Protokoll #17769

{
    "event": "PreToolUse",
    "tool_name": "Read",
    "tool_input": {
        "file_path": "\/var\/www\/scripts\/pipeline\/analyzers\/entity_extractor.py",
        "limit": 100
    }
}

{
    "tool_response": {
        "type": "text",
        "file": {
            "filePath": "\/var\/www\/scripts\/pipeline\/analyzers\/entity_extractor.py",
            "content": "\"\"\"\nEntity Extraction - Extract and store entities from text.\n\"\"\"\n\nimport json\nimport re\nimport sys\nimport time\nimport unicodedata\n\nimport requests\n\nsys.path.insert(0, \"\/var\/www\/scripts\/pipeline\")\n\nfrom config import ANTHROPIC_MODEL, OLLAMA_HOST\nfrom db import db\nfrom protokoll import protokoll\n\n\ndef normalize_name(name: str) -> str:\n    \"\"\"Generate canonical_name from entity name.\n\n    Rules:\n    - Lowercase\n    - German umlauts: ä→ae, ö→oe, ü→ue, ß→ss\n    - Replace spaces with underscores\n    - Remove special characters except underscores\n    - Collapse multiple underscores\n    \"\"\"\n    if not name:\n        return \"\"\n\n    result = name.lower()\n\n    replacements = {\n        \"ä\": \"ae\", \"ö\": \"oe\", \"ü\": \"ue\", \"ß\": \"ss\",\n        \"Ä\": \"ae\", \"Ö\": \"oe\", \"Ü\": \"ue\",\n    }\n    for old, new in replacements.items():\n        result = result.replace(old, new)\n\n    result = unicodedata.normalize(\"NFKD\", result)\n    result = result.encode(\"ascii\", \"ignore\").decode(\"ascii\")\n    result = re.sub(r\"[\\s\\-]+\", \"_\", result)\n    result = re.sub(r\"[^a-z0-9_]\", \"\", result)\n    result = re.sub(r\"_+\", \"_\", result)\n    result = result.strip(\"_\")\n\n    return result\n\n\ndef extract_entities_ollama(text: str, model: str = \"gemma3:27b-it-qat\") -> list[dict]:\n    \"\"\"Extract entities using Ollama.\"\"\"\n    prompt_data = db.get_prompt_by_use_case(\"entity_extraction\")\n    prompt_template = prompt_data[\"content\"] if prompt_data else None\n\n    if not prompt_template:\n        db.log(\"WARNING\", \"entity_extraction prompt not found in DB, using fallback\")\n        prompt_template = \"\"\"Analysiere den Text und extrahiere wichtige Entitäten.\nKategorisiere als: PERSON, ORGANIZATION, CONCEPT, LOCATION\nAntworte NUR im JSON-Format:\n{\"entities\": [{\"name\": \"...\", \"type\": \"...\", \"description\": \"...\"}]}\n\nText:\n{{TEXT}}\"\"\"\n\n    prompt = prompt_template.replace(\"{{TEXT}}\", text[:3000])\n\n    try:\n        start_time = time.time()\n        response = requests.post(\n            f\"{OLLAMA_HOST}\/api\/generate\",\n            json={\"model\": model, \"prompt\": prompt, \"stream\": False, \"format\": \"json\"},\n            timeout=120,\n        )\n        response.raise_for_status()\n        data = response.json()\n        duration_ms = int((time.time() - start_time) * 1000)\n\n        response_text = data.get(\"response\", \"{}\")\n\n        protokoll.log_llm_call(\n            request=f\"[entity_extraction] {prompt[:500]}...\",\n            response=response_text[:2000],\n            model_name=f\"ollama:{model}\",\n            tokens_input=data.get(\"prompt_eval_count\", 0),\n            tokens_output=data.get(\"eval_count\", 0),\n            duration_ms=duration_ms,\n            status=\"completed\",\n        )\n\n        try:\n            entities = json.loads(response_text)\n            return entities.get(\"entities\", [])\n        except json.JSONDecodeError:\n            db.log(\"WARNING\", \"Failed to parse entity JSON from Ollama\")\n            return []\n    except Exception as e:\n        db.log(\"ERROR\", f\"Ollama entity extraction failed: {e}\")\n        protokoll.log_llm_call(",
            "numLines": 100,
            "startLine": 1,
            "totalLines": 281
        }
    }
}