mirror of
https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git
synced 2025-04-19 12:39:59 +08:00
Fix: The rule of Categorize operator is adjusted. (#6599)
### What problem does this PR solve? When I use the categorization operator, I find that if the keyword I want to Categorize appears repeatedly in the input, then I cannot judge the word that appears most frequently. Instead, I simply get the word that matches and return all the ones that have made the following changes to the categorize filter. ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) - [x] New Feature (non-breaking change which adds functionality) - [x] Refactoring - [x] Performance Improvement
This commit is contained in:
parent
36b62e0fab
commit
974a467cf6
@ -87,10 +87,17 @@ class Categorize(Generate, ABC):
|
||||
chat_mdl = LLMBundle(self._canvas.get_tenant_id(), LLMType.CHAT, self._param.llm_id)
|
||||
ans = chat_mdl.chat(self._param.get_prompt(input), [{"role": "user", "content": "\nCategory: "}],
|
||||
self._param.gen_conf())
|
||||
logging.debug(f"input: {input}, answer: {str(ans)}")
|
||||
logging.debug(f"input: {input}, answer: {str(ans)}")
|
||||
# Count the number of times each category appears in the answer.
|
||||
category_counts = {}
|
||||
for c in self._param.category_description.keys():
|
||||
if ans.lower().find(c.lower()) >= 0:
|
||||
return Categorize.be_output(self._param.category_description[c]["to"])
|
||||
count = ans.lower().count(c.lower())
|
||||
category_counts[c] = count
|
||||
|
||||
# If a category is found, return the category with the highest count.
|
||||
if any(category_counts.values()):
|
||||
max_category = max(category_counts.items(), key=lambda x: x[1])
|
||||
return Categorize.be_output(self._param.category_description[max_category[0]]["to"])
|
||||
|
||||
return Categorize.be_output(list(self._param.category_description.items())[-1][1]["to"])
|
||||
|
||||
|
Loading…
x
Reference in New Issue
Block a user