feat(rag): RAG Hermes — Qdrant + rag-ingest/rag-query + skill funk-ai

Indexation de admin/ (284 chunks) dans Qdrant via embeddings Qwen3-8B.
rag-query utilisable en CLI et depuis le profil funk-ai de Hermes.
Note: modèle d'embedding générique — qualité limitée, voir admin/ia/rag.md.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

ansible/roles/rag/files/rag-query

@@ -0,0 +1,76 @@
+#!/usr/bin/env python3
+"""
+Interroge la base vectorielle Qdrant avec une question en langage naturel.
+Usage: rag-query "ma question" [--top N]
+Retourne les passages de documentation les plus pertinents.
+"""
+import sys
+import json
+import os
+import urllib.request
+
+QDRANT_URL  = os.environ.get("QDRANT_URL",  "http://127.0.0.1:6333")
+EMBED_URL   = os.environ.get("EMBED_URL",   "http://192.168.10.20:1234/v1/embeddings")
+EMBED_MODEL = os.environ.get("EMBED_MODEL", "qwen3-8b")
+COLLECTION  = os.environ.get("RAG_COLLECTION", "funk-docs")
+MIN_SCORE   = 0.60
+
+
+def _post(url, data):
+    req = urllib.request.Request(
+        url,
+        data=json.dumps(data).encode(),
+        headers={"Content-Type": "application/json"},
+        method="POST"
+    )
+    with urllib.request.urlopen(req, timeout=60) as r:
+        return json.loads(r.read())
+
+
+def embed(text):
+    result = _post(EMBED_URL, {"model": EMBED_MODEL, "input": text})
+    return result["data"][0]["embedding"]
+
+
+def search(question, top=5):
+    vector = embed(question)
+    result = _post(f"{QDRANT_URL}/collections/{COLLECTION}/points/search", {
+        "vector": vector,
+        "limit": top,
+        "with_payload": True,
+        "score_threshold": MIN_SCORE,
+    })
+    return result["result"]
+
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("Usage: rag-query \"question\" [--top N]", file=sys.stderr)
+        sys.exit(1)
+
+    question = sys.argv[1]
+    top = 5
+    if "--top" in sys.argv:
+        idx = sys.argv.index("--top")
+        try:
+            top = int(sys.argv[idx + 1])
+        except (IndexError, ValueError):
+            pass
+
+    try:
+        results = search(question, top)
+    except Exception as e:
+        print(f"ERREUR: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    if not results:
+        print(f"Aucun résultat pertinent pour : {question}")
+        sys.exit(0)
+
+    print(f"=== Contexte RAG — {len(results)} résultat(s) pour : {question} ===\n")
+    for i, r in enumerate(results, 1):
+        p = r["payload"]
+        score = r["score"]
+        print(f"--- [{i}] {p['file']} § {p['section']}  (score: {score:.3f}) ---")
+        print(p["text"][:700])
+        print()