Delete chatbot.py

chatbot.py

@@ -1,210 +0,0 @@
-"""
-chatbot.py — Conversational AI that answers from what it has actually learned.
-Synthesizes knowledge into natural paragraph answers, like ChatGPT/Claude/Gemini.
-"""
-import json, re, math, os, random
-from collections import Counter, defaultdict
-from html import unescape
-
-KNOWLEDGE_FILE = 'knowledge.jsonl'
-STOPWORDS = {
-    'a','an','the','is','it','in','on','at','to','for','of','and','or','but',
-    'was','are','were','be','been','have','has','had','do','does','did','will',
-    'would','could','should','may','might','that','this','these','those','with',
-    'from','by','as','not','also','than','then','so','if','when','what','how',
-    'who','which','its','their','our','your','my','his','her','we','they','he',
-    'she','you','i','me','him','us','them','said','says',
-}
-
-def tokenize(text):
-    text = re.sub(r'[^\w\s]', ' ', text.lower())
-    return [w for w in text.split() if w not in STOPWORDS and len(w) > 2]
-
-def clean_text(text):
-    """Remove HTML artifacts from stored text."""
-    text = unescape(text)
-    text = re.sub(r'&#?[a-zA-Z0-9]+;', ' ', text)
-    text = re.sub(r'<[^>]+>', ' ', text)
-    text = re.sub(r'\s+', ' ', text).strip()
-    return text
-
-
-class KnowledgeBase:
-    def __init__(self):
-        self.docs=[]; self.doc_tokens=[]; self.idf={}; self.last_count=0
-        self._load()
-
-    def _load(self):
-        if not os.path.exists(KNOWLEDGE_FILE): return
-        new_docs = []
-        try:
-            with open(KNOWLEDGE_FILE,'r',encoding='utf-8') as f:
-                for line in f:
-                    line=line.strip()
-                    if line:
-                        try: new_docs.append(json.loads(line))
-                        except: pass
-        except: return
-        if len(new_docs)==self.last_count: return
-        self.docs=new_docs; self.last_count=len(new_docs)
-        self.doc_tokens=[tokenize(clean_text(d.get('text',''))) for d in self.docs]
-        N=len(self.docs)
-        df=defaultdict(int)
-        for tokens in self.doc_tokens:
-            for w in set(tokens): df[w]+=1
-        self.idf={w:math.log((N+1)/(c+1))+1 for w,c in df.items()}
-
-    def search(self, query, top_k=8):
-        self._load()
-        if not self.docs: return []
-        q=tokenize(query)
-        if not q: return []
-        def score(dt):
-            tf=Counter(dt); n=max(len(dt),1)
-            return sum((tf[w]/n)*self.idf.get(w,0) for w in q if w in tf)
-        ranked=sorted(range(len(self.docs)),key=lambda i:-score(self.doc_tokens[i]))
-        return [(self.docs[i], score(self.doc_tokens[i])) for i in ranked[:top_k]
-                if score(self.doc_tokens[i])>0]
-
-    def get_stats(self):
-        self._load()
-        return {
-            'total':      len(self.docs),
-            'categories': dict(Counter(d.get('category','other') for d in self.docs)),
-            'sources':    dict(Counter(d.get('source','unknown') for d in self.docs)),
-        }
-
-
-def _synthesize(query, results):
-    """
-    Turn retrieved article snippets into a natural conversational answer.
-    Like ChatGPT — reads all sources, writes a coherent paragraph response.
-    """
-    q_tokens = set(tokenize(query))
-
-    # Gather the best individual sentences across all docs
-    all_sentences = []
-    for doc, sc in results:
-        text = clean_text(doc.get('text', ''))
-        # Split into sentences
-        sents = re.split(r'(?<=[.!?])\s+', text)
-        for s in sents:
-            s = s.strip()
-            if len(s) < 30: continue
-            overlap = len(q_tokens & set(tokenize(s)))
-            # Slight relevance boost for sentences that mention query words
-            all_sentences.append((overlap + sc * 0.3, s))
-
-    # Deduplicate and pick top sentences
-    seen = set(); chosen = []
-    for score, sent in sorted(all_sentences, reverse=True):
-        key = sent[:60].lower()
-        if key not in seen and len(chosen) < 6:
-            seen.add(key)
-            chosen.append(sent)
-
-    if not chosen:
-        return None
-
-    # Build a flowing paragraph (not a bullet dump)
-    # Join sentences intelligently
-    answer_sents = chosen[:4]
-
-    # Fix any leftover HTML entities in chosen sentences
-    answer_sents = [unescape(s) for s in answer_sents]
-
-    # Combine into paragraphs
-    if len(answer_sents) <= 2:
-        paragraph = ' '.join(answer_sents)
-    else:
-        paragraph = ' '.join(answer_sents[:2])
-        rest = ' '.join(answer_sents[2:])
-        paragraph = paragraph + '\n\n' + rest
-
-    return paragraph.strip()
-
-
-class RAGChatbot:
-    def __init__(self):
-        self.kb = KnowledgeBase()
-
-    def _answer(self, query, results, stats):
-        total = stats['total']
-
-        if total == 0:
-            return ("My brain is empty right now 🧠\n\n"
-                    "Go to **Control → ▶ Start Text** to feed me internet articles. "
-                    "The more I read, the smarter I get!")
-
-        if not results:
-            topics = ', '.join(list(stats['categories'].keys())[:5])
-            return (f"I've read **{total} articles** so far, but I haven't learned "
-                    f"enough about *{query}* yet.\n\n"
-                    f"My current knowledge is mostly about: **{topics}**.\n\n"
-                    f"Keep me training and I'll learn more over time! 📚")
-
-        answer = _synthesize(query, results)
-        if not answer:
-            return (f"I found related articles but couldn't form a clear answer yet. "
-                    f"Try asking in a different way!")
-
-        # Conversational wrap — just the answer, clean and simple
-        return answer
-
-    def chat(self, user_message, history):
-        history = list(history or [])
-        msg = user_message.strip()
-        if not msg: return history
-
-        lower = msg.lower()
-        stats = self.kb.get_stats()
-
-        # ── Greetings ──
-        if lower in ('hi','hello','hey','sup','yo','hiya','howdy','helo','hai'):
-            total = stats['total']
-            if total == 0:
-                bot_reply = ("Hey! 👋 I'm your AI, but I haven't read anything yet.\n\n"
-                             "Go to **Control → ▶ Start Text** to start teaching me!")
-            else:
-                topics = ', '.join(list(stats['categories'].keys())[:4])
-                bot_reply = (f"Hey! 👋 I've read **{total} articles** so far.\n\n"
-                             f"I know quite a bit about **{topics}**. What do you want to know?")
-
-        elif any(p in lower for p in ('how are you','how r you',"what's up",'whats up')):
-            bot_reply = "I'm doing great — always learning! 🤖 What do you want to know?"
-
-        elif any(p in lower for p in ('who are you','what are you','what can you do','tell me about yourself')):
-            bot_reply = (
-                "I'm a **Living Neural Network** — an AI that learns from real internet articles in real time! 🧠\n\n"
-                f"I've read **{stats['total']} articles** so far. Unlike ChatGPT, I only know what "
-                "I've actually been trained on — no pre-built knowledge. "
-                "The more articles I read, the smarter I get. Ask me anything I might have learned!"
-            )
-
-        elif lower in ('stats','status','what do you know','knowledge'):
-            lines = '\n'.join(f"• **{k}**: {v} articles"
-                             for k,v in sorted(stats['categories'].items(),key=lambda x:-x[1]))
-            srcs  = ', '.join(f"{k} ({v})" for k,v in list(stats['sources'].items())[:6])
-            bot_reply = (f"**My knowledge so far:**\n\n{lines or '• nothing yet'}\n\n"
-                         f"**Sources I've read from:** {srcs or 'none yet'}\n\n"
-                         f"**Total:** {stats['total']} articles")
-
-        elif lower in ('help','?','commands'):
-            bot_reply = ("Just ask me anything — I'll answer from what I've learned!\n\n"
-                         "**Examples:**\n"
-                         "- *What is science?*\n"
-                         "- *Who is Elon Musk?*\n"
-                         "- *What's happening in AI?*\n"
-                         "- *Tell me about climate change*\n\n"
-                         "Type `stats` to see what I know.")
-
-        elif any(p in lower for p in ('thanks','thank you','thx','ty')):
-            bot_reply = "You're welcome! 😊"
-
-        else:
-            results   = self.kb.search(msg, top_k=8)
-            bot_reply = self._answer(msg, results, stats)
-
-        history.append({"role": "user",      "content": user_message})
-        history.append({"role": "assistant", "content": bot_reply})
-        return history