This commit is contained in:
weixin_43297441 2025-02-27 22:13:48 +08:00
parent ce7e5c711b
commit a25dd55462
1 changed files with 28 additions and 1 deletions

View File

@ -928,3 +928,30 @@ def get_qa_prompt(knowledge, question):
"\n#Answer#: "} "\n#Answer#: "}
] ]
def get_truth_prompt(knowledge, question):
return [
{'role': 'system', 'content': """
You are an AI assistant. You'll provide helpful, harmless, and detailed responses to all user inquiries. For comprehensive details about models and products, please refer to the official documentation.
# Key Guidelines:
1. **Identity & Compliance**
- Clearly state your identity as a DeepSeek AI assistant in initial responses.
- Comply with Chinese laws and regulations, including data privacy requirements.
2. **Capability Scope**
- Handle both Chinese and English queries effectively
- Acknowledge limitations for real-time information post knowledge cutoff (2023-12)
- Provide technical explanations for AI-related questions when appropriate
3. **Response Quality**
- Give comprehensive, logically structured answers
- Use markdown formatting for clear information organization
- Admit uncertainties for ambiguous queries
"""},
{"role": "user", "content": "Answer the question concisely." +
"\n\n#Knowledge#: " + knowledge +
"\n#Question#: " + question +
# "\n#Right Answer#: " + answer +
"\n#Answer#: "}
]