Spaces:
Sleeping
Sleeping
File size: 32,327 Bytes
a4c189f a0cbb48 08e2519 a0cbb48 7c434cd bb30230 f52e0e6 a0cbb48 f52e0e6 2271e95 a0cbb48 7c434cd 5b420d6 7c434cd 2851ee8 a0cbb48 bb30230 79fd5d1 bb30230 a0cbb48 2851ee8 bb30230 a0cbb48 bb30230 5b420d6 7c434cd 79fd5d1 7c434cd 79fd5d1 5b420d6 79fd5d1 5b420d6 79fd5d1 5b420d6 79fd5d1 7c434cd 79fd5d1 7c434cd 5b420d6 7c434cd 79fd5d1 7c434cd 79fd5d1 7c434cd bb30230 7c434cd 79fd5d1 5b420d6 bb30230 7c434cd 2851ee8 7c434cd 79fd5d1 7c434cd 79fd5d1 bb30230 a0cbb48 79fd5d1 3d9f649 79fd5d1 3d9f649 79fd5d1 3d9f649 79fd5d1 a0cbb48 2271e95 79fd5d1 a4c189f 79fd5d1 a4c189f 79fd5d1 3ceebe8 79fd5d1 3ceebe8 79fd5d1 6812c77 79fd5d1 6812c77 79fd5d1 6812c77 79fd5d1 6812c77 79fd5d1 6812c77 79fd5d1 3ceebe8 79fd5d1 3ceebe8 79fd5d1 6812c77 79fd5d1 6812c77 79fd5d1 3ceebe8 79fd5d1 6812c77 79fd5d1 6812c77 79fd5d1 6812c77 79fd5d1 a4c189f 79fd5d1 6812c77 79fd5d1 6812c77 79fd5d1 6812c77 79fd5d1 a4c189f 79fd5d1 a4c189f 79fd5d1 a4c189f 79fd5d1 a4c189f 79fd5d1 a4c189f 79fd5d1 3ceebe8 79fd5d1 a4c189f 79fd5d1 bb30230 a4c189f bb30230 a4c189f 79fd5d1 bb30230 a4c189f 79fd5d1 a4c189f 79fd5d1 2271e95 79fd5d1 2271e95 79fd5d1 bb30230 2271e95 bb30230 2271e95 bb30230 2271e95 79fd5d1 2271e95 bb30230 2271e95 0263c1c a4c189f 2271e95 f52e0e6 2271e95 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 |
from flask import Flask, render_template_string, request, jsonify, send_from_directory
import os
from dotenv import load_dotenv
from langchain_community.vectorstores import FAISS
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_core.documents import Document
import requests
from bs4 import BeautifulSoup # New
from collections import deque # New
from urllib.parse import urljoin, urlparse # New
import time # New for crawl delay
load_dotenv()
app = Flask(__name__)
# Global variables
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
vectorstore = None
retriever = None
groq_api_key = None
def initialize_groq():
global groq_api_key
groq_api_key = os.getenv("GROQ_API_KEY")
return "Groq API key found" if groq_api_key else "Groq API key not found"
def crawl_website(url_to_crawl, max_pages=10):
"""
Crawls a website to extract text content and links.
Args:
url_to_crawl (str): The starting URL for the crawl.
max_pages (int): Maximum number of pages to crawl.
Returns:
list: A list of dictionaries, each containing 'text' and 'url' of crawled pages.
"""
base_domain = urlparse(url_to_crawl).netloc
queue = deque([url_to_crawl])
visited_urls = set()
scraped_data = []
print(f"Starting crawl from: {url_to_crawl}")
while queue and len(scraped_data) < max_pages:
current_url = queue.popleft()
if current_url in visited_urls:
continue
print(f"Crawling: {current_url}")
visited_urls.add(current_url)
try:
response = requests.get(current_url, timeout=10)
response.raise_for_status() # Raise an HTTPError for bad responses (4xx or 5xx)
soup = BeautifulSoup(response.text, 'lxml')
# Extract text content
page_text = ' '.join(p.get_text() for p in soup.find_all('p'))
page_text += ' '.join(li.get_text() for li in soup.find_all('li'))
page_text += ' '.join(h.get_text() for h in soup.find_all(['h1', 'h2', 'h3', 'h4', 'h5', 'h6']))
# Clean up extra whitespace and newlines
page_text = ' '.join(page_text.split()).strip()
if page_text:
scraped_data.append({"text": page_text, "url": current_url})
# Extract links
for link in soup.find_all('a', href=True):
href = link['href']
absolute_url = urljoin(current_url, href)
parsed_absolute_url = urlparse(absolute_url)
# Only follow links within the same domain and not already visited
if parsed_absolute_url.netloc == base_domain and absolute_url not in visited_urls:
if '#' not in absolute_url and 'mailto:' not in absolute_url and 'tel:' not in absolute_url: # Avoid anchor links and mail/tel links
queue.append(absolute_url)
except requests.exceptions.RequestException as e:
print(f"Error crawling {current_url}: {e}")
except Exception as e:
print(f"An unexpected error occurred with {current_url}: {e}")
time.sleep(1) # Be polite and avoid overwhelming the server
print(f"Finished crawling. Scraped {len(scraped_data)} pages.")
