Update agent.py

agent.py

@@ -11,7 +11,183 @@ Never answer questions without using your tool action: SEARCH action_input=https
 Always use the provided tools to satisfy your purpose
 Current Date/Time:
 {date_time_str}
-Purpose:
+Purpose: 
+'''
+urls = [
+    "https://twitter.com/wlcscrdp",
+    "https://www.facebook.com/aurorareddevils/",
+    "https://www.facebook.com/brightpanthers/",
+    "https://www.facebook.com/carrollcountychamberin/",
+    "https://www.facebook.com/Culver.Cavs.MHS",
+    "https://www.facebook.com/culver.elementary.school",
+    "https://www.facebook.com/CulverCommunitySchools",
+    "https://www.facebook.com/DillsboroBulldogs/",
+    "https://www.facebook.com/ECMSTROJANS",
+    "https://www.facebook.com/enjoywhitecountyIN/",
+    "https://www.facebook.com/farmersvilleelementary",
+    "https://www.facebook.com/groups/SDMSparents",
+    "https://www.facebook.com/jghsart/",
+    "https://www.facebook.com/jgmusicdept",
+    "https://www.facebook.com/John-Glenn-Education-Foundation-208326199636364/",
+    "https://www.facebook.com/John-Glenn-High-School-1102148953201006/",
+    "https://www.facebook.com/John-Glenn-Theatre-Company-383638295064502/",
+    "https://www.facebook.com/JohnGlennFalconsAthletics",
+    "https://www.facebook.com/KIRPC-Head-Start-1485812354989001",
+    "https://www.facebook.com/KIRPC1",
+    "https://www.facebook.com/LHNEeagles",
+    "https://www.facebook.com/LuceElementarySchool/",
+    "https://www.facebook.com/marrselementary",
+    "https://www.facebook.com/messhiners/",
+    "https://www.facebook.com/monticellocitypool",
+    "https://www.facebook.com/monticelloinwastewater/",
+    "https://www.facebook.com/MooresHillBobcats/",
+    "https://www.facebook.com/msdmv",
+    "https://www.facebook.com/msdnorthposey",
+    "https://www.facebook.com/MUTPL/",
+    "https://www.facebook.com/MVJHS/",
+    "https://www.facebook.com/mvshs",
+    "https://www.facebook.com/njspjrsrhighschool?mibextid=b06tZ0",
+    "https://www.facebook.com/NorthElementaryStars/",
+    "https://www.facebook.com/NorthLibertyElementary/",
+    "https://www.facebook.com/northposey/",
+    "https://www.facebook.com/northposeyhs/",
+    "https://www.facebook.com/NPJuniorHigh",
+    "https://www.facebook.com/Prairie-Heights-Elementary-659322230934707/",
+    "https://www.facebook.com/Prairie-Heights-High-School-2027713067459043/",
+    "https://www.facebook.com/PrairieHeightsPanthers/",
+    "https://www.facebook.com/profile.php?id=100057030237096",
+    "https://www.facebook.com/profile.php?id=100057451179651",
+    "https://www.facebook.com/profile.php?id=100063463513451",
+    "https://www.facebook.com/profile.php?id=100063612319256",
+    "https://www.facebook.com/profile.php?id=100064532596422",
+    "https://www.facebook.com/profile.php?id=100067180226810",
+    "https://www.facebook.com/profile.php?id=61563484312348",
+    "https://www.facebook.com/PTOSWES/",
+    "https://www.facebook.com/RandolphSouthern/",
+    "https://www.facebook.com/RochesterMiddleSchool",
+    "https://www.facebook.com/RochesterZebraNewTechHigh",
+    "https://www.facebook.com/rockportelementarysouthspencer/",
+    "https://www.facebook.com/satellitesathletics/",
+    "https://www.facebook.com/seymourcommunityschools/",
+    "https://www.facebook.com/SeymourHighSchool/",
+    "https://www.facebook.com/SouthDearbornHighSchool/",
+    "https://www.facebook.com/southarbornschools/",
+    "https://www.facebook.com/SouthDearbornSquires/",
+    "https://www.facebook.com/southspencerhighschool",
+    "https://www.facebook.com/southspencermiddleschool/",
+    "https://www.facebook.com/SouthSpencerSchools",
+    "https://www.facebook.com/SouthTerracePanthers/",
+    "https://www.facebook.com/sunmantigers/",
+    "https://www.facebook.com/SWShelbySpartan/",
+    "https://www.facebook.com/TallTimbersMarina",
+    "https://www.facebook.com/WabashValleyESC/",
+    "https://www.facebook.com/Walkerton-Elementary-School-283088605088622/",
+    "https://www.facebook.com/westcentralcte/",
+    "https://www.facebook.com/westelementary",
+    "https://www.facebook.com/wlcscrdp",
+    "https://www.instagram.com/mutpl/",
+    "https://www.instagram.com/northposeyhsathletics",
+    "https://www.instagram.com/rchsprincipalcook/",
+    "https://www.instagram.com/southdearbornhighschool/",
+    "https://www.instagram.com/southdearbornschools/",
+    "https://www.instagram.com/westcentralcte/",
+    "https://www.tiktok.com/@mutplteen"
+    ]
+
+
+# Configure logging
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+
+# 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"
+
+# Ensure the directory exists
+os.makedirs(os.path.dirname(DEFAULT_FILE_PATH), exist_ok=True)
+
+# Function to monitor URLs for changes
+def monitor_urls(storage_location, urls, scrape_interval, content_type):
+    global HISTORY
+    previous_hashes = [""] * len(urls)
+
+    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}")
+
+# Define main function to handle user input
+def handle_input(storage_location, urls, scrape_interval, content_type):
+    global CURRENT_TASK, HISTORY
+
+    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)))
+
+# 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": ""}
+
+# 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}
 """