3cx-telefonie-middleware/tools/filter_uncertain.py

import json, time, requests
from pathlib import Path
from concurrent.futures import ThreadPoolExecutor, as_completed

BASE = Path("/opt/3cx-middleware/3cx-telefonie-middleware")
SRC = BASE / "data/transcripts"
SCREEN = BASE / "data/transcript_screening.jsonl"
OUT = BASE / "data/transcript_relevance_final.jsonl"

URL = "http://192.168.1.101:11434/api/chat"
MODEL = "llama3.2:3b"
WORKERS = 1

SYSTEM = """Du klassifizierst ein Telefontranskript ausschließlich nach Relevanz.

RELEVANT:
Ein echter Dialog mit Kunde, Interessent, Lieferant oder Geschäftspartner.

IRRELEVANT:
reine Telefonansage, Mailbox, Warteschleife, Fehlanruf ohne Gespräch,
Werbung oder praktisch kein Gespräch.

UNCERTAIN:
nicht eindeutig.

Antworte ausschließlich mit JSON:
{"relevance":"RELEVANT","confidence":0.0}
oder
{"relevance":"IRRELEVANT","confidence":0.0}
oder
{"relevance":"UNCERTAIN","confidence":0.0}
"""

items = []
for line in SCREEN.read_text(encoding="utf-8").splitlines():
    r = json.loads(line)
    if r["relevance"] == "UNCERTAIN":
        items.append(r["file"])

print(f"UNCERTAIN: {len(items)}")

def run(filename):
    text = (SRC / filename).read_text(
        encoding="utf-8", errors="replace"
    ).strip()

    payload = {
        "model": MODEL,
        "messages": [
            {"role": "system", "content": SYSTEM},
            {"role": "user", "content": text[:5000]}
        ],
        "stream": False,
        "think": False,
        "format": "json",
        "options": {"temperature": 0}
    }

    start = time.time()
    r = requests.post(URL, json=payload, timeout=120)
    r.raise_for_status()

    result = json.loads(r.json()["message"]["content"])

    return {
        "file": filename,
        "relevance": result.get("relevance", "UNCERTAIN"),
        "confidence": result.get("confidence", 0),
        "seconds": round(time.time() - start, 1)
    }

with OUT.open("w", encoding="utf-8") as f:
    with ThreadPoolExecutor(max_workers=WORKERS) as pool:
        futures = [pool.submit(run, x) for x in items]

        for i, future in enumerate(as_completed(futures), 1):
            try:
                r = future.result()
                f.write(json.dumps(r, ensure_ascii=False) + "\n")
                f.flush()
                print(
                    f"[{i}/{len(items)}] {r['file']} "
                    f"{r['seconds']}s → {r['relevance']} "
                    f"{r['confidence']}",
                    flush=True
                )
            except Exception as e:
                print("ERROR:", e, flush=True)

print("\nFertig:", OUT)