知识库初始化

curl --location --request POST 'http://121.229.177.64:8088/wanxin_ai//zhixin_agent/knowledge_database/init' \
--header 'Content-Type: application/json' \
--data-raw '{
    "indexing_technique": "high_quality",
    "user_info": {
        "user_name": "hongxm",
        "user_id": "0001"
    },
    "dataset_info": {
        "dataset_name": "测试数据库",
        "dataset_description": "该知识库里面全是关于测试数据库的",
        "data_source_type": "notion_import"
    },
    "process_rule": {
        "rules": {
            "pre_processing_rules": [
                {
                    "id": "remove_extra_spaces",
                    "enabled": true
                },
                {
                    "id": "remove_urls_emails",
                    "enabled": false
                }
            ],
            "segmentation": {
                "separator": "\n\n, \n, 。, !, ？, ",
                "max_tokens": 500,
                "chunk_overlap": 50
            }
        },
        "mode": "custom"
    },
    "doc_form": "text_model",
    "doc_language": "Chinese",
    "retrieval_model": {
        "search_method": "hybrid_search",
        "reranking_enable": true,
        "reranking_model": {
            "reranking_provider_name": "langgenius/tongyi/tongyi",
            "reranking_model_name": "gte-rerank"
        },
        "top_k": 3,
        "score_threshold_enabled": true,
        "score_threshold": 0.5,
        "reranking_mode": "reranking_model",
        "weights": {
            "weight_type": "customized",
            "vector_setting": {
                "vector_weight": 0.7,
                "embedding_provider_name": "",
                "embedding_model_name": ""
            },
            "keyword_setting": {
                "keyword_weight": 0.3
            }
        }
    },
    "embedding_model": "text-embedding-v3",
    "embedding_model_provider": "langgenius/tongyi/tongyi"
}'