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 1 Packages Projects Releases Wiki Activity

fix: refactoring of merge_answer_node

Browse Source
This commit is contained in:
Matteo Vedovati 2024-08-07 21:42:54 +02:00
parent bfc6852b77
commit 898e5a7af5
3 changed files with 16 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
scrapegraphai/helpers/__init__.py
View File

@ -10,3 +10,4 @@ from .generate_answer_node_prompts import template_chunks, template_no_chunks, t
from .generate_answer_node_csv_prompts import template_chunks_csv, template_no_chunks_csv, template_merge_csv from .generate_answer_node_csv_prompts import template_chunks_csv, template_no_chunks_csv, template_merge_csv
from .generate_answer_node_pdf_prompts import template_chunks_pdf, template_no_chunks_pdf, template_merge_pdf from .generate_answer_node_pdf_prompts import template_chunks_pdf, template_no_chunks_pdf, template_merge_pdf
from .generate_answer_node_omni_prompts import template_chunks_omni, template_no_chunk_omni, template_merge_omni from .generate_answer_node_omni_prompts import template_chunks_omni, template_no_chunk_omni, template_merge_omni
from .merge_answer_node_prompts import template_combined

13
scrapegraphai/helpers/merge_answer_node_prompts.py Normal file
View File

@ -0,0 +1,13 @@
"""
Merge answer node prompts
"""
template_combined = """
You are a website scraper and you have just scraped some content from multiple websites.\n
You are now asked to provide an answer to a USER PROMPT based on the content you have scraped.\n
You need to merge the content from the different websites into a single answer without repetitions (if there are any). \n
The scraped contents are in a JSON format and you need to merge them based on the context and providing a correct JSON structure.\n
OUTPUT INSTRUCTIONS: {format_instructions}\n
USER PROMPT: {user_prompt}\n
WEBSITE CONTENT: {website_content}
"""

13
scrapegraphai/nodes/merge_answers_node.py
View File

@ -7,6 +7,7 @@ from langchain.prompts import PromptTemplate
from langchain_core.output_parsers import JsonOutputParser from langchain_core.output_parsers import JsonOutputParser
from ..utils.logging import get_logger from ..utils.logging import get_logger
from .base_node import BaseNode from .base_node import BaseNode
from ..helpers import template_combined
class MergeAnswersNode(BaseNode): class MergeAnswersNode(BaseNode):
@ -79,18 +80,8 @@ class MergeAnswersNode(BaseNode):
format_instructions = output_parser.get_format_instructions() format_instructions = output_parser.get_format_instructions()
template_merge = """
You are a website scraper and you have just scraped some content from multiple websites.\n
You are now asked to provide an answer to a USER PROMPT based on the content you have scraped.\n
You need to merge the content from the different websites into a single answer without repetitions (if there are any). \n
The scraped contents are in a JSON format and you need to merge them based on the context and providing a correct JSON structure.\n
OUTPUT INSTRUCTIONS: {format_instructions}\n
USER PROMPT: {user_prompt}\n
WEBSITE CONTENT: {website_content}
"""
prompt_template = PromptTemplate( prompt_template = PromptTemplate(
template=template_merge, template=template_combined,
input_variables=["user_prompt"], input_variables=["user_prompt"],
partial_variables={ partial_variables={
"format_instructions": format_instructions, "format_instructions": format_instructions,