refac: web search

This commit is contained in:
Timothy J. Baek
2024-09-07 04:50:29 +01:00
parent ff46fe2b4a
commit 5c8fb4b3d5
7 changed files with 142 additions and 103 deletions

View File

@@ -4,6 +4,9 @@ from datetime import datetime
from typing import Optional
from open_webui.utils.misc import get_last_user_message, get_messages_content
def prompt_template(
template: str, user_name: Optional[str] = None, user_location: Optional[str] = None
) -> str:
@@ -37,9 +40,7 @@ def prompt_template(
return template
def title_generation_template(
template: str, prompt: str, user: Optional[dict] = None
) -> str:
def replace_prompt_variable(template: str, prompt: str) -> str:
def replacement_function(match):
full_match = match.group(0)
start_length = match.group(1)
@@ -66,7 +67,13 @@ def title_generation_template(
replacement_function,
template,
)
return template
def title_generation_template(
template: str, prompt: str, user: Optional[dict] = None
) -> str:
template = replace_prompt_variable(template, prompt)
template = prompt_template(
template,
**(
@@ -79,36 +86,50 @@ def title_generation_template(
return template
def search_query_generation_template(
template: str, prompt: str, user: Optional[dict] = None
) -> str:
def replace_messages_variable(template: str, messages: list[str]) -> str:
def replacement_function(match):
full_match = match.group(0)
start_length = match.group(1)
end_length = match.group(2)
middle_length = match.group(3)
if full_match == "{{prompt}}":
return prompt
# Process messages based on the number of messages required
if full_match == "{{MESSAGES}}":
return get_messages_content(messages)
elif start_length is not None:
return prompt[: int(start_length)]
return get_messages_content(messages[: int(start_length)])
elif end_length is not None:
return prompt[-int(end_length) :]
return get_messages_content(messages[-int(end_length) :])
elif middle_length is not None:
middle_length = int(middle_length)
if len(prompt) <= middle_length:
return prompt
start = prompt[: math.ceil(middle_length / 2)]
end = prompt[-math.floor(middle_length / 2) :]
return f"{start}...{end}"
mid = int(middle_length)
if len(messages) <= mid:
return get_messages_content(messages)
# Handle middle truncation: split to get start and end portions of the messages list
half = mid // 2
start_msgs = messages[:half]
end_msgs = messages[-half:] if mid % 2 == 0 else messages[-(half + 1) :]
formatted_start = get_messages_content(start_msgs)
formatted_end = get_messages_content(end_msgs)
return f"{formatted_start}\n{formatted_end}"
return ""
template = re.sub(
r"{{prompt}}|{{prompt:start:(\d+)}}|{{prompt:end:(\d+)}}|{{prompt:middletruncate:(\d+)}}",
r"{{MESSAGES}}|{{MESSAGES:START:(\d+)}}|{{MESSAGES:END:(\d+)}}|{{MESSAGES:MIDDLETRUNCATE:(\d+)}}",
replacement_function,
template,
)
return template
def search_query_generation_template(
template: str, messages: list[dict], user: Optional[dict] = None
) -> str:
prompt = get_last_user_message(messages)
template = replace_prompt_variable(template, prompt)
template = replace_messages_variable(template, messages)
template = prompt_template(
template,
**(