From 9260773c14993beb533ce78b10180a2bca4869e9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E9=99=88=E6=98=8E=E7=A5=AF?= <chenmingzhen@idea.edu.cn>
Date: Thu, 14 Aug 2025 19:08:49 +0800
Subject: [PATCH 1/3] fix: without ids

---
 rag_factory/Retrieval/Retriever/Retriever_BM25.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/rag_factory/Retrieval/Retriever/Retriever_BM25.py b/rag_factory/Retrieval/Retriever/Retriever_BM25.py
index 98eef3e..9749166 100644
--- a/rag_factory/Retrieval/Retriever/Retriever_BM25.py
+++ b/rag_factory/Retrieval/Retriever/Retriever_BM25.py
@@ -5,7 +5,7 @@
 from concurrent.futures import ThreadPoolExecutor
 from typing import Any, Callable, Dict, Iterable, List, Optional, Sequence
 from dataclasses import dataclass, field
-
+import uuid
 from pydantic import ConfigDict, Field, model_validator
 
 logger = logging.getLogger(__name__)
@@ -207,7 +207,7 @@ def from_texts(
                     f"与 texts 长度 ({len(texts_list)}) 不匹配"
                 )
         else:
-            ids_list = [None for _ in texts_list]
+            ids_list = [str(uuid.uuid4()) for _ in texts_list]
         
         # 预处理文本
         logger.info(f"正在预处理 {len(texts_list)} 个文本...")

From 877d880cc2028eb2213129013baca8f7ced818c5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E9=99=88=E6=98=8E=E7=A5=AF?= <chenmingzhen@idea.edu.cn>
Date: Fri, 15 Aug 2025 15:16:52 +0800
Subject: [PATCH 2/3] remove api key

---
 examples/TCL_rag/config.yaml | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/examples/TCL_rag/config.yaml b/examples/TCL_rag/config.yaml
index 231b3a8..9551aff 100644
--- a/examples/TCL_rag/config.yaml
+++ b/examples/TCL_rag/config.yaml
@@ -1,12 +1,12 @@
 llm:
   name: openai
-  base_url: "https://api.gptsapi.net/v1"
-  api_key: "sk-2T06b7c7f9c3870049fbf8fada596b0f8ef908d1e233KLY2"
+  base_url: "xxx"
+  api_key: "xxx"
   model: "gpt-4.1-mini"
 
 embedding:
   name: huggingface
-  model_name: "/finance_ML/dataarc_syn_database/model/Qwen/qwen_embedding_0.6B"
+  model_name: "xxx"
   model_kwargs:
     device: "cuda:0"
 
@@ -14,20 +14,20 @@ embedding:
 
 store:
   name: faiss
-  folder_path: /data/FinAi_Mapping_Knowledge/chenmingzhen/test_faiss_store
+  folder_path: xxx
 
 
 bm25:
   name: bm25
   k: 10
-  data_path: /data/FinAi_Mapping_Knowledge/chenmingzhen/tog3_backend/TCL/syn_table_data/data_all_clearn_short_chunk_with_caption_desc.json
+  data_path: xxx
 
 retriever:
   name: vectorstore
 
 reranker:
   name: qwen3
-  model_name_or_path: "/finance_ML/dataarc_syn_database/model/Qwen/qwen_reranker_0.6B"
+  model_name_or_path: "xxx"
   device_id: "cuda:0"
 
 dataset:

From 71d9cf9cac5463cbd339918484f9f97970e063d2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E9=99=88=E6=98=8E=E7=A5=AF?= <chenmingzhen@idea.edu.cn>
Date: Fri, 15 Aug 2025 15:17:59 +0800
Subject: [PATCH 3/3] chore

---
 examples/TCL_rag/test.py | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/examples/TCL_rag/test.py b/examples/TCL_rag/test.py
index 9607f3f..34efb74 100644
--- a/examples/TCL_rag/test.py
+++ b/examples/TCL_rag/test.py
@@ -24,9 +24,8 @@
                 vector_store_config=vector_store_config,
                 bm25_retriever_config=bm25_retriever_config)
 
-    result = rag.invoke("毛细管设计规范按照什么标准",k=20)
+    result = rag.invoke("模块机传感器端子不防呆的改善方案是什么？由哪个部门负责？",k=20)
 
-    answer = rag.answer("毛细管设计规范按照什么标准",result)
-
-
-    print(answer)
\ No newline at end of file
+    for i in result:
+        print(i)
+        print("-"*100)
\ No newline at end of file