add log

requirements.txt

@@ -77,3 +77,4 @@ streamlit-chatbox==1.1.11
 streamlit-modal>=0.1.0
 streamlit-aggrid>=0.3.4.post3
 watchdog>=3.0.0
+docx2txt

requirements_api.txt

@@ -67,3 +67,4 @@ arxiv>=2.0.0
 youtube-search>=2.1.2
 duckduckgo-search>=3.9.9
 metaphor-python>=0.1.23
+docx2txt

requirements_webui.txt

@@ -7,3 +7,4 @@ streamlit-modal>=0.1.0
 streamlit-aggrid>=0.3.4.post3
 httpx[brotli,http2,socks]>=0.25.2
 watchdog>=3.0.0
+docx2txt

server/knowledge_base/kb_doc_api.py

@@ -35,7 +35,9 @@ def search_docs(
     data = []
     if kb is not None:
         if query:
+            print(f"search_docs, query:{query}")  
             docs = kb.search_docs(query, top_k, score_threshold)
+            print(f"search_docs, docs:{docs}")
             data = [DocumentWithVSId(**x[0].dict(), score=x[1], id=x[0].metadata.get("id")) for x in docs]
         elif file_name or metadata:
             data = kb.list_docs(file_name=file_name, metadata=metadata)
@@ -155,6 +157,8 @@ def upload_docs(
     failed_files = {}
     file_names = list(docs.keys())
 
+    print(f"upload_docs, file_names:{file_names}")
+
     # 先将上传的文件保存到磁盘
     for result in _save_files_in_thread(files, knowledge_base_name=knowledge_base_name, override=override):
         filename = result["data"]["file_name"]
@@ -164,7 +168,9 @@ def upload_docs(
         if filename not in file_names:
             file_names.append(filename)
 
+   
     # 对保存的文件进行向量化
+    print(f"upload_docs, to_vector_store:{to_vector_store}")
     if to_vector_store:
         result = update_docs(
             knowledge_base_name=knowledge_base_name,

server/knowledge_base/kb_service/es_kb_service.py

@@ -141,6 +141,7 @@ class ESKBService(KBService):
 
     def do_search(self, query:str, top_k: int, score_threshold: float):
         # 文本相似性检索
+        print(f"do_search,top_k:{top_k},score_threshold:{score_threshold}")
         docs = self.db_init.similarity_search_with_score(query=query,
                                          k=top_k)
         return docs

server/knowledge_base/kb_service/faiss_kb_service.py

@@ -62,6 +62,7 @@ class FaissKBService(KBService):
                   top_k: int,
                   score_threshold: float = SCORE_THRESHOLD,
                   ) -> List[Document]:
+        print(f"do_search,top_k:{top_k},score_threshold:{score_threshold}")
         embed_func = EmbeddingsFunAdapter(self.embed_model)
         embeddings = embed_func.embed_query(query)
         with self.load_vector_store().acquire() as vs: