diff --git a/dsRag/.idea/RAG.iml b/dsRag/.idea/RAG.iml index a1e4a226..7a412d0e 100644 --- a/dsRag/.idea/RAG.iml +++ b/dsRag/.idea/RAG.iml @@ -2,7 +2,7 @@ - + \ No newline at end of file diff --git a/dsRag/.idea/misc.xml b/dsRag/.idea/misc.xml index 86b5f48b..913c162f 100644 --- a/dsRag/.idea/misc.xml +++ b/dsRag/.idea/misc.xml @@ -3,5 +3,5 @@ - + \ No newline at end of file diff --git a/dsRag/Config/__pycache__/Config.cpython-310.pyc b/dsRag/Config/__pycache__/Config.cpython-310.pyc index b4871591..1a6d2428 100644 Binary files a/dsRag/Config/__pycache__/Config.cpython-310.pyc and b/dsRag/Config/__pycache__/Config.cpython-310.pyc differ diff --git a/dsRag/Config/__pycache__/__init__.cpython-310.pyc b/dsRag/Config/__pycache__/__init__.cpython-310.pyc index 2278514c..b3f99ca7 100644 Binary files a/dsRag/Config/__pycache__/__init__.cpython-310.pyc and b/dsRag/Config/__pycache__/__init__.cpython-310.pyc differ diff --git a/dsRag/T1_ManageMapping.py b/dsRag/T1_EsMapping.py similarity index 96% rename from dsRag/T1_ManageMapping.py rename to dsRag/T1_EsMapping.py index 914ef991..a8fb23b0 100644 --- a/dsRag/T1_ManageMapping.py +++ b/dsRag/T1_EsMapping.py @@ -96,6 +96,5 @@ if __name__ == "__main__": # 创建新的向量索引 manage_index("create", "vector", dims=200) - # 创建新的原始文本索引 manage_index("create", "text") diff --git a/dsRag/T2_ImportTxt.py b/dsRag/T2_ImportTxt.py index ecf1ba92..d3688279 100644 --- a/dsRag/T2_ImportTxt.py +++ b/dsRag/T2_ImportTxt.py @@ -23,8 +23,6 @@ def split_paragraphs(text): paragraphs = [p.strip() for p in text.split('\n\n') if p.strip()] return paragraphs -# 修改process_file函数 -# Move save_to_es function definition before process_file def save_to_es(text): """保存向量化文本和原始文本到ES""" vector = text_to_embedding(text) @@ -46,7 +44,6 @@ def save_to_es(text): except Exception as e: logger.error(f"保存文本到ES失败: {e}") -# Then define process_file function def process_file(file_path): """处理文本文件""" with open(file_path, 'r', encoding='utf-8') as f: diff --git a/dsRag/Util/__pycache__/EmbeddingUtil.cpython-310.pyc b/dsRag/Util/__pycache__/EmbeddingUtil.cpython-310.pyc index ce16b97a..cd5032e9 100644 Binary files a/dsRag/Util/__pycache__/EmbeddingUtil.cpython-310.pyc and b/dsRag/Util/__pycache__/EmbeddingUtil.cpython-310.pyc differ diff --git a/dsRag/Util/__pycache__/__init__.cpython-310.pyc b/dsRag/Util/__pycache__/__init__.cpython-310.pyc index 2089b6b5..79767003 100644 Binary files a/dsRag/Util/__pycache__/__init__.cpython-310.pyc and b/dsRag/Util/__pycache__/__init__.cpython-310.pyc differ