'commit'

dsRagAnything/Config/Config.py

@@ -0,0 +1,14 @@
+# 嵌入模型
+EMBED_MODEL_NAME = "BAAI/bge-m3"
+EMBED_API_KEY = "sk-pbqibyjwhrgmnlsmdygplahextfaclgnedetybccknxojlyl"
+EMBED_BASE_URL = "https://api.siliconflow.cn/v1"
+
+# 大模型
+LLM_API_KEY="sk-44ae895eeb614aa1a9c6460579e322f1"
+LLM_BASE_URL = "https://api.deepseek.com"
+LLM_MODEL_NAME = "deepseek-chat"
+
+# 视觉模型
+VISION_API_KEY = "sk-pbqibyjwhrgmnlsmdygplahextfaclgnedetybccknxojlyl"
+VISION_BASE_URL = "https://api.siliconflow.cn/v1/chat/completions"
+VISION_MODEL_NAME = "GLM-4.1V-9B-Thinking"

dsRagAnything/T1_Train.py

@@ -5,6 +5,7 @@ import loguru
 from raganything import RAGAnything, RAGAnythingConfig
 from lightrag.llm.openai import openai_complete_if_cache, openai_embed
 from lightrag.utils import EmbeddingFunc
+from Config.Config import *
 
 
 async def main():
@@ -12,10 +13,6 @@ async def main():
     loguru.logger.remove()  # 移除默认配置
     loguru.logger.add(sys.stderr, level="INFO")  # 输出INFO及以上级别到控制台
 
-    # Set up API configuration
-    api_key = "sk-44ae895eeb614aa1a9c6460579e322f1"
-    base_url = "https://api.deepseek.com"  # Optional
-
     # Create RAGAnything configuration
     config = RAGAnythingConfig(
         working_dir="./rag_storage",
@@ -28,12 +25,12 @@ async def main():
     # Define LLM model function
     def llm_model_func(prompt, system_prompt=None, history_messages=[], **kwargs):
         return openai_complete_if_cache(
-            "deepseek-chat",
+            LLM_MODEL_NAME,
             prompt,
             system_prompt=system_prompt,
             history_messages=history_messages,
-            api_key=api_key,
+            api_key=LLM_API_KEY,
-            base_url=base_url,
+            base_url=LLM_BASE_URL,
             **kwargs,
         )
 
@@ -43,7 +40,7 @@ async def main():
     ):
         if image_data:
             return openai_complete_if_cache(
-                "GLM-4.1V-9B-Thinking",  # 这里设置为了硅基流动中免费视觉模型的模型名称
+                VISION_MODEL_NAME,  # 这里设置为了硅基流动中免费视觉模型的模型名称
                 "",
                 system_prompt=None,
                 history_messages=[],
@@ -66,8 +63,8 @@ async def main():
                     if image_data
                     else {"role": "user", "content": prompt},
                 ],
-                api_key="sk-pbqibyjwhrgmnlsmdygplahextfaclgnedetybccknxojlyl",
+                api_key=VISION_API_KEY,
-                base_url="https://api.siliconflow.cn/v1/chat/completions",
+                base_url=VISION_BASE_URL,
                 **kwargs,
             )
         else:
@@ -79,9 +76,9 @@ async def main():
         max_token_size=8192,
         func=lambda texts: openai_embed(
             texts,
-            model="BAAI/bge-m3",
+            model=EMBED_MODEL_NAME,
-            api_key="sk-pbqibyjwhrgmnlsmdygplahextfaclgnedetybccknxojlyl",
+            api_key=EMBED_API_KEY,
-            base_url="https://api.siliconflow.cn/v1",
+            base_url=EMBED_BASE_URL,
         ),
     )
 
@@ -93,39 +90,16 @@ async def main():
         embedding_func=embedding_func,
     )
 
-    #file_path = "D:\python\小乔证件\黄琬乔2023蓝桥杯省赛准考证.pdf"
+    # file_path = "D:\python\小乔证件\黄琬乔2023蓝桥杯省赛准考证.pdf"
     file_path = "./Txt/驿来特平台安全.docx"
-    # Process a document
     await rag.process_document_complete(
         file_path=file_path,
         output_dir="./output",
         parse_method="auto"
     )
 
-
     print("Processing complete.")
 
-    # 调用LightRAG的代码，包括:1、创建索引，2、查询知识库，不应该放在这个模块中完成，这里只需要完成到文本解析完成即可。
-    # Query the processed content
-    # Pure text query - for basic knowledge base search
-    # text_result = await rag.aquery(
-    #     "这个文档是做什么用的?",
-    #     mode="hybrid"
-    # )
-    # print("Text query result:", text_result)
-
-    # # Multimodal query with specific multimodal content
-    # multimodal_result = await rag.aquery_with_multimodal(
-    #     "Explain this formula and its relevance to the document content",
-    #     multimodal_content=[{
-    #         "type": "equation",
-    #         "latex": "P(d|q) = \\frac{P(q|d) \\cdot P(d)}{P(q)}",
-    #         "equation_caption": "Document relevance probability"
-    #     }],
-    #     mode="hybrid"
-    # )
-    # print("Multimodal query result:", multimodal_result)
-
 
 if __name__ == "__main__":
     asyncio.run(main())