answer': answer})
             self._select_radio(radios, answer)
@@ -283,12 +275,10 @@ class LinkedInEasyApplier:
                 answer = self.gpt_answerer.answer_question_textual_wide_range(question_text)
             existing_answer = None
             for item in self.all_data:
-                if item['question'] == self._sanitize_text(question_text) and item['type'] == question_type:
+                if 'cover' not in item['question'] and item['question'] == self._sanitize_text(question_text) and item['type'] == question_type:
                     existing_answer = item
-                    break
+                    self._enter_text(text_field, existing_answer['answer'])
-            if existing_answer:
+                    return True
-                self._enter_text(text_field, existing_answer['answer'])
-                return True
             self._save_questions_to_json({'type': question_type, 'question': question_text, 'answer': answer})
             self._enter_text(text_field, answer)
             return True
@@ -302,15 +292,12 @@ class LinkedInEasyApplier:
             answer_date = self.gpt_answerer.answer_question_date()
             answer_text = answer_date.strftime("%Y-%m-%d")
 
-
             existing_answer = None
             for item in self.all_data:
                 if  self._sanitize_text(question_text) in item['question'] and item['type'] == 'date':
                     existing_answer = item
-                    break
+                    self._enter_text(date_field, existing_answer['answer'])
-            if existing_answer:
+                    return True
-                self._enter_text(date_field, existing_answer['answer'])
-                return True
 
             self._save_questions_to_json({'type': 'date', 'question': question_text, 'answer': answer_text})
             self._enter_text(date_field, answer_text)
@@ -325,16 +312,12 @@ class LinkedInEasyApplier:
             if dropdown:
                 select = Select(dropdown)
                 options = [option.text for option in select.options]
-
                 existing_answer = None
                 for item in self.all_data:
                     if  self._sanitize_text(question_text) in item['question'] and item['type'] == 'dropdown':
                         existing_answer = item
-                        break
+                        self._select_dropdown_option(dropdown, existing_answer['answer'])
-                if existing_answer:
+                        return True
-                    self._select_dropdown_option(dropdown, existing_answer['answer'])
-                    return True
-
                 answer = self.gpt_answerer.answer_question_from_options(question_text, options)
                 self._save_questions_to_json({'type': 'dropdown', 'question': question_text, 'answer': answer})
                 self._select_dropdown_option(dropdown, answer)
@@ -385,7 +368,6 @@ class LinkedInEasyApplier:
             tb_str = traceback.format_exc()
             raise Exception(f"Error saving questions data to JSON file: \nTraceback:\n{tb_str}")
 
-
     def _sanitize_text(self, text: str) -> str:
         sanitized_text = text.lower()
         sanitized_text = sanitized_text.strip()

src/linkedIn_job_manager.py

@@ -53,18 +53,6 @@ class LinkedInJobManager:
     def set_resume_generator_manager(self, resume_generator_manager):
         self.resume_generator_manager = resume_generator_manager
 
-    """ def old_question(self):
-        self.set_old_answers = {}
-        file_path = 'data_folder/output/old_Questions.csv'
-        if os.path.exists(file_path):
-            with open(file_path, 'r', newline='', encoding='utf-8', errors='ignore') as file:
-                csv_reader = csv.reader(file, delimiter=',', quotechar='"')
-                for row in csv_reader:
-                    if len(row) == 3:
-                        answer_type, question_text, answer = row
-                        self.set_old_answers[(answer_type.lower(), question_text.lower())] = answer"""
-
-
     def start_applying(self):
         self.easy_applier_component = LinkedInEasyApplier(self.driver, self.resume_path, self.set_old_answers, self.gpt_answerer, self.resume_generator_manager)
         searches = list(product(self.positions, self.locations))