return scraped_data
def update_vectorstore_from_crawl(url_to_crawl="https://www.atomcamp.com/", max_pages=20):
"""
Performs a web crawl and updates the FAISS vector store with the scraped data.
"""
global vectorstore, retriever
print("Initiating website crawl for vector store update...")
scraped_data = crawl_website(url_to_crawl, max_pages)
if not scraped_data:
print("No data scraped from the website. Using sample data as fallback.")
# Fallback to sample data if crawl fails or yields no content
sample_data = [
{
"text": "Atomcamp is a leading data science education platform offering comprehensive courses in machine learning, Python programming, data analysis, and AI. We provide hands-on projects, expert mentorship, and career guidance to help students become successful data scientists.",
"url": "https://www.atomcamp.com/about"
},
{
"text": "Our courses include: Python for Data Science, Machine Learning Fundamentals, Deep Learning with TensorFlow, Data Visualization with Matplotlib and Seaborn, SQL for Data Analysis, Statistics for Data Science, and Advanced AI Techniques.",
"url": "https://www.atomcamp.com/courses"
},
{
"text": "Atomcamp offers flexible learning paths: Beginner Track (3 months) - Python basics, data manipulation, basic statistics. Intermediate Track (6 months) - Machine learning, advanced Python, real projects. Advanced Track (9 months) - Deep learning, AI, industry projects, job placement assistance.",
"url": "https://www.atomcamp.com/learning-paths"
}
]
docs = [Document(page_content=item["text"], metadata={"url": item["url"]}) for item in sample_data]
else:
docs = [Document(page_content=item["text"], metadata={"url": item["url"]}) for item in scraped_data]
splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
chunks = splitter.split_documents(docs)
vectorstore = FAISS.from_documents(chunks, embeddings)
vectorstore.save_local("atomcamp_vector_db")
retriever = vectorstore.as_retriever()
print("Vectorstore updated successfully from crawled data (or sample fallback).")
return "Vectorstore updated successfully"
def initialize_vectorstore():
global vectorstore, retriever
try:
# Attempt to load existing vectorstore
vectorstore = FAISS.load_local("atomcamp_vector_db", embeddings, allow_dangerous_deserialization=True)
retriever = vectorstore.as_retriever()
print("Vectorstore loaded successfully from local storage.")
return "Vectorstore loaded successfully"
except Exception as e:
print(f"Failed to load vectorstore: {e}. Attempting to crawl and build.")
# If loading fails, crawl the website and build a new one
return update_vectorstore_from_crawl()
def call_groq_api(message, context):
global groq_api_key
if not groq_api_key:
return None
try:
system_prompt = f"""You are an AI assistant for Atomcamp, a data science education platform.
Use the following context to answer questions about Atomcamp's courses, career services, and data science topics.
Context: {context}
Guidelines:
- Be helpful and informative
- Focus on Atomcamp's offerings
- Provide specific details when available
- Use bullet points for lists
- Keep responses concise but comprehensive
- Do not use emojis
"""
headers = {
"Authorization": f"Bearer {groq_api_key}",
"Content-Type": "application/json"
}
data = {
"messages": [
{"role": "system", "content": system_prompt},
{"role": "user", "content": message}
],
"model": "llama3-8b-8192",
"temperature": 0.7,
"max_tokens": 1000
}
response = requests.post(
"https://api.groq.com/openai/v1/chat/completions",
headers=headers,
json=data,
timeout=30
)
if response.status_code == 200:
result = response.json()
return result["choices"][0]["message"]["content"]
else:
print(f"Groq API Error: {response.status_code} - {response.text}")
return None
except Exception as e:
print(f"Error calling Groq API: {e}")
return None
def generate_response(message, context):
groq_response = call_groq_api(message, context)
if groq_response:
return groq_response
# Fallback responses (less likely to be hit with web scraping)
message_lower = message.lower()
if any(word in message_lower for word in ['course', 'courses', 'learn', 'study']):
return """Atomcamp Courses:
Core Programs:
• Python for Data Science - Master Python programming fundamentals
• Machine Learning Fundamentals - Learn ML algorithms and applications
• Deep Learning with TensorFlow - Build neural networks and AI models
• Data Visualization - Create stunning charts with Matplotlib & Seaborn
• SQL for Data Analysis - Database querying and data manipulation
• Statistics for Data Science - Statistical analysis and hypothesis testing
Learning Tracks:
• Beginner Track (3 months) - Perfect for newcomers
• Intermediate Track (6 months) - Build real-world projects
• Advanced Track (9 months) - Industry-ready with job placement
Would you like details about any specific course?"""
