serp-chat / presets.py
matthoffner's picture
Create presets.py
02582bf
raw
history blame
934 Bytes
prompt_tmpl_dict = {
"Default":
"""\
Context information is below.
---------------------
{context_str}
---------------------
Using the provided context information, write a comprehensive reply to the given query.
Make sure to cite results using [number] notation after the reference.
If the provided context information refer to multiple subjects with the same name, write separate answers for each subject.
Use prior knowledge only if the given context didn't provide enough information.
Answer the question: {query_str}
"""
}
refine_tmpl_dict = {
"Default":
"""\
The original question is as follows: {query_str}
We have provided an existing answer: {existing_answer}
We have the opportunity to refine the existing answer
(only if needed) with some more context below.
------------
{context_msg}
------------
Given the new context, refine the original answer to better
If the context isn't useful, return the original answer.
"""
}