wehub-resource-sync
e768098d0e
tools_continuous_delivery / Private PyPI non-main branch release (push) Has been skipped
tools_continuous_delivery / Private PyPI main branch release (push) Failing after 2m42s
Publish Promptflow Doc / Build (push) Has been cancelled
Publish Promptflow Doc / Deploy (push) Has been cancelled
Flake8 Lint / flake8 (push) Has been cancelled
Spell check CI / Spell_Check (push) Has been cancelled
32 lines
1.1 KiB
Python
32 lines
1.1 KiB
Python
from jinja2 import Environment, FileSystemLoader
|
|
import os
|
|
from utils.logging import log
|
|
from utils.oai import OAIChat, render_with_token_limit
|
|
|
|
|
|
def rewrite_question(question: str, history: list):
|
|
template = Environment(
|
|
loader=FileSystemLoader(os.path.dirname(os.path.abspath(__file__)))
|
|
).get_template("rewrite_question_prompt.md")
|
|
token_limit = int(os.environ["PROMPT_TOKEN_LIMIT"])
|
|
max_completion_tokens = int(os.environ["MAX_COMPLETION_TOKENS"])
|
|
|
|
# Try to render the prompt with token limit and reduce the history count if it fails
|
|
while True:
|
|
try:
|
|
prompt = render_with_token_limit(
|
|
template, token_limit, question=question, history=history
|
|
)
|
|
break
|
|
except ValueError:
|
|
history = history[:-1]
|
|
log(f"Reducing chat history count to {len(history)} to fit token limit")
|
|
|
|
chat = OAIChat()
|
|
rewritten_question = chat.generate(
|
|
messages=[{"role": "user", "content": prompt}], max_tokens=max_completion_tokens
|
|
)
|
|
log(f"Rewritten question: {rewritten_question}")
|
|
|
|
return rewritten_question
|