elif any(word in message_lower for word in ['career', 'job', 'placement']):
return """Career Services at Atomcamp:
Job Placement Support:
• Resume building and optimization
• Technical interview preparation
• Portfolio development guidance
• Direct connections with hiring partners
• Mock interviews with industry experts
Career Growth:
• Average salary increase: 150-300%
• 95% job placement rate within 6 months
• Access to exclusive job opportunities
• Ongoing career mentorship
• Industry networking events
Ready to transform your career in data science?"""
else:
return f"""Thank you for your question about "{message}"!
As an Atomcamp AI assistant, I'm here to help you with:
Course Information - Learn about our data science programs
Career Guidance - Job placement and career growth
Technical Topics - Python, ML, AI, and data analysis
Getting Started - How to begin your data science journey
Would you like me to elaborate on any specific aspect?"""
@app.route('/')
def index():
html_template = """
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>atomcamp AI Chatbot</title>
<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700&display=swap" rel="stylesheet">
<style>
* {
margin: 0;
padding: 0;
box-sizing: border-box;
}
body {
font-family: 'Inter', sans-serif;
background: linear-gradient(135deg, #f9fafb 0%, #ffffff 100%);
min-height: 100vh;
display: flex;
flex-direction: column;
}
.header {
display: flex;
flex-direction: column;
align-items: center;
padding-top: 2rem;
padding-bottom: 1.5rem;
}
.logo {
margin-bottom: 1.5rem;
}
.logo-img {
height: 48px;
width: auto;
object-fit: contain;
max-width: 200px;
}
.title-bubble {
width: 100%;
max-width: 64rem;
padding: 0 1rem;
}
.bubble-container {
background: #f0fdf4;
border: 1px solid #e5e7eb;
border-radius: 1rem;
box-shadow: 0 1px 3px 0 rgba(0, 0, 0, 0.1);
padding: 1.5rem;
max-width: fit-content;
}
.bubble-content {
text-align: left;
}
.chatbot-title {
font-size: 1.5rem;
font-weight: 600;
color: #166534;
margin-bottom: 0.25rem;
letter-spacing: -0.025em;
}
.typing-indicator {
display: flex;
align-items: center;
gap: 0.5rem;
}
.typing-dots {
display: flex;
gap: 0.25rem;
}
.typing-dot {
width: 0.375rem;
height: 0.375rem;
background: #166534;
border-radius: 50%;
animation: bounce 1s infinite;
}
.typing-dot:nth-child(2) {
animation-delay: 0.1s;
}
.typing-dot:nth-child(3) {
animation-delay: 0.2s;
}
.typing-text {
color: #166534;
font-size: 1rem;
font-weight: 500;
}
.status-indicator {
display: flex;
align-items: center;
gap: 0.5rem;
}
.status-dot {
width: 0.5rem;
height: 0.5rem;
border-radius: 50%;
background: #16a34a;
}
.status-text {
font-size: 0.875rem;
font-weight: 500;
color: #166534;
}
.chat-container {
max-width: 64rem;
margin: 0 auto;
padding: 0 1rem;
padding-bottom: 8rem;
flex: 1;
overflow-y: auto;
height: calc(100vh - 300px);
}
.welcome-screen {
text-align: center;
padding: 3rem 0;
}
.welcome-card {
background: white;
border-radius: 1rem;
box-shadow: 0 4px 6px -1px rgba(0, 0, 0, 0.1);
padding: 2rem;
max-width: 36rem;
margin: 0 auto;
}
.welcome-icon {
width: 3rem;
height: 3rem;
background: #22c55e;
border-radius: 0.75rem;
display: flex;
align-items: center;
justify-content: center;
margin: 0 auto 1rem;
color: white;
font-size: 1.5rem;
font-weight: bold;
}
.welcome-title {
font-size: 1.25rem;
font-weight: 600;
color: #1f2937;
margin-bottom: 0.75rem;
letter-spacing: -0.025em;
}
.welcome-description {
color: #6b7280;
font-size: 0.875rem;
line-height: 1.5;
margin-bottom: 1.5rem;
}
.feature-grid {
display: grid;
grid-template-columns: repeat(auto-fit, minmax(250px, 1fr));
gap: 0.75rem;
text-align: left;
}
.feature-card {
background: #f9fafb;
border-radius: 0.5rem;
padding: 0.75rem;
}
.feature-title {
font-weight: 600;
color: #1f2937;
margin-bottom: 0.5rem;
font-size: 0.875rem;
}
.feature-list {
