CodeCow/Scrapegraph-ai
1
0
Fork 0
mirror of https://github.com/VinciGit00/Scrapegraph-ai.git synced 2026-07-01 21:00:48 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

feat: refactoring of get_probable_tags node

Browse Source
This commit is contained in:
Marco Vinciguerra 2024-10-23 12:15:16 +02:00
parent 94b9836ef6
commit f658092dff
3 changed files with 15 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
scrapegraphai/nodes/get_probable_tags_node.py
View File

@ -4,6 +4,7 @@ GetProbableTagsNode Module
from typing import List, Optional from typing import List, Optional
from langchain.output_parsers import CommaSeparatedListOutputParser from langchain.output_parsers import CommaSeparatedListOutputParser
from langchain.prompts import PromptTemplate from langchain.prompts import PromptTemplate
from ..prompts import TEMPLATE_GET_PROBABLE_TAGS
from ..utils.logging import get_logger from ..utils.logging import get_logger
from .base_node import BaseNode from .base_node import BaseNode
@ -68,14 +69,7 @@ class GetProbableTagsNode(BaseNode):
output_parser = CommaSeparatedListOutputParser() output_parser = CommaSeparatedListOutputParser()
format_instructions = output_parser.get_format_instructions() format_instructions = output_parser.get_format_instructions()
template = """ template = TEMPLATE_GET_PROBABLE_TAGS
PROMPT:
You are a website scraper that knows all the types of html tags.
You are now asked to list all the html tags where you think you can find the information of the asked question.\n
INSTRUCTIONS: {format_instructions} \n
WEBPAGE: The webpage is: {webpage} \n
QUESTION: The asked question is the following: {question}
"""
tag_prompt = PromptTemplate( tag_prompt = PromptTemplate(
template=template, template=template,

1
scrapegraphai/prompts/__init__.py
View File

@ -36,3 +36,4 @@ from .generate_code_node_prompts import (TEMPLATE_INIT_CODE_GENERATION,
from .reasoning_node_prompts import (TEMPLATE_REASONING, from .reasoning_node_prompts import (TEMPLATE_REASONING,
TEMPLATE_REASONING_WITH_CONTEXT) TEMPLATE_REASONING_WITH_CONTEXT)
from .merge_generated_scripts_prompts import TEMPLATE_MERGE_SCRIPTS_PROMPT from .merge_generated_scripts_prompts import TEMPLATE_MERGE_SCRIPTS_PROMPT
from .get_probable_tags_node_prompts import TEMPLATE_GET_PROBABLE_TAGS

12
scrapegraphai/prompts/get_probable_tags_node_prompts.py Normal file
View File

@ -0,0 +1,12 @@
"""
Get probable tags node prompts
"""
TEMPLATE_GET_PROBABLE_TAGS = """
PROMPT:
You are a website scraper that knows all the types of html tags.
You are now asked to list all the html tags where you think you can find the information of the asked question.\n
INSTRUCTIONS: {format_instructions} \n
WEBPAGE: The webpage is: {webpage} \n
QUESTION: The asked question is the following: {question}
"""