graph_rag_server/conf/rag_parser_config.py

class RagParserDefaults:

    DATASET_PERMISSION="team"

    DATASET_CHUNK_METHOD="naive"

    DATASET_CONFIG_DICT = {
            "chunk_token_num": 256,
            "delimiter": "\n!?;。；！？",
            "html4excel": False,
            "layout_recognize": "Pro/Qwen/Qwen2.5-VL-7B-Instruct@SILICONFLOW",
            "auto_keywords": 5,
            "tag_kb_ids": [],
            "topn_tags": 3,
            "task_page_size": 4,
            "raptor": {
                "max_cluster": 64,
                "max_token": 256,
                "prompt": "Please summarize the following paragraphs. Be careful with the numbers, do not make things up. Paragraphs as following:\n      {cluster_content}\nThe above is the content you need to summarize.",
                "random_seed": 0,
                "threshold": 0.1,
                "use_raptor": True
            },
            "graphrag": {
                "resolution": True,
                "use_graphrag": True,
                "method": "general",
                "entity_types": [
                    "event",
                    "Book",
                    "Author",
                    "Illustrator",
                    "Series",
                    "Theme",
                    "Genre",
                    "Character",
                    "Setting",
                    "AgeGroup",
                    "Competency",
                    "ArtStyle",
                    "Award",
                    "Publisher",
                    "Role"
                ]
            }
        }