feat: refactoring of get_probable_tags node

U-C4N · Oct 23, 2024 · f658092 · f658092
1 parent 94b9836
commit f658092
Show file tree

Hide file tree

Showing 3 changed files with 15 additions and 8 deletions.
diff --git a/scrapegraphai/nodes/get_probable_tags_node.py b/scrapegraphai/nodes/get_probable_tags_node.py
@@ -4,6 +4,7 @@
 from typing import List, Optional
 from langchain.output_parsers import CommaSeparatedListOutputParser
 from langchain.prompts import PromptTemplate
+from ..prompts import TEMPLATE_GET_PROBABLE_TAGS
 from ..utils.logging import get_logger
 from .base_node import BaseNode
 
@@ -68,14 +69,7 @@ def execute(self, state: dict) -> dict:
         output_parser = CommaSeparatedListOutputParser()
         format_instructions = output_parser.get_format_instructions()
 
-        template = """
-        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}
-        """
+        template = TEMPLATE_GET_PROBABLE_TAGS
 
         tag_prompt = PromptTemplate(
             template=template,

diff --git a/scrapegraphai/prompts/__init__.py b/scrapegraphai/prompts/__init__.py
@@ -36,3 +36,4 @@
 from .reasoning_node_prompts import (TEMPLATE_REASONING,
                                      TEMPLATE_REASONING_WITH_CONTEXT)
 from .merge_generated_scripts_prompts import TEMPLATE_MERGE_SCRIPTS_PROMPT
+from .get_probable_tags_node_prompts import TEMPLATE_GET_PROBABLE_TAGS
diff --git a/scrapegraphai/prompts/get_probable_tags_node_prompts.py b/scrapegraphai/prompts/get_probable_tags_node_prompts.py
@@ -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}
+"""