Skip to main content

json_scraper_multi_huggingfacehub

"""
Module for showing how PDFScraper multi works
"""
import os
import json
from dotenv import load_dotenv
from scrapegraphai.graphs import JSONScraperMultiGraph
from langchain_community.llms import HuggingFaceEndpoint
from langchain_community.embeddings import HuggingFaceInferenceAPIEmbeddings

load_dotenv()

HUGGINGFACEHUB_API_TOKEN = os.getenv('HUGGINGFACEHUB_API_TOKEN')

repo_id = "mistralai/Mistral-7B-Instruct-v0.2"

llm_model_instance = HuggingFaceEndpoint(
repo_id=repo_id, max_length=128, temperature=0.5, token=HUGGINGFACEHUB_API_TOKEN
)

embedder_model_instance = HuggingFaceInferenceAPIEmbeddings(
api_key=HUGGINGFACEHUB_API_TOKEN, model_name="sentence-transformers/all-MiniLM-l6-v2"
)

graph_config = {
"llm": {"model_instance": llm_model_instance},
}
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))