stable 0.2.0 (#188)

1.  修复minio 不配置导致的bug
2.  修改默认配置注释

src/backend/bisheng/api/v1/knowledge.py

@@ -57,7 +57,7 @@ async def upload_file(*, file: UploadFile = File(...)):
         # 缓存本地
         file_path = save_uploaded_file(file.file, 'bisheng', file_name)
         if not isinstance(file_path, str):
-            file_path = str(file_path) + '_' + file_name
+            file_path = str(file_path)
         return UploadFileResponse(file_path=file_path)
     except Exception as exc:
         logger.error(f'Error saving file: {exc}')
@@ -116,7 +116,7 @@ async def process_knowledge(*,
     result = []
     for path in file_path:
         filepath, file_name = file_download(path)
-        md5_ = filepath.rsplit('/', 1)[1].split('.')[0]
+        md5_ = filepath.rsplit('/', 1)[1].split('.')[0].split('_')[0]
         # 是否包含重复文件
         repeat = session.exec(select(KnowledgeFile)
                               .where(KnowledgeFile.md5 == md5_,

src/backend/bisheng/cache/utils.py

@@ -183,8 +183,7 @@ def save_uploaded_file(file, folder_name, file_name):
         minio_client.upload_tmp(file_name, file_byte)
         file_path = minio_client.get_share_link(file_name, tmp_bucket)
     else:
-        file_type = md5_name.split('.')[-1]
-        file_path = folder_path / f'{md5_name}.{file_type}'
+        file_path = folder_path / f'{md5_name}_{file_name}'
         with open(file_path, 'wb') as new_file:
             while chunk := file.read(8192):
                 new_file.write(chunk)
@@ -248,7 +247,7 @@ def file_download(file_path: str):
         return file_path, filename
     elif not os.path.isfile(file_path):
         raise ValueError('File path %s is not a valid file or url' % file_path)
-    return file_path, ''
+    return file_path, file_path.split('_', 1)[1] if '_' in file_path else ''
 
 
 def _is_valid_url(url: str):

src/backend/bisheng/chat/manager.py

@@ -290,7 +290,7 @@ def refresh_graph_data(self, graph_data: dict, node_data: List[dict]):
                 if url_path.netloc:
                     file_name = unquote(url_path.path.split('/')[-1])
                 else:
-                    file_path, file_name = file_path.split('_', 1)
+                    file_name = file_path.split('_', 1)[1] if '_' in file_path else ''
                 nd['value'] = file_name
                 tweak[nd.get('id')] = {'file_path': file_path, 'value': file_name}
             elif 'VariableNode' in nd.get('id'):

src/backend/bisheng/initdb_config.yaml

@@ -11,18 +11,18 @@ knowledges: # 知识库相关配置
   vectorstores:
     # Milvus 最低要求cpu 4C 8G 推荐4C 16G
     Milvus: # 如果需要切换其他vectordb，确保其他服务已经启动，然后配置对应参数
-      connection_args: {'host': 'milvus', 'port': '19530', 'user': '', 'password': '', 'secure': False}
+      connection_args: {'host': '110.16.193.170', 'port': '50032', 'user': '', 'password': '', 'secure': False}
     # 可选配置，有些类型的场景使用ES可以提高召回效果
-    ElasticKeywordsSearch:
-      elasticsearch_url: 'http://elasticsearch:9200'
-      ssl_verify: "{'basic_auth': ('elastic', 'password')}"
-  minio: # 如果要支持溯源功能，由于溯源会展示源文件，必须配置 oss 存储
-    SCHEMA: true
-    CERT_CHECK: false
-    MINIO_ENDPOINT: "milvus:9001"
-    MINIO_SHAREPOIN: "milvus:9001"
-    MINIO_ACCESS_KEY: "minioadmin"
-    MINIO_SECRET_KEY: "minioadmin"
+    # ElasticKeywordsSearch:
+    #   elasticsearch_url: 'http://elasticsearch:9200'
+    #   ssl_verify: "{'basic_auth': ('elastic', 'password')}"
+  # minio: # 如果要支持溯源功能，由于溯源会展示源文件，必须配置 oss 存储
+  #   SCHEMA: false         # 是否支持 https
+  #   CERT_CHECK: false         # 是否校验 http证书
+  #   MINIO_ENDPOINT: "milvus:9001"       # 这个地址用来写请求
+  #   MINIO_SHAREPOIN: "milvus:9001"      # 为保证外网和内网隔离。 浏览器获取连接是这个域名
+  #   MINIO_ACCESS_KEY: "minioadmin"
+  #   MINIO_SECRET_KEY: "minioadmin"
   #
 
