AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-08-12 03:19:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

optimize qa prompt (#1957)

Browse Source 
Co-authored-by: jyong <jyong@dify.ai>
This commit is contained in:
Jyong 2024-01-05 18:17:55 +08:00 committed by GitHub
parent b934232411
commit 28b26f67e2
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
api/core/prompt/prompts.py
View File

@ -75,7 +75,7 @@ GENERATOR_QA_PROMPT = (
'Step 3: Decompose or combine multiple pieces of information and concepts.\n' 'Step 3: Decompose or combine multiple pieces of information and concepts.\n'
'Step 4: Generate 20 questions and answers based on these key information and concepts.' 'Step 4: Generate 20 questions and answers based on these key information and concepts.'
'The questions should be clear and detailed, and the answers should be detailed and complete.\n' 'The questions should be clear and detailed, and the answers should be detailed and complete.\n'
"Answer according to the the language:{language} and in the following format: Q1:\nA1:\nQ2:\nA2:...\n" "Answer MUST according to the the language:{language} and in the following format: Q1:\nA1:\nQ2:\nA2:...\n"
) )
RULE_CONFIG_GENERATE_TEMPLATE = """Given MY INTENDED AUDIENCES and HOPING TO SOLVE using a language model, please select \ RULE_CONFIG_GENERATE_TEMPLATE = """Given MY INTENDED AUDIENCES and HOPING TO SOLVE using a language model, please select \