Skip to main content

json_scraper_multi_ollama

"""
Module for showing how PDFScraper multi works
"""
import os
import json
from scrapegraphai.graphs import JSONScraperMultiGraph

graph_config = {
"llm": {
"model": "ollama/llama3",
"temperature": 0,
"format": "json", # Ollama needs the format to be specified explicitly
"model_tokens": 4000,
},
"embeddings": {
"model": "ollama/nomic-embed-text",
"temperature": 0,
},
"verbose": True,
"headless": False,
}
FILE_NAME = "inputs/example.json"
curr_dir = os.path.dirname(os.path.realpath(__file__))
file_path = os.path.join(curr_dir, FILE_NAME)

with open(file_path, 'r', encoding="utf-8") as file:
text = file.read()

sources = [text, text]

multiple_search_graph = JSONScraperMultiGraph(
prompt= "List me all the authors, title and genres of the books",
source= sources,
schema=None,
config=graph_config
)

result = multiple_search_graph.run()
print(json.dumps(result, indent=4))