scripts/test_llm_api.py hinzugefügt

scripts/test_llm_api.py

@@ -0,0 +1,307 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Erweiterter API-Schnelltest – v2.0
+
+Deckt ab:
+- OpenAPI erreichbar
+- Wiki-Routen: /import/wiki/health, /semantic/pages, /info, /parsepage, optional /login
+- Exercise-Routen: /exercise (Upsert & Idempotenz), /exercise/by-external-id, /exercise/search (Filter-only & Vector),
+  /exercise/delete-by-external-id
+- Embed-Routen: /embed, /search, /prompt, /delete-source, /delete-collection
+
+Konfiguration via ENV:
+  BASE_URL (default http://127.0.0.1:8000)
+  QDRANT_HTTP (default http://127.0.0.1:6333) – optional, hier nicht zwingend genutzt
+  TEST_WIKI_CATEGORY (default "Übungen")
+  WIKI_BOT_USER, WIKI_BOT_PASSWORD – optional; wenn gesetzt, wird /import/wiki/login getestet
+
+Exit-Code != 0 bei Fehler. Ausgabe mit ✓/✗.
+"""
+
+import os
+import sys
+import json
+import uuid
+import time
+import requests
+
+BASE = os.getenv("BASE_URL", "http://127.0.0.1:8000").rstrip("/")
+TEST_WIKI_CATEGORY = os.getenv("TEST_WIKI_CATEGORY", "Übungen")
+WIKI_USER = os.getenv("WIKI_BOT_USER")
+WIKI_PASS = os.getenv("WIKI_BOT_PASSWORD")
+
+COL = "test_collection"
+SRC = "unit-test-src"
+
+# ---- helpers ----
+
+def fail(msg, resp: requests.Response | None = None):
+    print("✗", msg)
+    if resp is not None:
+        try:
+            print("  → status:", resp.status_code)
+            print("  → body:", resp.text[:800])
+        except Exception:
+            pass
+    sys.exit(1)
+
+
+def ok(msg):
+    print("✓", msg)
+
+
+# ---- basic ----
+
+def test_openapi():
+    r = requests.get(f"{BASE}/openapi.json")
+    if r.status_code != 200:
+        fail("/openapi.json nicht erreichbar", r)
+    ok("OpenAPI erreichbar")
+
+
+# ---- wiki ----
+
+def test_wiki_health():
+    r = requests.get(f"{BASE}/import/wiki/health", params={"verbose": 1})
+    if r.status_code != 200 or r.json().get("status") != "ok":
+        fail("/import/wiki/health fehlgeschlagen", r)
+    ok("Wiki /health ok")
+
+
+def test_wiki_semantic_pages_pick_one():
+    r = requests.get(f"{BASE}/import/wiki/semantic/pages", params={"category": TEST_WIKI_CATEGORY})
+    if r.status_code != 200:
+        fail("/import/wiki/semantic/pages fehlgeschlagen", r)
+    data = r.json()
+    if not isinstance(data, dict) or not data:
+        fail("/semantic/pages lieferte keine Titel", r)
+    # Beliebigen Titel nehmen (stabil: erster Key)
+    title = next(iter(data.keys()))
+    entry = data[title]
+    pageid = entry.get("pageid")
+    if not pageid:
+        fail("/semantic/pages ohne pageid nach Enrichment", r)
+    ok(f"Wiki /semantic/pages ok – Beispiel: '{title}' (pageid={pageid})")
+    return title, pageid
+
+
+def test_wiki_info(title: str):
+    r = requests.get(f"{BASE}/import/wiki/info", params={"title": title})
+    if r.status_code != 200:
+        fail("/import/wiki/info fehlgeschlagen", r)
+    js = r.json()
+    if not js.get("pageid"):
+        fail("/info ohne pageid", r)
+    ok("Wiki /info ok")
+
+
+def test_wiki_parse(pageid: int, title: str):
+    r = requests.get(f"{BASE}/import/wiki/parsepage", params={"pageid": pageid, "title": title})
+    if r.status_code != 200:
+        fail("/import/wiki/parsepage fehlgeschlagen", r)
+    js = r.json()
+    if not isinstance(js.get("wikitext"), str):
