mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-07-04 21:00:36 +08:00
45 lines
1.1 KiB
Python
45 lines
1.1 KiB
Python
"""
|
|
Module for showing how PDFScraper multi works
|
|
"""
|
|
import os
|
|
import json
|
|
from dotenv import load_dotenv
|
|
from scrapegraphai.graphs import JSONScraperMultiGraph
|
|
|
|
load_dotenv()
|
|
|
|
fireworks_api_key = os.getenv("FIREWORKS_APIKEY")
|
|
|
|
graph_config = {
|
|
"llm": {
|
|
"api_key": fireworks_api_key,
|
|
"model": "fireworks/accounts/fireworks/models/mixtral-8x7b-instruct"
|
|
},
|
|
"embeddings": {
|
|
"model": "ollama/nomic-embed-text",
|
|
"temperature": 0,
|
|
# "base_url": "http://localhost:11434", # set ollama URL arbitrarily
|
|
},
|
|
"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))
|