cyberes
/
server-personification
Archived
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

simplfy web_reader tool description

This commit is contained in:
Cyberes 2024-03-07 18:54:13 -07:00
parent 57d47eb7fe
commit 3c5d82d4c6
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
pers/langchain/tools/web_reader.py
View File

@ -121,9 +121,8 @@ class ReaderToolInput(BaseModel):
@tool(args_schema=ReaderToolInput) @tool(args_schema=ReaderToolInput)
def read_webpage(url: str, reasoning: str, include_body: bool = True, cursor: int = 0): def read_webpage(url: str, reasoning: str, include_body: bool = True, cursor: int = 0):
"""Fetch a webpage's text content. """Fetch a webpage's text content. Best for when you need to simply read the page.
This tool trunucates the text content if it is longer than the context limit. You will see a line like `PAGE WAS TRUNCATED. TO CONTINUE READING, USE CURSOR=n.` when this happens, where `CURSOR=n` is the starting position for the next page. To continue reading, call this tool with the `cursor` argument with where you want to begin. This tool trunucates the text content if it is longer than the context limit. You will see a line like `PAGE WAS TRUNCATED. TO CONTINUE READING, USE CURSOR=n.` when this happens, where `CURSOR=n` is the starting position for the next page. To continue reading, call this tool with the `cursor` argument with where you want to begin."""
This function may not correctly parse complicated webpages, so use render_webpage if targeting specific HTML elements or expecting a complicated page. Best for when you need to simply read the page."""
if PRINT_USAGE: if PRINT_USAGE:
_print_func_call('read_webpage', {'url': url, 'reasoning': reasoning}) _print_func_call('read_webpage', {'url': url, 'reasoning': reasoning})