+        fail("/parsepage ohne wikitext", r)
+    ok("Wiki /parsepage ok")
+
+
+def test_wiki_login_if_env():
+    if not (WIKI_USER and WIKI_PASS):
+        ok("Wiki /login übersprungen (ENV nicht gesetzt)")
+        return
+    r = requests.post(f"{BASE}/import/wiki/login", json={"username": WIKI_USER, "password": WIKI_PASS})
+    if r.status_code != 200 or r.json().get("status") != "success":
+        fail("/import/wiki/login fehlgeschlagen", r)
+    ok("Wiki /login ok")
+
+
+# ---- exercise ----
+
+def make_exercise_payload(external_id: str):
+    return {
+        "external_id": external_id,
+        "fingerprint": "unit-test-sha",
+        "source": "UnitTest",
+        "title": "Testübung Reaktion",
+        "summary": "Kurzbeschreibung für Test.",
+        "short_description": "Kurzbeschreibung für Test.",
+        "keywords": ["Reaktion", "Bälle", "Bälle"],
+        "link": "http://example.local",
+        "discipline": "Karate",
+        "group": "5",
+        "age_group": "Teenager",
+        "target_group": "Breitensport",
+        "min_participants": 1,
+        "duration_minutes": 10,
+        "capabilities": {"Reaktionsfähigkeit": 2, "Kopplungsfähigkeit": 1},
+        "category": "Übungen",
+        "purpose": "Aufwärmen",
+        "execution": "Einfacher Ablauf.",
+        "notes": "Hinweise.",
+        "preparation": "Bälle holen.",
+        "method": "Frontale Methode",
+        "equipment": ["Bälle", "Pratze"]
+    }
+
+
+def test_exercise_upsert_and_idempotence():
+    ext = f"ut:{uuid.uuid4()}"
+    payload = make_exercise_payload(ext)
+
+    # create
+    r1 = requests.post(f"{BASE}/exercise", json=payload)
+    if r1.status_code != 200:
+        fail("POST /exercise (create) fehlgeschlagen", r1)
+    id1 = r1.json().get("id")
+    if not id1:
+        fail("POST /exercise lieferte keine id", r1)
+
+    # update (idempotent)
+    r2 = requests.post(f"{BASE}/exercise", json=payload)
+    if r2.status_code != 200:
+        fail("POST /exercise (update) fehlgeschlagen", r2)
+    id2 = r2.json().get("id")
+    if id2 != id1:
+        fail("Idempotenz verletzt: id hat sich geändert")
+
+    # by-external-id
+    r3 = requests.get(f"{BASE}/exercise/by-external-id", params={"external_id": ext})
+    if r3.status_code != 200:
+        fail("GET /exercise/by-external-id fehlgeschlagen", r3)
+    id3 = r3.json().get("id")
+    if id3 != id1:
+        fail("Lookup by external_id liefert andere id")
+
+    ok("Exercise Upsert & Idempotenz ok")
+    return ext, id1
+
+
+def test_exercise_search_filter(ext_id: str):
+    # Treffer mit Level >=2 in Reaktionsfähigkeit und Ausrüstung Bälle
+    req = {
+        "discipline": "Karate",
+        "equipment_all": ["Bälle"],
+        "capability_names": ["Reaktionsfähigkeit"],
+        "capability_ge_level": 2,
+        "limit": 10,
+    }
+    r = requests.post(f"{BASE}/exercise/search", json=req)
+    if r.status_code != 200:
+        fail("POST /exercise/search (Filter) fehlgeschlagen", r)
+    js = r.json(); hits = js.get("hits", [])
+    if not isinstance(hits, list) or not hits:
+        fail("/exercise/search liefert keine Treffer (Filter)", r)
+    # Optional prüfen, ob unser Testpunkt in den Treffern ist
+    if not any(h.get("payload", {}).get("external_id") == ext_id for h in hits):
+        ok("Exercise Search (Filter) ok – Testpunkt nicht zwingend unter Top-N")
