I’m trying to get scapegraph-ai working. I downloaded the repo from here https://github.com/ScrapeGraphAI/Scrapegraph-ai and followed the instructions in the readme. I downloaded Ollama from here https://ollama.com/ and downloaded the LLama3.1 model. When I launch Ollama from CMD everything seems to work correctly. I can use the model using the command ollama run llama3.1. However, I have problems in python. I’m trying to scrape using the scapegraph-ai library using the ollama models locally. I created a simple program in python that allows you to do scaping using scapegraph and taking as input from the prompt the URL and the prompt instructions:

Main.py:

import sys
from scraper import Scraper

def main():
  if len(sys.argv) != 3:
    print("Command: python main.py <URL> <PROMPT_INSTRUCTIONS>")
    sys.exit(1)

  scr = Scraper(sys.argv[1], sys.argv[2])
  scr.scrape()

  if __name__ == "__main__":
    main()

Scraper.py:

from scrapegraphai.graphs import SmartScraperGraph
from scrapegraphai.utils import prettify_exec_info

class Scraper:
   def __init__(self, url, command):
       self.url = url
       self.command = command

   def scrape(self):
       try:
          graph_config = {
              "llm": {
                  "model": "ollama/llama3.1",
                  "temperature": 1,
                  "format": "json",
                  "model_tokens": 2000,
                  "base_url": "http://localhost:11434"
              },
              "embeddings": {
                  "model": "ollama/nomic-embed-text",
                  "temperature": 0,
                  "base_url": "http://localhost:11434"
              }
          }

        smart_scraper_graph = SmartScraperGraph(
            prompt=self.command,
            source=self.url,
            config=graph_config
        )

        result = smart_scraper_graph.run()
        print(result)
        
    except Exception as e:
        print(f"Error: {e}")

But when I launch my python code I get the error:

Model not found, using default token size (8192)

Does anyone know what I’m doing wrong?