Open Manamama opened 3 months ago
Is there an existing issue for the same bug?
- [x] I have checked the existing issues.
Branch name
main
Commit ID
?
Other environment information
All online, on your https://demo.ragflow.io/knowledge/dataset?id=1cec9bb2379e11ef94380242ac120006 server, account set up 3 days ago, reproducible over many days.
Embedding model: BGE Large EN v. 1.5 Chunk method: General Chunk token number: 128
Actual behavior
Error:
Process Begin At: Tue, 02 Jul 2024 15:26:17 GMT Process Duration: 16.75 s Progress Msg: Task has been received. Start to parse. [ERROR]Internal server error: int() base must be >= 2 and <= 36, or 0
Expected behavior
No response
Steps to reproduce
All the source files are TXT: medium and very small.
Two short source samples below: 1.
The programmer's wife couldn't take it anymore. Every discussion with her husband turned into an argument over semantics, picking over every piece of trivial detail. One day she sent him to the grocery store to pick up some eggs. On his way out the door, she said, "While you are there, pick up milk."
Program: class Programmer: def __init__(self): self.grocery_list = ['eggs'] def go_to_store(self): while True: # Infinite loop to represent the joke's endless cycle print("Entering the store...") for item in self.grocery_list: print(f"Picking up {item}...") if 'milk' not in self.grocery_list: print("Oh, I need to pick up milk while I'm here.") self.grocery_list.append('milk') else: print("I've already picked up milk, but the instruction was 'while you are there, pick up milk'...") print("So, do I need to pick up another milk?") print("This is confusing... Let's start over.") self.grocery_list.remove('milk') # Reset the condition to keep the loop going husband = Programmer() husband.go_to_store()
Additional information
It errors at about 20 percent of parsing, each time.
fixed
Works now, with same files! 🐙👏
Is there an existing issue for the same bug?
Branch name
main
Commit ID
?
Other environment information
All online, on your https://demo.ragflow.io/knowledge/dataset?id=1cec9bb2379e11ef94380242ac120006 server, account set up 3 days ago, reproducible over many days.
Embedding model: BGE Large EN v. 1.5 Chunk method: General Chunk token number: 128
Actual behavior
Error:
Process Begin At: Tue, 02 Jul 2024 15:26:17 GMT Process Duration: 16.75 s Progress Msg: Task has been received. Start to parse. [ERROR]Internal server error: int() base must be >= 2 and <= 36, or 0
Expected behavior
No response
Steps to reproduce
All the source files are TXT: medium and very small.
Two short source samples below:
The programmer's wife couldn't take it anymore. Every discussion with her husband turned into an argument over semantics, picking over every piece of trivial detail. One day she sent him to the grocery store to pick up some eggs. On his way out the door, she said, "While you are there, pick up milk."
husband = Programmer() husband.go_to_store()