+    else:
+        ok("Exercise Search (Filter) ok – Testpunkt gefunden")
+
+
+def test_exercise_search_vector():
+    req = {
+        "query": "Aufwärmen 10min, Reaktionsfähigkeit, Teenager, Bälle",
+        "discipline": "Karate",
+        "limit": 5
+    }
+    r = requests.post(f"{BASE}/exercise/search", json=req)
+    if r.status_code != 200:
+        fail("POST /exercise/search (Vector) fehlgeschlagen", r)
+    js = r.json(); hits = js.get("hits", [])
+    if not isinstance(hits, list):
+        fail("/exercise/search (Vector) liefert ungültige Struktur", r)
+    ok(f"Exercise Search (Vector) ok – {len(hits)} Treffer")
+
+
+def test_exercise_delete(ext_id: str):
+    r = requests.delete(f"{BASE}/exercise/delete-by-external-id", params={"external_id": ext_id})
+    if r.status_code != 200:
+        fail("DELETE /exercise/delete-by-external-id fehlgeschlagen", r)
+    ok("Exercise Delete-by-external-id ok")
+
+
+# ---- embed pipeline (bestehend) ----
+
+def test_embed_ingest():
+    payload = {
+        "collection": COL,
+        "chunks": [
+            {"text": "Das ist ein Testtext für Embed.", "source": SRC}
+        ]
+    }
+    r = requests.post(f"{BASE}/embed", json=payload)
+    if r.status_code != 200:
+        fail("/embed fehlgeschlagen", r)
+    js = r.json()
+    if js.get("count") != 1:
+        fail("/embed count != 1", r)
+    ok("Embed ingest ok")
+
+
+def test_embed_search():
+    params = {"query": "Testtext", "collection": COL}
+    r = requests.get(f"{BASE}/search", params=params)
+    if r.status_code != 200:
+        fail("/search fehlgeschlagen", r)
+    results = r.json()
+    if not any("score" in item for item in results):
+        fail("/search keine Treffer")
+    ok("Embed search ok")
+
+
+def test_prompt():
+    payload = {"query": "Wie lautet dieser Testtext?", "context_limit": 1, "collection": COL}
+    r = requests.post(f"{BASE}/prompt", json=payload)
+    if r.status_code != 200:
+        fail("/prompt fehlgeschlagen", r)
+    data = r.json()
+    if "answer" not in data:
+        fail("/prompt ohne 'answer'")
+    ok("Prompt ok")
+
+
+def test_delete_source():
+    params = {"collection": COL, "source": SRC}
+    r = requests.delete(f"{BASE}/delete-source", params=params)
+    if r.status_code != 200:
+        fail("/delete-source fehlgeschlagen", r)
+    data = r.json()
+    if data.get("count") != 1:
+        fail("/delete-source count != 1")
+    ok("Delete-source ok")
+
+
+def test_delete_collection():
+    params = {"collection": COL}
+    r = requests.delete(f"{BASE}/delete-collection", params=params)
+    if r.status_code != 200:
+        fail("/delete-collection fehlgeschlagen", r)
+    ok("Delete-collection ok")
+
+
+if __name__ == "__main__":
+    print("\nStarte API-Tests...\n")
+    test_openapi()
+
+    # Wiki
+    test_wiki_health()
+    title, pageid = test_wiki_semantic_pages_pick_one()
+    test_wiki_info(title)
+    test_wiki_parse(pageid, title)
+    test_wiki_login_if_env()
+
+    # Exercise
+    ext, _id = test_exercise_upsert_and_idempotence()
+    test_exercise_search_filter(ext)
+    test_exercise_search_vector()
+    test_exercise_delete(ext)
+
+    # Embed
+    test_embed_ingest()
+    test_embed_search()
+    test_prompt()
+    test_delete_source()
+    test_delete_collection()
+
+    print("\n🎉 Alle Tests erfolgreich durchlaufen!\n")