No credit card required

Extended GPT Scraper

drobnikj/extended-gpt-scraper

No credit card required

Extract data from any website and feed it into GPT via the OpenAI API. Use ChatGPT to proofread content, analyze sentiment, summarize reviews, extract contact details, and much more.

Do you want to learn more about this Actor?

Get a demo

Back to issues Create new issue

Instructions limit with JSON output

Closed

thegenie opened this issue

Hi,

Thanks for clarifying the limit 1280 in our other closed ticket. I can see the error now which is useful and through trial and error realised there must be a limit (perhaps add to the page info too)

However, I've only put text in the "instructions" and not the "schemaDescription" as advised, but I still get the error message relating to char limit? I have set the option "Use JSON schema to format answer" to confirm.

Does this perhaps force the instructions into the the description irrispective of using the instructions, as you mentioned it's copied over? Therefore, is there no way round this?

I was wanting a fixed JSON output but with long instructions to get chatGPT to do a complex scoring system for product analysis so the instructions need to be pretty long to get it to do all the scoring I need.

Thanks J

Lukáš Průša (lukas.prusa)

Hi again,

thanks a lot for the suggestion! We will definitely add the tip to schema and improve it ;)

Yes, as mentioned the schemaDescription by default, takes the value of instructions unless it has a value already. Simply set schemaDescription to any value, e.g. " ". From the tooltip: “By default, the instructions field's value is used as the schema description, you can change it here.”

OpenAI's own documentation around the JSON functions does not contain much useful information. There is almost no info about the difference between the context (our instructions) and the functions descriptions (our schemaDescription). From my own experience, you can simply use instructions and enable the JSON schema, and it will give almost the same results ;)

I hope this helps, thanks!

Add comment

Developer

Jakub Drobník

Actor Metrics

79 monthly users
46 stars
>99% runs succeeded
5.8 days response time
Created in Jun 2023
Modified 6 days ago

Categories

Lead generation

Developer tools

Website Content Crawler

apify/website-content-crawler

Crawl websites and extract text content to feed AI models, LLM applications, vector databases, or RAG pipelines. The Actor supports rich formatting using Markdown, cleans the HTML, downloads files, and integrates well with 🦜🔗 LangChain, LlamaIndex, and the wider LLM ecosystem.

Apify

26.9k

663

Google Maps Extractor

compass/google-maps-extractor

Extract data from hundreds of places fast. Scrape Google Maps by keyword, category, location, URLs & other filters. Get addresses, contact info, opening hours, popular times, prices, menus & more. Export scraped data, run the scraper via API, schedule and monitor runs, or integrate with other tools.

Compass

18k

357

Instagram Scraper

apify/instagram-scraper

Scrape and download Instagram posts, profiles, places, hashtags, photos, and comments. Get data from Instagram using one or more Instagram URLs or search queries. Export scraped data, run the scraper via API, schedule and monitor runs or integrate with other tools.

Apify

59.3k

507

Facebook Posts Scraper

apify/facebook-posts-scraper

Extract data from hundreds of Facebook posts from one or multiple Facebook pages and profiles. Get post URL, post text, page or profile URL, timestamp, number of likes, shares, comments, and more. Download the data in JSON, CSV, and Excel and use it in apps, spreadsheets, and reports.

Apify

15k

191

Contact Details Scraper

vdrmota/contact-info-scraper

Free email extractor to extract and download emails, phone numbers, Facebook, Twitter, LinkedIn, and Instagram profiles from any website. Extract contact information at scale from lists of URLs and download the data as Excel, CSV, JSON, HTML, and XML.

Vojta Drmota

24.7k

195

Cheerio Scraper

apify/cheerio-scraper

Crawls websites using raw HTTP requests, parses the HTML with the Cheerio library, and extracts data from the pages using a Node.js code. Supports both recursive crawling and lists of URLs. This actor is a high-performance alternative to apify/web-scraper for websites that do not require JavaScript.

Apify

5.6k

Google Maps Scraper

compass/crawler-google-places

Extract data from hundreds of Google Maps locations and businesses. Get Google Maps data including reviews, images, contact info, opening hours, location, popular times, prices & more. Export scraped data, run the scraper via API, schedule and monitor runs, or integrate with other tools.

Compass

79k

568

Web Scraper

apify/web-scraper

Crawls arbitrary websites using the Chrome browser and extracts data from pages using JavaScript code. The Actor supports both recursive crawling and lists of URLs and automatically manages concurrency for maximum performance. This is Apify's basic tool for web crawling and scraping.

Apify

71.6k

226

Facebook Groups Scraper

apify/facebook-groups-scraper

Extract data from one or multiple public Facebook groups. Get group and post URLs, post text, comments, timestamp, likes and comments count, and basic commentator info. Download the data in JSON, CSV, and Excel and use it in apps, spreadsheets, and reports.

Apify

7.2k