Lars
12043b7752
All checks were successful
Deploy mindnet to llm-node / deploy (push) Successful in 2s
97 lines
3.6 KiB
Python
97 lines
3.6 KiB
Python
#!/usr/bin/env python3
|
||
"""
|
||
Richtet die Qdrant-Collections für das mindnet-Projekt ein.
|
||
|
||
- mindnet_chunks : semantische Suche über Text-Chunks (384/Cosine)
|
||
- mindnet_notes : 1 Punkt pro Notiz (optional Titel-Embedding)
|
||
- mindnet_edges : explizite Link-Kanten (Dummy-Vektor size=1; Filter über Payload)
|
||
|
||
Idempotent: legt nur an, wenn nicht vorhanden.
|
||
"""
|
||
|
||
import os
|
||
import sys
|
||
import json
|
||
import argparse
|
||
import requests
|
||
|
||
DEFAULT_QDRANT_URL = os.environ.get("QDRANT_URL", "http://127.0.0.1:6333")
|
||
|
||
def rq(method: str, path: str, **kwargs) -> requests.Response:
|
||
url = DEFAULT_QDRANT_URL.rstrip("/") + path
|
||
r = requests.request(method, url, timeout=15, **kwargs)
|
||
if not r.ok:
|
||
raise RuntimeError(f"{method} {url} -> {r.status_code} {r.text}")
|
||
return r
|
||
|
||
def collection_exists(name: str) -> bool:
|
||
r = rq("GET", f"/collections/{name}")
|
||
data = r.json()
|
||
return data.get("result", {}).get("status") == "green"
|
||
|
||
def create_collection(name: str, size: int, distance: str = "Cosine") -> None:
|
||
if collection_exists(name):
|
||
print(f"[=] Collection '{name}' existiert bereits – überspringe Anlage.")
|
||
return
|
||
payload = {"vectors": {"size": size, "distance": distance}}
|
||
rq("PUT", f"/collections/{name}", json=payload)
|
||
print(f"[+] Collection '{name}' angelegt (size={size}, distance={distance}).")
|
||
|
||
def create_keyword_index(collection: str, field: str) -> None:
|
||
payload = {"field_name": field, "field_schema": "keyword"}
|
||
rq("PUT", f"/collections/{collection}/index", json=payload)
|
||
print(f"[+] Index keyword on {collection}.{field}")
|
||
|
||
def create_text_index(collection: str, field: str = "text") -> None:
|
||
payload = {"field_name": field, "field_schema": {"type": "text"}}
|
||
rq("PUT", f"/collections/{collection}/index", json=payload)
|
||
print(f"[+] Index text on {collection}.{field}")
|
||
|
||
def main():
|
||
ap = argparse.ArgumentParser()
|
||
ap.add_argument("--qdrant-url", default=DEFAULT_QDRANT_URL, help="z.B. http://127.0.0.1:6333")
|
||
ap.add_argument("--prefix", default="mindnet", help="Collection-Präfix (default: mindnet)")
|
||
ap.add_argument("--dim", type=int, default=384, help="Embedding-Dimension (384 für all-MiniLM-L6-v2)")
|
||
ap.add_argument("--distance", default="Cosine", choices=["Cosine", "Euclid", "Dot"], help="Distanzmetrik")
|
||
args = ap.parse_args()
|
||
|
||
# Qdrant-URL überschreiben, falls per Argument gesetzt
|
||
global DEFAULT_QDRANT_URL
|
||
DEFAULT_QDRANT_URL = args.qdrant_url
|
||
|
||
chunks = f"{args.prefix}_chunks"
|
||
notes = f"{args.prefix}_notes"
|
||
edges = f"{args.prefix}_edges"
|
||
|
||
# 1) Collections anlegen
|
||
create_collection(chunks, size=args.dim, distance=args.distance)
|
||
create_collection(notes, size=args.dim, distance=args.distance)
|
||
create_collection(edges, size=1, distance=args.distance) # Dummy-Vektor
|
||
|
||
# 2) Indizes
|
||
for f in ["note_id", "Status", "Typ", "title", "path"]:
|
||
create_keyword_index(chunks, f)
|
||
for f in ["tags", "Rolle", "links"]:
|
||
create_keyword_index(chunks, f)
|
||
create_text_index(chunks, "text")
|
||
|
||
for f in ["note_id", "title", "path", "Typ", "Status"]:
|
||
create_keyword_index(notes, f)
|
||
for f in ["tags", "Rolle"]:
|
||
create_keyword_index(notes, f)
|
||
|
||
for f in ["src_note_id", "dst_note_id", "src_chunk_id", "dst_chunk_id", "link_text", "relation"]:
|
||
create_keyword_index(edges, f)
|
||
|
||
# 3) Ausgabe
|
||
r = rq("GET", "/collections")
|
||
print("\n[Info] Collections vorhanden:")
|
||
print(json.dumps(r.json().get("result", {}).get("collections", []), indent=2, ensure_ascii=False))
|
||
|
||
if __name__ == "__main__":
|
||
try:
|
||
main()
|
||
except Exception as e:
|
||
print(f"[ERROR] {e}", file=sys.stderr)
|
||
sys.exit(1)
|