docs: 移除知识库混合搜索API文档说明

docreader/parser/chain_parser.py

@@ -6,6 +6,7 @@ from docreader.parser.base_parser import BaseParser
 from docreader.utils import endecode
 
 logger = logging.getLogger(__name__)
+logger.setLevel(logging.INFO)
 
 
 class FirstParser(BaseParser):
@@ -16,16 +17,15 @@ class FirstParser(BaseParser):
 
         self._parsers: List[BaseParser] = []
         for parser_cls in self._parser_cls:
-            try:
-                parser = parser_cls(*args, **kwargs)
-                self._parsers.append(parser)
-            except Exception as e:
-                logger.error(f"Failed to create parser {parser_cls.__name__}: {e}")
+            parser = parser_cls(*args, **kwargs)
+            self._parsers.append(parser)
 
     def parse_into_text(self, content: bytes) -> Document:
         for p in self._parsers:
+            logger.info(f"FirstParser: using parser {p.__class__.__name__}")
             document = p.parse_into_text(content)
             if document.is_valid():
+                logger.info(f"FirstParser: parser {p.__class__.__name__} succeeded")
                 return document
         return Document()
 
@@ -43,16 +43,14 @@ class PipelineParser(BaseParser):
 
         self._parsers: List[BaseParser] = []
         for parser_cls in self._parser_cls:
-            try:
-                parser = parser_cls(*args, **kwargs)
-                self._parsers.append(parser)
-            except Exception as e:
-                logger.error(f"Failed to create parser {parser_cls.__name__}: {e}")
+            parser = parser_cls(*args, **kwargs)
+            self._parsers.append(parser)
 
     def parse_into_text(self, content: bytes) -> Document:
         images: Dict[str, str] = {}
         document = Document()
         for p in self._parsers:
+            logger.info(f"PipelineParser: using parser {p.__class__.__name__}")
             document = p.parse_into_text(content)
             content = endecode.encode_bytes(document.content)
             images.update(document.images)

docreader/parser/mineru_parser.py

@@ -28,7 +28,6 @@ class StdMinerUParser(BaseParser):
         self.image_helper = MarkdownImageUtil()
         self.base64_pattern = re.compile(r"data:image/(\w+);base64,(.*)")
         self.enable = self.ping()
-        assert self.ping(), "MinerU API is not reachable"
 
     def ping(self, timeout: int = 5) -> bool:
         try:
@@ -41,6 +40,10 @@ class StdMinerUParser(BaseParser):
             return False
 
     def parse_into_text(self, content: bytes) -> Document:
+        if not self.enable:
+            logger.debug("MinerU API is not enabled")
+            return Document()
+
         logger.info(f"Parsing scanned PDF via MinerU API (size: {len(content)} bytes)")
         md_content: str = ""
         images_b64: Dict[str, str] = {}

docs/API.md

@@ -334,7 +334,6 @@ curl --location 'http://localhost:8080/api/v1/tenants' \
 | GET    | `/knowledge-bases/:id`               | 获取知识库详情           |
 | PUT    | `/knowledge-bases/:id`               | 更新知识库               |
 | DELETE | `/knowledge-bases/:id`               | 删除知识库               |
-| GET    | `/knowledge-bases/:id/hybrid-search` | 混合搜索知识库内容       |
 | POST   | `/knowledge-bases/copy`              | 拷贝知识库               |
 
 #### POST `/knowledge-bases` - 创建知识库
@@ -656,51 +655,6 @@ curl --location --request DELETE 'http://localhost:8080/api/v1/knowledge-bases/b
 }
 ```
 
-#### GET `/knowledge-bases/:id/hybrid-search` - 混合搜索知识库内容
-
-**请求**:
-
-```curl
-curl --location --request GET 'http://localhost:8080/api/v1/knowledge-bases/kb-00000001/hybrid-search' \
---header 'Content-Type: application/json' \
---header 'X-API-Key: sk-vQHV2NZI_LK5W7wHQvH3yGYExX8YnhaHwZipUYbiZKCYJbBQ' \
---data '{
-    "query_text": "彗星",
-    "vector_threshold": 0.1,
-    "keyword_threshold": 0.1,
-    "match_count": 1
-}'
-```
-
-**响应**:
-
-```json
-{
-    "data": [
-        {
-            "id": "7d955251-3f79-4fd5-a6aa-02f81e044091",
-            "content": "有几位后来xxxxx",
-            "knowledge_id": "a6790b93-4700-4676-bd48-0d4804e1456b",
-            "chunk_index": 3,
-            "knowledge_title": "彗星.txt",
-            "start_at": 2287,
-            "end_at": 2760,
-            "seq": 3,
-            "score": 0.7402352891601821,
-            "match_type": 2,
-            "sub_chunk_id": null,
-            "metadata": {},
-            "chunk_type": "text",
-            "parent_chunk_id": "",
-            "image_info": "",
-            "knowledge_filename": "彗星.txt",
-            "knowledge_source": ""
-        }
-    ],
-    "success": true
-}
-```
-
 <div align="right"><a href="#weknora-api-文档">返回顶部 ↑</a></div>
 
 ### 知识管理API