font-size: 0.75rem;
color: #6b7280;
line-height: 1.5;
list-style: none;
padding: 0;
margin: 0;
}
.feature-list li {
margin-bottom: 0.25rem;
}
.messages-container {
display: flex;
flex-direction: column;
gap: 1rem;
}
.message {
display: flex;
animation: fadeIn 0.3s ease-out;
margin-bottom: 0.5rem;
}
.message.user {
justify-content: flex-end;
}
.message.assistant {
justify-content: flex-start;
}
.message-content {
display: flex;
align-items: flex-end;
gap: 0.5rem;
max-width: 90%;
}
.avatar {
width: 2rem;
height: 2rem;
border-radius: 50%;
display: flex;
align-items: center;
justify-content: center;
flex-shrink: 0;
}
.avatar.user {
background: #22c55e;
color: white;
}
.avatar.assistant {
background: #e5e7eb;
color: #6b7280;
}
.message-bubble {
padding: 0.625rem 0.875rem;
border-radius: 1rem;
font-size: 0.875rem;
line-height: 1.4;
max-width: 90%;
}
.message.user .message-bubble {
background: #22c55e;
color: white;
border-bottom-right-radius: 0.375rem;
}
.message.assistant .message-bubble {
background: #e5e7eb;
color: #1f2937;
border-bottom-left-radius: 0.375rem;
}
.message-text {
font-size: 0.875rem;
font-weight: 500;
line-height: 1.5;
}
.message-formatted {
font-size: 0.875rem;
line-height: 1.5;
}
.input-area {
position: fixed;
bottom: 0;
left: 0;
right: 0;
background: rgba(255, 255, 255, 0.95);
backdrop-filter: blur(8px);
border-top: 1px solid #e5e7eb;
padding: 1rem;
}
.input-container {
max-width: 64rem;
margin: 0 auto;
}
.input-form {
position: relative;
}
.input-wrapper {
position: relative;
background: #4b5563;
border-radius: 9999px;
overflow: hidden;
box-shadow: 0 4px 6px -1px rgba(0, 0, 0, 0.1);
}
.message-input {
width: 100%;
padding: 0.875rem 1.25rem;
padding-right: 3rem;
background: transparent;
border: none;
outline: none;
color: white;
font-size: 0.875rem;
font-weight: 500;
resize: none;
line-height: 1.5;
min-height: 3.25rem;
max-height: 9rem;
overflow-y: auto;
}
.message-input::placeholder {
color: #d1d5db;
}
.send-button {
position: absolute;
right: 0.5rem;
top: 50%;
transform: translateY(-50%);
background: #22c55e;
color: white;
border: none;
border-radius: 50%;
width: 2.5rem;
height: 2.5rem;
display: flex;
align-items: center;
justify-content: center;
cursor: pointer;
transition: all 0.2s;
box-shadow: 0 1px 3px 0 rgba(0, 0, 0, 0.1);
}
.send-button:hover:not(:disabled) {
background: #16a34a;
box-shadow: 0 4px 6px -1px rgba(0, 0, 0, 0.1);
}
.send-button:disabled {
opacity: 0.5;
cursor: not-allowed;
}
.status-bar {
display: flex;
justify-content: space-between;
align-items: center;
margin-top: 0.5rem;
padding: 0 0.5rem;
}
.connection-status {
font-size: 0.75rem;
font-weight: 500;
color: #6b7280;
}
.char-count {
font-size: 0.75rem;
font-weight: 500;
color: #9ca3af;
}
.hidden {
display: none !important;
}
@keyframes bounce {
0%, 100% {
transform: translateY(0);
}
50% {
transform: translateY(-4px);
}
}
@keyframes fadeIn {
from {
opacity: 0;
transform: translateY(8px);
}
to {
opacity: 1;
transform: translateY(0);
}
}
@media (max-width: 768px) {
.header {
padding-top: 1rem;
padding-bottom: 1rem;
}
.chat-container {
padding-bottom: 6rem;
}
.message-content {
max-width: calc(100vw - 2rem);
}
.message.user .message-content {
max-width: calc(100vw - 2rem);
}
}
</style>
</head>
<body>
<div class="header">
<div class="logo">
<img src="/static/atomcamp_logo.png" alt="Atomcamp Logo" class="logo-image" style="height: 42px;">
</div>
<div class="title-bubble">
<div class="bubble-container">
<div class="bubble-content">
<h1 class="chatbot-title">Chatbot</h1>
<div id="typingIndicator" class="typing-indicator hidden">
<div class="typing-dots">
<div class="typing-dot"></div>
<div class="typing-dot"></div>
<div class="typing-dot"></div>
</div>
<span class="typing-text">Typing...</span>
</div>
<div id="statusIndicator" class="status-indicator">
