Scrapegraph-ai/examples/fireworks/csv_scraper_graph_multi_fireworks.py
Marco Vinciguerra 4b56604413
Some checks failed
/ build (3.10) (push) Has been cancelled
add examples + test
2024-06-25 10:32:29 +02:00

64 lines
1.8 KiB
Python

"""
Basic example of scraping pipeline using CSVScraperMultiGraph from CSV documents
"""
import os
from dotenv import load_dotenv
import pandas as pd
from scrapegraphai.graphs import CSVScraperMultiGraph
from scrapegraphai.utils import convert_to_csv, convert_to_json, prettify_exec_info
load_dotenv()
# ************************************************
# Read the CSV file
# ************************************************
FILE_NAME = "inputs/username.csv"
curr_dir = os.path.dirname(os.path.realpath(__file__))
file_path = os.path.join(curr_dir, FILE_NAME)
text = pd.read_csv(file_path)
# ************************************************
# Define the configuration for the graph
# ************************************************
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,
}
# ************************************************
# Create the CSVScraperMultiGraph instance and run it
# ************************************************
csv_scraper_graph = CSVScraperMultiGraph(
prompt="List me all the last names",
source=[str(text), str(text)],
config=graph_config
)
result = csv_scraper_graph.run()
print(result)
# ************************************************
# Get graph execution info
# ************************************************
graph_exec_info = csv_scraper_graph.get_execution_info()
print(prettify_exec_info(graph_exec_info))
# Save to json or csv
convert_to_csv(result, "result")
convert_to_json(result, "result")