Merge branch 'master' into dev

api.py

@@ -181,7 +181,7 @@ async def delete_docs(
         if os.path.exists(doc_path):
             os.remove(doc_path)
         else:
-            return {"code": 1, "msg": f"document {doc_name} not found"}
+            BaseResponse(code=1, msg=f"document {doc_name} not found")
 
         remain_docs = await list_docs(knowledge_base_id)
         if remain_docs["code"] != 0 or len(remain_docs["data"]) == 0:
@@ -211,24 +211,30 @@ async def local_doc_chat(
 ):
     vs_path = os.path.join(VS_ROOT_PATH, knowledge_base_id)
     if not os.path.exists(vs_path):
-        raise ValueError(f"Knowledge base {knowledge_base_id} not found")
+        # return BaseResponse(code=1, msg=f"Knowledge base {knowledge_base_id} not found")
+        return ChatMessage(
+            question=question,
+            response=f"Knowledge base {knowledge_base_id} not found",
+            history=history,
+            source_documents=[],
+        )
+    else:
+        for resp, history in local_doc_qa.get_knowledge_based_answer(
+                query=question, vs_path=vs_path, chat_history=history, streaming=True
+        ):
+            pass
+        source_documents = [
+            f"""出处 [{inum + 1}] {os.path.split(doc.metadata['source'])[-1]}：\n\n{doc.page_content}\n\n"""
+            f"""相关度：{doc.metadata['score']}\n\n"""
+            for inum, doc in enumerate(resp["source_documents"])
+        ]
 
-    for resp, history in local_doc_qa.get_knowledge_based_answer(
+        return ChatMessage(
-            query=question, vs_path=vs_path, chat_history=history, streaming=True
+            question=question,
-    ):
+            response=resp["result"],
-        pass
+            history=history,
-    source_documents = [
+            source_documents=source_documents,
-        f"""出处 [{inum + 1}] {os.path.split(doc.metadata['source'])[-1]}：\n\n{doc.page_content}\n\n"""
+        )
-        f"""相关度：{doc.metadata['score']}\n\n"""
-        for inum, doc in enumerate(resp["source_documents"])
-    ]
-
-    return ChatMessage(
-        question=question,
-        response=resp["result"],
-        history=history,
-        source_documents=source_documents,
-    )
 
 
 async def chat(

chains/local_doc_qa.py

@@ -39,7 +39,11 @@ def load_file(filepath, sentence_size=SENTENCE_SIZE):
 
 
 def write_check_file(filepath, docs):
-    fout = open('load_file.txt', 'a')
+    folder_path = os.path.join(os.path.dirname(filepath), "tmp_files")
+    if not os.path.exists(folder_path):
+        os.makedirs(folder_path)
+    fp = os.path.join(folder_path, 'load_file.txt')
+    fout = open(fp, 'a')
     fout.write("filepath=%s,len=%s" % (filepath, len(docs)))
     fout.write('\n')
     for i in docs:

cli_demo.py

@@ -31,13 +31,13 @@ if __name__ == "__main__":
                                                                      chat_history=history,
                                                                      streaming=STREAMING):
             if STREAMING:
-                logger.info(resp["result"][last_print_len:])
+                print(resp["result"][last_print_len:], end="", flush=True)
                 last_print_len = len(resp["result"])
             else:
-                logger.info(resp["result"])
+                print(resp["result"])
         if REPLY_WITH_SOURCE:
             source_text = [f"""出处 [{inum + 1}] {os.path.split(doc.metadata['source'])[-1]}：\n\n{doc.page_content}\n\n"""
                            # f"""相关度：{doc.metadata['score']}\n\n"""
                            for inum, doc in
                            enumerate(resp["source_documents"])]
-            logger.info("\n\n" + "\n\n".join(source_text))
+            print("\n\n" + "\n\n".join(source_text))

loader/image_loader.py

@@ -30,7 +30,7 @@ class UnstructuredPaddleImageLoader(UnstructuredFileLoader):
       
       
 if __name__ == "__main__":
-    filepath = "../content/samples/test.jpg"
+    filepath = os.path.join(os.path.dirname(os.path.dirname(__file__)), "content", "samples", "test.jpg")
     loader = UnstructuredPaddleImageLoader(filepath, mode="elements")
     docs = loader.load()
     for doc in docs:

loader/pdf_loader.py

@@ -46,7 +46,7 @@ class UnstructuredPaddlePDFLoader(UnstructuredFileLoader):
 
 
 if __name__ == "__main__":
-    filepath = "../content/samples/test.pdf"
+    filepath = os.path.join(os.path.dirname(os.path.dirname(__file__)), "content", "samples", "test.pdf")
     loader = UnstructuredPaddlePDFLoader(filepath, mode="elements")
     docs = loader.load()
     for doc in docs: