Update agent.py

agent.py

@@ -93,101 +93,29 @@ urls = [
     "https://www.instagram.com/westcentralcte/",
     "https://www.tiktok.com/@mutplteen"
     ]
+action: SEARCH_urls; # https://www.facebook.com/CulverCommunitySchools, https://www.culver.k12.in.us/
 
+action: OBSERVE_new; # initial database build -- all observations from feeds are new
 
-# Configure logging
-logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+- action: UPDATE_log; # each school's log gets dumped into a folder named after the school, within this folder:  # "Storage Location" and is going to be fed via rss via website. Must stay stored. lets just use this repo, here is the folder location's url -- i will provide authorization token with write perimission ; storage url: https://huggingface.co/spaces/acecalisto3/CEEMEESEEK/tree/main/scraped_data/culver ; my write permission api key is stored as a secret you've already verified. 
 
-# Define constants
-DATE_TIME_STR = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-PURPOSE = f"You go to Culvers sites, you continuously seek changes on them since your last observation. Anything new that gets logged and dumped into csv, stored in your log folder at user/app/scraped_data."
-HISTORY = []
-CURRENT_TASK = None
-DEFAULT_FILE_PATH = "user/app/scraped_data/culver/culvers_changes.csv"
+action: OBSERVE_change; # after db build -- any and all changes from previous feed observation
 
-# Ensure the directory exists
-os.makedirs(os.path.dirname(DEFAULT_FILE_PATH), exist_ok=True)
+- action: UPDATE_log; # each school's log gets dumped into a folder named after the school, within this folder:  # "Storage Location" and is going to be fed via rss via website. Must stay stored. lets just use this repo, here is the folder location's url -- i will provide authorization token with write perimission ; storage url: https://huggingface.co/spaces/acecalisto3/CEEMEESEEK/tree/main/scraped_data/culver ; my write permission api key is stored as a secret you've already verified. 
 
-# Function to monitor URLs for changes
-def monitor_urls(storage_location, urls, scrape_interval, content_type):
-    global HISTORY
-    previous_hashes = [""] * len(urls)
+action: OBSERVE_live; # in the event of a live stream -- return "Currently Live-Streaming at "```html <link_to_stream> " Join us!"
 
-    try:
-        with webdriver.Chrome(service=Service(ChromeDriverManager().install()), options=Options()) as driver:
-            while True:
-                for i, url in enumerate(urls):
-                    try:
-                        driver.get(url)
-                        time.sleep(2)  # Wait for the page to load
-                        if content_type == "text":
-                            current_content = driver.page_source
-                        elif content_type == "media":
-                            current_content = driver.find_elements_by_tag_name("img")
-                        else:
-                            current_content = driver.page_source
-                        current_hash = hashlib.md5(str(current_content).encode('utf-8')).hexdigest()
-                        if current_hash != previous_hashes[i]:
-                            previous_hashes[i] = current_hash
-                            date_time_str = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-                            HISTORY.append(f"Change detected at {url} on {date_time_str}")
-                            with open(storage_location, "a", newline="") as csvfile:
-                                csv_writer = csv.DictWriter(csvfile, fieldnames=["date", "time", "url", "change"])
-                                csv_writer.writerow({"date": date_time_str.split()[0], "time": date_time_str.split()[1], "url": url, "change": "Content changed"})
-                                logging.info(f"Change detected at {url} on {date_time_str}")
-                    except Exception as e:
-                        logging.error(f"Error accessing {url}: {e}")
-                time.sleep(scrape_interval * 60)  # Check every scrape_interval minutes
-    except Exception as e:
-        logging.error(f"Error starting ChromeDriver: {e}")
+action: UPDATE_task[extract>update log>monitor # scan the urls at user specified intervals] purpose: extract data/media from posts/pages, convert and deliver data in mysql database optimzied for rss feed>
 
-# Define main function to handle user input
-def handle_input(storage_location, urls, scrape_interval, content_type):
-    global CURRENT_TASK, HISTORY
+rss
 
-    CURRENT_TASK = f"Monitoring URLs: {', '.join(urls)}"
-    HISTORY.append(f"Task started: {CURRENT_TASK}")
-    monitor_urls(storage_location, urls, scrape_interval, content_type)
-    return TASK_PROMPT.format(task=CURRENT_TASK, history="\n".join(map(str, HISTORY)))
+- action: UPDATE_log  # this is "Storage Location" and is going to be fed via rss via website. Must stay stored. lets just use this repo, here is the folder location's url -- i will provide authorization token with write perimission ; storage url: https://huggingface.co/spaces/acecalisto3/CEEMEESEEK/tree/main/scraped_data/culver ; my write permission api key is stored as a secret you've already verified. 
 
-# Load custom prompts
-try:
-    with open("custom_prompts.yaml", "r") as fp:
-        custom_prompts = yaml.safe_load(fp)
-except FileNotFoundError:
-    custom_prompts = {"WEB_DEV": "", "AI_SYSTEM_PROMPT": "", "PYTHON_CODE_DEV": "", "CODE_GENERATION": "", "CODE_INTERPRETATION": "", "CODE_TRANSLATION": "", "CODE_IMPLEMENTATION": ""}
+#...
+# anything i missed should be dealt with by the app's global ai. it should handle all conversion logics, all triggering events the user doesnt handle, and so on
+# ...
+- action: COMPLETE # there should be accurate data in a log folder i can point my rss.app at to obtain fresh and updated feed from this repo's log...
 
-# Define agents
-AGENTS = ["WEB_DEV", "AI_SYSTEM_PROMPT", "PYTHON_CODE_DEV", "CODE_GENERATION", "CODE_INTERPRETATION", "CODE_TRANSLATION", "CODE_IMPLEMENTATION"]
-
-# Define the Mistral inference client
-client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
-
-# Define the chat response function
-def respond(message, history, system_message, max_tokens, temperature, top_p):
-    return generate(message, history, system_message, max_tokens, temperature, top_p)
-
-# Function to start scraping
-def start_scraping(storage_location, url1, url2, url3, url4, url5, url6, url7, url8, url9, url10, scrape_interval, content_type):
-    urls = [url for url in [url1, url2, url3, url4, url5, url6, url7, url8, url9, url10] if url]
-    handle_input(storage_location, urls, scrape_interval, content_type)
-    return f"Started scraping {', '.join(urls)} every {scrape_interval} minutes."
-
-# Function to display CSV content
-def display_csv(storage_location):
-    if os.path.exists(storage_location):
-        with open(storage_location, "r") as file:
-            return file.read()
-    else:
-        return "No data available."
-
-# Create Gradio interface
-def chat_interface(message, system_message, max_tokens, temperature, top_p, storage_location, url1, url2, url3, url4, url5, url6, url7, url8, url9, url10, scrape_interval, content_type):
-    global HISTORY
-    response = respond(message, HISTORY, system_message, max_tokens, temperature, top_p)
-    HISTORY.append((message, response))
-    return HISTORY, ""
-'''
 {purpose}
 """