Skip to content

fix(FetchNode): add OpenAI markdown optimization to Azure #555

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 17, 2024
Merged

fix(FetchNode): add OpenAI markdown optimization to Azure #555

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions scrapegraphai/nodes/fetch_node.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@

import json
from typing import List, Optional
from langchain_openai import ChatOpenAI
from langchain_openai import ChatOpenAI, AzureChatOpenAI
import pandas as pd
import requests
from langchain_community.document_loaders import PyPDFLoader
Expand Down Expand Up @@ -221,7 +221,7 @@ def handle_local_source(self, state, source):

parsed_content = source

if isinstance(self.llm_model, ChatOpenAI) and not self.script_creator or self.force and not self.script_creator:
if (isinstance(self.llm_model, ChatOpenAI) or isinstance(self.llm_model, AzureChatOpenAI)) and not self.script_creator or self.force and not self.script_creator:
parsed_content = convert_to_md(source)
else:
parsed_content = source
Expand Down Expand Up @@ -258,7 +258,7 @@ def handle_web_source(self, state, source):
if not self.cut:
parsed_content = cleanup_html(response, source)

if (isinstance(self.llm_model, ChatOpenAI)
if ((isinstance(self.llm_model, ChatOpenAI) or isinstance(self.llm_model, AzureChatOpenAI))
and not self.script_creator) or (self.force and not self.script_creator):
parsed_content = convert_to_md(source, parsed_content)

Expand Down Expand Up @@ -287,7 +287,7 @@ def handle_web_source(self, state, source):
raise ValueError("No HTML body content found in the document fetched by ChromiumLoader.")
parsed_content = document[0].page_content

if isinstance(self.llm_model, ChatOpenAI) and not self.script_creator or self.force and not self.script_creator and not self.openai_md_enabled:
if (isinstance(self.llm_model, ChatOpenAI) or isinstance(self.llm_model, AzureChatOpenAI)) and not self.script_creator or self.force and not self.script_creator and not self.openai_md_enabled:
parsed_content = convert_to_md(document[0].page_content, parsed_content)

compressed_document = [
Expand Down
Loading