1 line
4.8 KiB
JSON
1 line
4.8 KiB
JSON
{"repo": "chraise/chemqa", "files": {"config/settings.py": {"f1e9cb05292869f8e088d1c2e9e69056ad00a8d7": {"t": 1785746908.9976573, "n": 914, "h": "6f6dc2a0d860b443", "c": "# 主配置文件\n\nimport os\n\nBASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\n\n\nclass Settings:\n # 数据路径\n RAW_PAPERS_DIR = os.path.join(BASE_DIR, \"data\", \"raw_papers\")\n PROCESSED_DIR = os.path.join(BASE_DIR, \"data\", \"processed\")\n VECTOR_DB_DIR = os.path.join(BASE_DIR, \"data\", \"vector_db\")\n\n # 文本处理参数\n CHUNK_SIZE = 500\n CHUNK_OVERLAP = 50\n\n # 向量存储配置\n EMBEDDING_MODEL = \"text2vec/paraphrase-multilingual-MiniLM-L12-v2\"\n RETRIEVAL_TOP_K = 10\n\n # 更新为DeepSeek API配置\n DEEPSEEK_API_CONFIG = {\n \"api_key\": \"sk-0a6b9d29efa94458ad99009fcb5b46bb\",\n \"base_url\": \"https://api.deepseek.com\",\n \"model\": \"deepseek-reasoner\",\n \"temperature\": 0.3\n }\n\n # PDF解析设置\n PDF_PARSING_ENGINE = \"pymupdf\"\n\n # 系统配置保持不变\n DOMAIN = \"organic electrocatalysis\"\n MAX_TOKENS = 30000\n\n MODEL_DIR = os.path.join(BASE_DIR, \"models\")\n\nsettings = Settings()\n"}, "fc657703017693dbbac9c7511aa295c90df72e4e": {"t": 1785768813.4506288, "n": 914, "h": "6f6dc2a0d860b443", "c": "# 主配置文件\n\nimport os\n\nBASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\n\n\nclass Settings:\n # 数据路径\n RAW_PAPERS_DIR = os.path.join(BASE_DIR, \"data\", \"raw_papers\")\n PROCESSED_DIR = os.path.join(BASE_DIR, \"data\", \"processed\")\n VECTOR_DB_DIR = os.path.join(BASE_DIR, \"data\", \"vector_db\")\n\n # 文本处理参数\n CHUNK_SIZE = 500\n CHUNK_OVERLAP = 50\n\n # 向量存储配置\n EMBEDDING_MODEL = \"text2vec/paraphrase-multilingual-MiniLM-L12-v2\"\n RETRIEVAL_TOP_K = 10\n\n # 更新为DeepSeek API配置\n DEEPSEEK_API_CONFIG = {\n \"api_key\": \"sk-0a6b9d29efa94458ad99009fcb5b46bb\",\n \"base_url\": \"https://api.deepseek.com\",\n \"model\": \"deepseek-reasoner\",\n \"temperature\": 0.3\n }\n\n # PDF解析设置\n PDF_PARSING_ENGINE = \"pymupdf\"\n\n # 系统配置保持不变\n DOMAIN = \"organic electrocatalysis\"\n MAX_TOKENS = 30000\n\n MODEL_DIR = os.path.join(BASE_DIR, \"models\")\n\nsettings = Settings()\n"}, "9fef1713cc8ac15da22b5abf4eae129b6bb8ced8": {"t": 1785768814.7965844, "n": 947, "h": "3980ac86eb9917d1", "c": "# 主配置文件\n\nimport os\n\nBASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\n\n\nclass Settings:\n # 数据路径\n RAW_PAPERS_DIR = os.path.join(BASE_DIR, \"data\", \"raw_papers\")\n PROCESSED_DIR = os.path.join(BASE_DIR, \"data\", \"processed\")\n VECTOR_DB_DIR = os.path.join(BASE_DIR, \"data\", \"vector_db\")\n\n # 文本处理参数\n CHUNK_SIZE = 500\n CHUNK_OVERLAP = 50\n\n # 向量存储配置\n EMBEDDING_MODEL = \"text2vec/paraphrase-multilingual-MiniLM-L12-v2\" # 使用本地模型\n RETRIEVAL_TOP_K = 10 # 增加检索文档数量\n\n # 更新为DeepSeek API配置\n DEEPSEEK_API_CONFIG = {\n \"api_key\": \"sk-0a6b9d29efa94458ad99009fcb5b46bb\",\n \"base_url\": \"https://api.deepseek.com\",\n \"model\": \"deepseek-reasoner\",\n \"temperature\": 0.3\n }\n\n # PDF解析设置\n PDF_PARSING_ENGINE = \"pymupdf\"\n\n # 系统配置保持不变\n DOMAIN = \"organic electrocatalysis\"\n MAX_TOKENS = 30000\n\n MODEL_DIR = os.path.join(BASE_DIR, \"models\") # 模型存储根目录\n\nsettings = Settings()\n"}, "1accfb1a5c4e18eea7e223258c4864d7e5f879c2": {"t": 1785768816.0017579, "n": 942, "h": "61acfd6e3a878a4a", "c": "# 主配置文件\n\nimport os\n\nBASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\n\n\nclass Settings:\n # 数据路径\n RAW_PAPERS_DIR = os.path.join(BASE_DIR, \"data\", \"raw_papers\")\n PROCESSED_DIR = os.path.join(BASE_DIR, \"data\", \"processed\")\n VECTOR_DB_DIR = os.path.join(BASE_DIR, \"data\", \"vector_db\")\n\n # 文本处理参数\n CHUNK_SIZE = 500\n CHUNK_OVERLAP = 50\n\n # 向量存储配置\n EMBEDDING_MODEL = \"text2vec/paraphrase-multilingual-MiniLM-L12-v2\" # 使用本地模型\n RETRIEVAL_TOP_K = 10 # 增加检索文档数量\n\n # 更新为DeepSeek API配置\n DEEPSEEK_API_CONFIG = {\n \"api_key\": \"sk-0a6b9d29efa94458ad99009fcb5b46bb\",\n \"base_url\": \"https://api.deepseek.com\",\n \"model\": \"deepseek-chat\",\n \"temperature\": 0.3\n }\n\n # PDF解析设置\n PDF_PARSING_ENGINE = \"pymupdf\"\n\n # 系统配置保持不变\n DOMAIN = \"organic electrocatalysis\"\n MAX_TOKENS = 3000\n\n MODEL_DIR = os.path.join(BASE_DIR, \"models\") # 模型存储根目录\n\nsettings = Settings()\n"}}}} |