<div class="status-dot"></div>
<span class="status-text">Online</span>
</div>
</div>
</div>
</div>
</div>
<div class="chat-container">
<div id="welcomeScreen" class="welcome-screen">
<div class="welcome-card">
<div class="welcome-icon">✨</div>
<h2 class="welcome-title">Welcome to atomcamp AI</h2>
<p class="welcome-description">Ask me about courses, data science concepts, and learning paths.</p>
<div class="feature-grid">
<div class="feature-card">
<h3 class="feature-title">Ask me about:</h3>
<ul class="feature-list">
<li>• Course information</li>
<li>• Data science concepts</li>
<li>• Learning paths</li>
</ul>
</div>
<div class="feature-card">
<h3 class="feature-title">Try asking:</h3>
<ul class="feature-list">
<li>• "What courses do you offer?"</li>
<li>• "Explain machine learning"</li>
<li>• "How do I get started?"</li>
</ul>
</div>
</div>
</div>
</div>
<div id="messagesContainer" class="messages-container hidden"></div>
</div>
<div class="input-area">
<div class="input-container">
<form id="chatForm" class="input-form">
<div class="input-wrapper">
<textarea
id="messageInput"
class="message-input"
placeholder="Ask me anything about atomcamp..."
maxlength="1000"
autocomplete="off"
rows="1"
>
</textarea>
<button type="submit" id="sendButton" class="send-button">
<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2">
<path d="M12 19V5M5 12l7-7 7 7"/>
</svg>
</button>
</div>
<div class="status-bar">
<span id="connectionStatus" class="connection-status">Connected to atomcamp AI</span>
<span id="charCount" class="char-count">0/1000</span>
</div>
</form>
</div>
</div>
<script>
let messages = [];
let isTyping = false;
let isConnected = true;
const welcomeScreen = document.getElementById('welcomeScreen');
const messagesContainer = document.getElementById('messagesContainer');
const chatForm = document.getElementById('chatForm');
const messageInput = document.getElementById('messageInput');
const sendButton = document.getElementById('sendButton');
const typingIndicator = document.getElementById('typingIndicator');
const statusIndicator = document.getElementById('statusIndicator');
const connectionStatus = document.getElementById('connectionStatus');
const charCount = document.getElementById('charCount');
chatForm.addEventListener('submit', handleSubmit);
messageInput.addEventListener('input', updateCharCount);
messageInput.addEventListener('input', () => {
messageInput.style.height = 'auto';
messageInput.style.height = messageInput.scrollHeight + 'px';
});
function updateCharCount() {
const count = messageInput.value.length;
charCount.textContent = `${count}/1000`;
}
async function handleSubmit(e) {
e.preventDefault();
const message = messageInput.value.trim();
if (!message || isTyping) return;
addMessage(message, 'user');
messageInput.value = '';
updateCharCount();
setTyping(true);
try {
const response = await fetch('/chat', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ message: message })
});
const data = await response.json();
await new Promise(resolve => setTimeout(resolve, 1200));
addMessage(data.response || 'Sorry, I could not generate a response.', 'assistant');
setConnected(true);
} catch (error) {
console.error('Error:', error);
setConnected(false);
addMessage('I am having trouble connecting. Please try again.', 'assistant');
} finally {
setTyping(false);
}
}
function addMessage(content, role) {
if (messages.length === 0) {
welcomeScreen.classList.add('hidden');
messagesContainer.classList.remove('hidden');
}
const messageDiv = document.createElement('div');
messageDiv.className = `message ${role}`;
const messageContent = document.createElement('div');
messageContent.className = 'message-content';
const avatar = document.createElement('div');
avatar.className = `avatar ${role}`;
if (role === 'user') {
