Initial commit: UMB Telegram Bot

2026-07-07 18:30:17 +07:00
commit 76e5701eba
31 changed files with 2524 additions and 0 deletions
@@ -0,0 +1,133 @@
+import json
+import logging
+import math
+import re
+
+from bot.utils.ai_client import _get_connector
+from bot.utils.database import get_summaries, save_conversation_summary
+from config import ROUTERAI_API_KEY, ROUTERAI_BASE_URL
+
+logger = logging.getLogger(__name__)
+
+EMBEDDING_MODEL = "openai/text-embedding-3-small"
+EMBEDDING_URL = f"{ROUTERAI_BASE_URL}/embeddings"
+
+
+async def create_embedding(text: str) -> list[float] | None:
+    if not ROUTERAI_API_KEY:
+        logger.warning("Embedding skipped | ROUTERAI_API_KEY not set")
+        return None
+
+    headers = {
+        "Authorization": f"Bearer {ROUTERAI_API_KEY}",
+        "Content-Type": "application/json",
+    }
+
+    payload = {
+        "model": EMBEDDING_MODEL,
+        "input": text[:8000],
+        "encoding_format": "float",
+    }
+
+    import aiohttp
+    from bot.utils.ai_client import get_client_timeout
+
+    connector = _get_connector()
+
+    try:
+        async with aiohttp.ClientSession(timeout=get_client_timeout(30), connector=connector) as session:
+            async with session.post(EMBEDDING_URL, json=payload, headers=headers) as response:
+                if response.status != 200:
+                    error_body = await response.text()
+                    logger.warning("Embedding error | status=%s error=%s", response.status, error_body[:200])
+                    return None
+
+                data = await response.json()
+                embedding = data["data"][0]["embedding"]
+                logger.info("Embedding created | dim=%d input_len=%d", len(embedding), min(len(text), 8000))
+                return embedding
+    except Exception as e:
+        logger.error("Embedding request error: %s", e)
+        return None
+
+
+def cosine_similarity(a: list[float], b: list[float]) -> float:
+    dot = sum(x * y for x, y in zip(a, b))
+    norm_a = math.sqrt(sum(x * x for x in a))
+    norm_b = math.sqrt(sum(y * y for y in b))
+    if norm_a == 0 or norm_b == 0:
+        return 0.0
+    return dot / (norm_a * norm_b)
+
+
+async def find_relevant_summaries(user_id: int, chat_id: int, query: str, top_k: int = 3) -> list[str]:
+    query_emb = await create_embedding(query)
+    if not query_emb:
+        return []
+
+    summaries = await get_summaries(user_id, chat_id, limit=20)
+    if not summaries:
+        logger.info("Relevant summaries | user=%d chat=%d no summaries found", user_id, chat_id)
+        return []
+
+    scored = []
+    for s in summaries:
+        if not s["embedding"]:
+            continue
+        try:
+            emb = json.loads(s["embedding"])
+            score = cosine_similarity(query_emb, emb)
+            scored.append((score, s["summary"]))
+        except Exception:
+            continue
+
+    scored.sort(key=lambda x: x[0], reverse=True)
+    top = [text for _, text in scored[:top_k]]
+    top_score = scored[0][0] if scored else 0
+
+    logger.info(
+        "Relevant summaries | user=%d chat=%d found=%d top_score=%.3f",
+        user_id, chat_id, len(top), top_score,
+    )
+    return top
+
+
+async def save_summary_with_embedding(user_id: int, chat_id: int, summary_text: str) -> None:
+    emb = await create_embedding(summary_text)
+    embedding_json = json.dumps(emb) if emb else None
+    await save_conversation_summary(user_id, chat_id, summary_text, embedding_json)
+    logger.info(
+        "Summary saved | user=%d chat=%d summary_len=%d emb=%s",
+        user_id, chat_id, len(summary_text), "yes" if emb else "no",
+    )
+
+
+async def generate_summary(messages: list[dict]) -> str | None:
+    from bot.utils.ai_client import ask_ai_simple
+
+    messages_text = "\n".join(
+        f"{'Пользователь' if m['role'] == 'user' else 'Астра'}: {m['content'][:300]}"
+        for m in messages[-50:]
+    )
+
+    prompt = (
+        "Сделай краткую выжимку этого диалога (3-5 предложений). "
+        "Выдели ключевые темы, факты и предпочтения пользователя:\n\n"
+        f"{messages_text}"
+    )
+
+    try:
+        summary = await ask_ai_simple(prompt)
+        if summary and len(summary) > 20:
+            cleaned = re.sub(r"<[^>]+>", "", summary)
+            cleaned = cleaned.strip()
+            logger.info("Summary generated | len=%d", len(cleaned))
+            return cleaned
+        elif summary:
+            logger.warning("Summary too short | len=%d", len(summary))
+        else:
+            logger.warning("Summary generation returned None")
+    except Exception as e:
+        logger.error("Summary generation error: %s", e)
+
+    return None