Initial commit: Hermes skill rag-pipeline-docker

scripts/test_qdrant_search.py

@@ -0,0 +1,60 @@
+#!/usr/bin/env python3
+"""
+test_qdrant_search.py — Тестовый скрипт поиска по Qdrant.
+Берёт текст, получает эмбеддинг через Ollama, ищет в Qdrant.
+
+Использование: python3 scripts/test_qdrant_search.py --query "текст"
+"""
+import argparse
+import json
+import sys
+import urllib.request
+from pathlib import Path
+
+OLLAMA_URL = "http://localhost:11434/api/embeddings"
+EMBEDDING_MODEL = "nomic-embed-text:latest"
+QDRANT_SEARCH_URL = "http://localhost:6333/collections/knowledge_base/points/search"
+TOP_K = 5
+
+
+def get_embedding(text: str) -> list[float]:
+    payload = json.dumps({"model": EMBEDDING_MODEL, "prompt": text}).encode()
+    req = urllib.request.Request(OLLAMA_URL, data=payload,
+                                  headers={"Content-Type": "application/json"})
+    with urllib.request.urlopen(req, timeout=30) as resp:
+        data = json.loads(resp.read())
+    return data.get("embedding")
+
+
+def search_qdrant(vector: list[float], top_k: int = TOP_K) -> list[dict]:
+    payload = json.dumps({
+        "vector": {"name": "dense", "vector": vector},
+        "limit": top_k,
+        "with_payload": True,
+        "with_vector": False,
+    }).encode()
+    req = urllib.request.Request(QDRANT_SEARCH_URL, data=payload,
+                                  headers={"Content-Type": "application/json"})
+    with urllib.request.urlopen(req, timeout=15) as resp:
+        data = json.loads(resp.read())
+    return data.get("result", [])
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--query", "-q", required=True)
+    args = parser.parse_args()
+
+    vector = get_embedding(args.query)
+    print(f"Embedding: {len(vector)} dims")
+
+    results = search_qdrant(vector)
+    print(f"Results: {len(results)}")
+    for i, r in enumerate(results, 1):
+        payload = r.get("payload", {})
+        text = (payload.get("text") or payload.get("content", ""))[:200]
+        print(f"  #{i} score={r['score']:.4f} | {payload.get('source','?')} | {text}...")
+
+
+if __name__ == "__main__":
+    main()