 # 全局配置大模型    

src/backend/bisheng/interface/chains/custom.py

@@ -109,8 +109,12 @@ def initialize(cls,
                    document_prompt: BasePromptTemplate = None,
                    token_max: str = -1):
         if chain_type == 'stuff':
-            return load_qa_chain(llm=llm, chain_type=chain_type, prompt=prompt,
-                                 token_max=token_max, document_prompt=document_prompt)
+            if document_prompt:
+                return load_qa_chain(llm=llm, chain_type=chain_type, prompt=prompt,
+                                     token_max=token_max, document_prompt=document_prompt)
+            else:
+                return load_qa_chain(llm=llm, chain_type=chain_type, prompt=prompt,
+                                     token_max=token_max)
         else:
             return load_qa_chain(llm=llm, chain_type=chain_type)
 

src/backend/bisheng/interface/initialize/loading.py

@@ -76,7 +76,7 @@ def instantiate_based_on_type(class_object, base_type, node_type, params, param_
     if base_type == 'agents':
         return instantiate_agent(node_type, class_object, params)
     elif base_type == 'prompts':
-        return instantiate_prompt(node_type, class_object, params)
+        return instantiate_prompt(node_type, class_object, params, param_id_dict)
     elif base_type == 'tools':
         tool = instantiate_tool(node_type, class_object, params)
         if hasattr(tool, 'name') and isinstance(tool, BaseTool):
@@ -320,7 +320,7 @@ def instantiate_agent(node_type, class_object: Type[agent_module.Agent], params:
     return load_agent_executor(class_object, params)
 
 
-def instantiate_prompt(node_type, class_object, params: Dict):
+def instantiate_prompt(node_type, class_object, params: Dict, param_id_dict: Dict):
 
     if node_type == 'ZeroShotPrompt':
         if 'tools' not in params:
@@ -339,6 +339,10 @@ def instantiate_prompt(node_type, class_object, params: Dict):
     else:
         prompt = class_object(**params)
 
+    no_human_input = set(param_id_dict.keys())
+    human_input = set(prompt.input_variables).difference(no_human_input)
+    order_input = list(human_input) + list(set(prompt.input_variables) & no_human_input)
+    prompt.input_variables = order_input
     format_kwargs: Dict[str, Any] = {}
     for input_variable in prompt.input_variables:
         if input_variable in params:
@@ -348,6 +352,14 @@ def instantiate_prompt(node_type, class_object, params: Dict):
             elif isinstance(variable, BaseOutputParser) and hasattr(variable,
                                                                     'get_format_instructions'):
                 format_kwargs[input_variable] = variable.get_format_instructions()
+            elif isinstance(variable, dict):
+                # variable node
+                if len(variable) == 0:
+                    format_kwargs[input_variable] = ''
+                    continue
+                elif len(variable) != 1:
+                    raise ValueError(f'VariableNode contains multi-key {variable.keys()}')
+                format_kwargs[input_variable] = list(variable.values())[0]
             elif isinstance(variable, List) and all(
                     isinstance(item, Document) for item in variable):
                 # Format document to contain page_content and metadata

src/bisheng-langchain/bisheng_langchain/chat_models/proxy_llm.py

@@ -195,11 +195,13 @@ def _completion_with_retry(**kwargs: Any) -> Any:
                 'functions': kwargs.get('functions', [])
             }
             response = self.client.post(self.elemai_base_url, json=params)
-            if response.status_code != 200:
-                raise
             return response.json()
 
-        return _completion_with_retry(**kwargs)
+        rsp_dict = _completion_with_retry(**kwargs)
+        if 200 != rsp_dict.get('status_code'):
+            logger.error(f'proxy_llm_error resp={rsp_dict}')
+            raise Exception(rsp_dict)
+        return rsp_dict
 
     def _combine_llm_outputs(self, llm_outputs: List[Optional[dict]]) -> dict:
         overall_token_usage: dict = {}