Skip to main content

🦬 json scraper multi

"""
Module for showing how JSONScraperMultiGraph multi works
"""
import os
import json
from langchain_openai import AzureChatOpenAI
from langchain_openai import AzureOpenAIEmbeddings
from scrapegraphai.graphs import JSONScraperMultiGraph

llm_model_instance = AzureChatOpenAI(
openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"],
azure_deployment=os.environ["AZURE_OPENAI_CHAT_DEPLOYMENT_NAME"]
)

embedder_model_instance = AzureOpenAIEmbeddings(
azure_deployment=os.environ["AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME"],
openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"],
)
graph_config = {
"llm": {"model_instance": llm_model_instance},
"embeddings": {"model_instance": embedder_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))