liuzhenghua

Results 12 comments of liuzhenghua

![image](https://github.com/langgenius/dify/assets/11787325/933ef6a4-2034-4c1a-9a36-e8a95afe922b)

Internal Server Error Traceback (most recent call last): File "/app/api/core/model_runtime/model_providers/__base/large_language_model.py", line 96, in invoke result = self._invoke(model, credentials, prompt_messages, model_parameters, tools, stop, stream, user) File "/app/api/core/model_runtime/model_providers/xinference/llm/llm.py", line 79, in _invoke...

while no 'user' role input, xinference returns 500 ![image](https://github.com/langgenius/dify/assets/11787325/4ba0e8e7-cdc8-4838-825e-0cb940f373d4)

![image](https://github.com/langgenius/dify/assets/11787325/c8a85450-fcbc-4e42-bd84-c3a638658c22)

If I add USER msg in wokflow node, it works. ![image](https://github.com/langgenius/dify/assets/11787325/c4124099-81ab-41fe-bf01-f756f972da9a) ![image](https://github.com/langgenius/dify/assets/11787325/f8c32fc7-1730-4ff2-aa48-5df6124d7103)

[2024-04-10 08:36:58,393: ERROR/MainProcess] consume document failed Traceback (most recent call last): File "/app/api/core/indexing_runner.py", line 64, in run text_docs = self._extract(index_processor, dataset_document, processing_rule.to_dict()) File "/app/api/core/indexing_runner.py", line 362, in _extract text_docs =...

由于创建空文件时,没有创建collection,下次往这个文档新建chunk的时候,无法往向量库写入数据,导致报错: "Error during query: [{'locations': [{'column': 6, 'line': 1}], 'message': 'Cannot query field \"Vector_index_3b5a7bd1_2cfb_4ae2_a89c_019472e90033_Node\" on type \"GetObjectsObj\". Did you mean \"Vector_index_6038789c_2c73_4190_809c_c170be45bb47_Node\"?', 'path': None}]"

> Hello @liuzhenghua, > > If I understood correctly then you wish to pass prompt directly to bito without using a prompt.txt file? Something like: echo "give me code for...