avatar.innerHTML = '<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2"><path d="M20 21v-2a4 4 0 0 0-4-4H8a4 4 0 0 0-4 4v2"></path><circle cx="12" cy="7" r="4"></circle></svg>';
} else {
avatar.innerHTML = '<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2"><rect x="3" y="11" width="18" height="11" rx="2" ry="2"></rect><circle cx="12" cy="5" r="2"></circle><path d="M12 7v4"></path><line x1="8" y1="16" x2="8" y2="16"></line><line x1="16" y1="16" x2="16" y2="16"></line></svg>';
}
const bubble = document.createElement('div');
bubble.className = 'message-bubble';
if (role === 'user') {
bubble.innerHTML = `<div class="message-text">${content}</div>`;
messageContent.appendChild(bubble);
messageContent.appendChild(avatar);
} else {
bubble.innerHTML = `<div class="message-formatted">${formatMessageContent(content)}</div>`;
messageContent.appendChild(avatar);
messageContent.appendChild(bubble);
}
messageDiv.appendChild(messageContent);
messagesContainer.appendChild(messageDiv);
scrollToBottom();
messages.push({ content, role, timestamp: new Date() });
}
function formatMessageContent(content) {
return content.split('\\n').map(line => {
if (line.trim().startsWith('•') || line.trim().startsWith('-')) {
return `<div style="display: flex; align-items: flex-start; margin-bottom: 0.375rem;">
<span style="color: #16a34a; margin-right: 0.5rem; margin-top: 0.125rem; font-size: 0.875rem; font-weight: 500;">•</span>
<span style="font-size: 0.875rem; line-height: 1.5;">${line.replace(/^[•-]\s*/, '')}</span>
</div>`;
} else if (/^\d+\./.test(line.trim())) {
const match = line.match(/^\d+\./);
return `<div style="display: flex; align-items: flex-start; margin-bottom: 0.375rem;">
<span style="color: #16a34a; margin-right: 0.5rem; font-weight: 600; font-size: 0.875rem;">${match ? match[0] : ''}</span>
<span style="font-size: 0.875rem; line-height: 1.5;">${line.replace(/^\d+\.\s*/, '')}</span>
</div>`;
} else if (line.trim() === '') {
return '<br>';
} else {
return `<p style="margin-bottom: 0.375rem; font-size: 0.875rem; line-height: 1.5;">${line}</p>`;
}
}).join('');
}
function setTyping(typing) {
isTyping = typing;
sendButton.disabled = typing;
if (typing) {
typingIndicator.classList.remove('hidden');
statusIndicator.classList.add('hidden');
} else {
typingIndicator.classList.add('hidden');
statusIndicator.classList.remove('hidden');
}
}
function setConnected(connected) {
isConnected = connected;
connectionStatus.textContent = connected ? 'Connected to atomcamp AI' : 'Connection lost';
}
function scrollToBottom() {
setTimeout(() => {
window.scrollTo({
top: document.body.scrollHeight,
behavior: 'smooth'
});
}, 100);
}
</script>
</body>
</html>
"""
return render_template_string(html_template)
@app.route('/chat', methods=['POST'])
def chat():
try:
data = request.get_json()
message = data.get('message', '')
if not message:
return jsonify({'error': 'No message provided'}), 400
# Retrieve relevant documents based on the user's query
if retriever:
docs = retriever.get_relevant_documents(message)
context = "\n\n".join([doc.page_content for doc in docs[:5]]) # Get top 5 relevant documents
print(f"Context from retriever: {context[:200]}...") # Print first 200 chars for debug
else:
context = "I'm an AI assistant for Atomcamp, a data science education platform."
print("Retriever not initialized, using default context.")
response = generate_response(message, context)
return jsonify({'response': response})
except Exception as e:
print(f"Error in chat endpoint: {e}")
return jsonify({'error': f'Error: {str(e)}'}), 500
@app.route('/static/<path:filename>')
def static_files(filename):
return send_from_directory('static', filename)
# Initialize systems
initialize_groq()
initialize_vectorstore()
if __name__ == "__main__":
port = int(os.environ.get("PORT", 7860))
app.run(host="0.0.0.0", port=port, debug=False) |