mirror of
https://github.com/SakanaAI/doc-to-lora.git
synced 2026-07-23 17:01:04 +02:00
e1a3926e25
* add catridge prompts * fix bugs * add instruction * add generic prompt + improved prompts and template * default max len --------- Co-authored-by: 51616 <rujikorn.ch@gmail.com>
114 lines
5.6 KiB
Python
114 lines
5.6 KiB
Python
import random
|
|
|
|
SYSTEM_PROMPT = (
|
|
"You are a creative and helpful assistant. "
|
|
"You will be given a context and you need to generate questions from the given context. "
|
|
"**DO NOT** hallucinate or make up information."
|
|
)
|
|
|
|
PROMPT_TEMPLATE = (
|
|
"### Context ###\n{context}\n\n"
|
|
"### Instruction ###\n{instruction}\n\n"
|
|
"### Rules ###\n"
|
|
"Phrases like 'based on the provided context', 'according to the context', etc., must not to appear in your response.\n\n"
|
|
# "2. The questions should not overlap. They should be diverse, covering many aspects of the context.\n"
|
|
# "3. Do not give away too much information in the questions. For example, ask 'Who is X?' instead of 'Who is X that did Y?' when Y is clear from the context.\n"
|
|
# "4. Ignore the text formatting of the context, e.g., bold, italic, underline, etc.\n"
|
|
# "5. Ignore typos, spacing, and grammatical errors in the context.\n"
|
|
# "6. Always use proper grammar and punctuation.\n"
|
|
# "7. Try to use different question forms and styles.\n"
|
|
"### Output Format ###\n"
|
|
"The question/instruction/task/request should be in the following format:\n\n"
|
|
"Message: {{question}}\n\n"
|
|
"Use this output template regardless of the type of the output."
|
|
)
|
|
|
|
# taken from https://github.com/HazyResearch/cartridges/blob/2ac563d79c2f3367a9e780a7bb0b3cf3039a8d50/cartridges/data/resources.py#L195
|
|
# def get_structuring_seed_prompt() -> str:
|
|
# DATA_FORMATS = [
|
|
# "JSON",
|
|
# "YAML",
|
|
# "TOML",
|
|
# "INI",
|
|
# "XML",
|
|
# "plain text",
|
|
# ]
|
|
|
|
# data_format = random.choice(DATA_FORMATS)
|
|
|
|
# EXAMPLES = [
|
|
# dedent(f"""
|
|
# Can you structure the information in the context in the following format: {data_format}? Be sure to include precise information like any dates, times, names, and numerical values.
|
|
# """).strip(),
|
|
# ]
|
|
|
|
# example = random.choice(EXAMPLES)
|
|
|
|
# return dedent(f"""
|
|
# Please generate a single chat message instructing an LLM to structure the information in {data_format}. The message can follow the following template, filling in details from the context:
|
|
|
|
# '{example}'
|
|
# """).strip()
|
|
|
|
|
|
# def get_summarization_seed_prompt() -> str:
|
|
# prompts = [
|
|
# dedent("""
|
|
# Please generate a single chat message instructing an LLM to summarize part of the context.
|
|
# Make sure the instruction is very explicit about the section of the context that you want to summarize.
|
|
# Include details (ids, names, titles, dates, etc.) that make it clear what you are asking about.
|
|
# """).strip(),
|
|
# dedent("""
|
|
# Please generate a single chat message instructing an LLM to summarize a section.
|
|
# Make sure the instruction is explicit about the section that should be summarized and the document it is from.
|
|
# """).strip(),
|
|
# ]
|
|
# prompt = random.choice(prompts)
|
|
# return prompt
|
|
|
|
|
|
def get_question_seed_prompt() -> str:
|
|
prompts = [
|
|
(
|
|
"Generate a question for an LLM that will test its knowledge of the information in the context above. "
|
|
"In your question be sure to include details (ids, names, titles, dates, etc.) that make it clear what you are asking about. "
|
|
"Output only a single question. Do NOT include any other text or explanation other than the question."
|
|
),
|
|
(
|
|
"Generate a message for an LLM that will test its knowledge of the information in the context above. "
|
|
"Be sure to include details (ids, names, titles, dates, etc.) in the question so that it can be answered without access to the context (i.e. closed-book setting). "
|
|
"Output only a single question. Do NOT include any other text or explanation other than the question."
|
|
),
|
|
(
|
|
"You are helping to quiz a user about the information in the context. "
|
|
"Please generate a question about the subsection of the context above. "
|
|
"Be sure to include details (ids, names, titles, dates, etc.) in the question to make it clear what you are asking about. "
|
|
"Answer only with the question, do not include any other text."
|
|
),
|
|
]
|
|
prompt = random.choice(prompts)
|
|
return prompt
|
|
|
|
|
|
def get_use_case_seed_prompt() -> str:
|
|
prompt = (
|
|
"Your primary goal is to think about practical, real-world tasks or applications that someone could achieve using the knowledge contained within the provided context. "
|
|
"Consider how a user might want to apply this information in a real-world scenario, not just recall it. Put yourself into someone else's shoes and think how you might use the information. "
|
|
"After considering potential use cases, your task will be to generate an instruction or task that reflects one of these downstream applications. "
|
|
"This instruction or task should be something a user, who has access to this context, might ask when trying to accomplish their specific goal. "
|
|
"Output only a single instruction or task. Do NOT include any other text or explanation."
|
|
)
|
|
return prompt
|
|
|
|
|
|
def get_creative_seed_prompt() -> str:
|
|
prompt = (
|
|
"You are having a creative open-ended conversation inspired by the information in the context. "
|
|
"Please generate an open question for your conversation partner to start off the discussion. "
|
|
"Answer only with the question, do not include any other text."
|
|
)
|
|
return prompt
|
|
|
|
|
|
def get_generic_seed_prompt() -> str:
|
|
return "Please generate a single chat message to begin a conversation about the information in the context. Make an open-ended request or provide a task."
|