RagFlow_Plugs/utils/es/templates.py

"""
Elasticsearch 动态模板映射
"""
from typing import Dict, Any


def get_dynamic_templates() -> Dict[str, Any]:
    """
    获取动态模板映射配置
    参考：d:/project/work/ragflow_plugs/book/es_dynamic.md
    
    Returns:
        Dict[str, Any]: 动态模板映射配置
    """
    return {
        "dynamic_templates": [
            {
                "int": {
                    "match": "*_int",
                    "mapping": {
                        "store": True,
                        "type": "integer"
                    }
                }
            },
            {
                "ulong": {
                    "match": "*_ulong",
                    "mapping": {
                        "store": True,
                        "type": "unsigned_long"
                    }
                }
            },
            {
                "long": {
                    "match": "*_long",
                    "mapping": {
                        "store": True,
                        "type": "long"
                    }
                }
            },
            {
                "short": {
                    "match": "*_short",
                    "mapping": {
                        "store": True,
                        "type": "short"
                    }
                }
            },
            {
                "numeric": {
                    "match": "*_flt",
                    "mapping": {
                        "store": True,
                        "type": "float"
                    }
                }
            },
            {
                "tks": {
                    "match": "*_tks",
                    "mapping": {
                        "analyzer": "whitespace",
                        "similarity": "scripted_sim",
                        "store": True,
                        "type": "text"
                    }
                }
            },
            {
                "ltks": {
                    "match": "*_ltks",
                    "mapping": {
                        "analyzer": "whitespace",
                        "store": True,
                        "type": "text"
                    }
                }
            },
            {
                "kwd": {
                    "match": "^(.*_(kwd|id|ids|uid|uids)|uid)$",
                    "match_pattern": "regex",
                    "mapping": {
                        "similarity": "boolean",
                        "store": True,
                        "type": "keyword"
                    }
                }
            },
            {
                "dt": {
                    "match": "^.*(_dt|_time|_at)$",
                    "match_pattern": "regex",
                    "mapping": {
                        "format": "yyyy-MM-dd HH:mm:ss||yyyy-MM-dd||yyyy-MM-dd_HH:mm:ss",
                        "store": True,
                        "type": "date"
                    }
                }
            },
            {
                "nested": {
                    "match": "*_nst",
                    "mapping": {
                        "type": "nested"
                    }
                }
            },
            {
                "object": {
                    "match": "*_obj",
                    "mapping": {
                        "dynamic": True,
                        "type": "object"
                    }
                }
            },
            {
                "string": {
                    "match": "^.*_(with_weight|list)$",
                    "match_pattern": "regex",
                    "mapping": {
                        "index": False,
                        "store": True,
                        "type": "text"
                    }
                }
            },
            {
                "rank_feature": {
                    "match": "*_fea",
                    "mapping": {
                        "type": "rank_feature"
                    }
                }
            },
            {
                "rank_features": {
                    "match": "*_feas",
                    "mapping": {
                        "type": "rank_features"
                    }
                }
            },
            {
                "dense_vector_512": {
                    "match": "*_512_vec",
                    "mapping": {
                        "dims": 512,
                        "index": True,
                        "similarity": "cosine",
                        "type": "dense_vector"
                    }
                }
            },
            {
                "dense_vector_768": {
                    "match": "*_768_vec",
                    "mapping": {
                        "dims": 768,
                        "index": True,
                        "similarity": "cosine",
                        "type": "dense_vector"
                    }
                }
            },
            {
                "dense_vector_1024": {
                    "match": "*_1024_vec",
                    "mapping": {
                        "dims": 1024,
                        "index": True,
                        "similarity": "cosine",
                        "type": "dense_vector"
                    }
                }
            },
            {
                "dense_vector_1536": {
                    "match": "*_1536_vec",
                    "mapping": {
                        "dims": 1536,
                        "index": True,
                        "similarity": "cosine",
                        "type": "dense_vector"
                    }
                }
            },
            {
                "binary": {
                    "match": "*_bin",
                    "mapping": {
                        "type": "binary"
                    }
                }
            }
        ],
        "date_detection": True
    }