Skip to content
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.

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

feat: added puppeteer loader node #314

Merged

Conversation

AidanTilgner
Copy link
Contributor

I updated the components package to add the puppeteer integration described in this issue. This is my first PR here, so let me know if I need to change anything/everything.

Screenshot 2023-06-13 at 1 18 00 PM
  • Add Puppeteer Loader node
  • Puppeteer Loader node should be able to scrape data from webpages
  • Build successful

Note: Puppeteer is updating their default headless mode, and therefore a warning is displayed and the option to update the headless proeprty to headless: "new" is offered. However, it seems that the decision to update to headless: "new" is controlled by the PuppeteerWebBaseLoader langchain loader. I don't think this is an issue, as the new headless mode will become the default soon, but I figured I'd mention it.

@CLAassistant
Copy link

CLAassistant commented Jun 13, 2023

CLA assistant check
All committers have signed the CLA.

@AidanTilgner
Copy link
Contributor Author

It seems that there are some merge conflicts now since the new emergency changes were made. I will update this tomorrow.

@govind-kumarr
Copy link
Contributor

I updated the components package to add the puppeteer integration described in this issue. This is my first PR here, so let me know if I need to change anything/everything.

Screenshot 2023-06-13 at 1 18 00 PM * [x] Add Puppeteer Loader node * [x] Puppeteer Loader node should be able to scrape data from webpages * [x] Build successful

Note: Puppeteer is updating their default headless mode, and therefore a warning is displayed, and the option to update the headless proeprty to headless: "new" is offered. However, it seems that the decision to update to headless: "new" is controlled by the PuppeteerWebBaseLoader langchain loader. I don't think this is an issue, as the new headless mode will become the default soon, but I figured I'd mention it.

How are you testing it?

@AidanTilgner
Copy link
Contributor Author

AidanTilgner commented Jun 14, 2023

Screenshot 2023-06-14 at 10 58 53 AM

I ran the build and start command according to the contributing guidelines. I also created the above chain for testing purposes. I confirmed that the "Puppeteer Web Scraper" node was scraping documents successfully. Then I used the "Pinecone Upsert Document" node to confirm that they were being scraped and then pulled into memory by the language model. Everything works the same as the cherio reference code.

Copy link
Contributor

@HenryHengZJ HenryHengZJ left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

thanks @AidanTilgner! lgtm

@HenryHengZJ HenryHengZJ merged commit 170450a into FlowiseAI:main Jun 14, 2023
JohnBQuinn pushed a commit to JohnBQuinn/Flowise that referenced this pull request Jun 7, 2024
* feat: adFlow auto layout

* chore: delete file and build pnpm lock file
JohnBQuinn pushed a commit to JohnBQuinn/Flowise that referenced this pull request Jun 7, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants