Local Documents

import os
from dotenv import load_dotenv
from scrapegraphai.graphs import CSVScraperGraph
from scrapegraphai.utils import 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)

with open(file_path, "r") as file:
    text = file.read()

# Define the configuration for the graph
openai_key = os.getenv("OPENAI_APIKEY")

graph_config = {
    "llm": {
        "api_key": openai_key,
        "model": "openai/gpt-4o",
    },
}

# Create the CSVScraperGraph instance and run it
csv_scraper_graph = CSVScraperGraph(
    prompt="List me all the last names",
    source=str(text),  # Pass the content of the file
    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))

import json
import os
from dotenv import load_dotenv
from scrapegraphai.graphs import DocumentScraperGraph

load_dotenv()

openai_key = os.getenv("OPENAI_APIKEY")

graph_config = {
    "llm": {
        "api_key": openai_key,
        "model": "openai/gpt-4o",
    }
}

source = """
    The Divine Comedy, Italian La Divina Commedia, original name La commedia, 
    long narrative poem written in Italian circa 1308/21 by Dante. It is usually 
    held to be one of the world's great works of literature.
    Divided into three major sections—Inferno, Purgatorio, and Paradiso—the 
    narrative traces the journey of Dante from darkness and error to the 
    revelation of the divine light, culminating in the Beatific Vision of God.
    Dante is guided by the Roman poet Virgil, who represents the epitome of 
    human knowledge, from the dark wood through the descending circles of the 
    pit of Hell (Inferno). He then climbs the mountain of Purgatory, guided
    by the Roman poet Statius, who represents the fulfilment of human knowledge, 
    and is finally led by his lifelong love, the Beatrice of his earlier poetry, 
    through the celestial spheres of Paradise.
"""

pdf_scraper_graph = DocumentScraperGraph(
    prompt="Summarize the text and find the main topics",
    source=source,
    config=graph_config,
)

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

first_name,last_name,email
John,Doe,[email protected]
Jane,Smith,[email protected]
Bob,Johnson,[email protected]

{
    "last_names": [
        "Doe",
        "Smith",
        "Johnson"
    ]
}

{
    "summary": "The Divine Comedy is a long narrative poem by Dante written circa 1308-1321, divided into three sections: Inferno, Purgatorio, and Paradiso. It traces Dante's journey from darkness to divine enlightenment.",
    "main_topics": [
        "Italian literature",
        "Dante's spiritual journey",
        "Three realms: Hell, Purgatory, Paradise",
        "Guidance by Virgil, Statius, and Beatrice",
        "Medieval Christian theology"
    ],
    "key_figures": [
        "Dante",
        "Virgil",
        "Statius",
        "Beatrice"
    ]
}

from scrapegraphai.graphs import CSVScraperMultiGraph

csv_files = [
    "data/sales_q1.csv",
    "data/sales_q2.csv",
    "data/sales_q3.csv",
]

csv_contents = []
for file_path in csv_files:
    with open(file_path, "r") as f:
        csv_contents.append(f.read())

multi_csv_graph = CSVScraperMultiGraph(
    prompt="Calculate total sales for each product",
    source=csv_contents,
    config=graph_config,
)

result = multi_csv_graph.run()
print(result)

from typing import List
from pydantic import BaseModel, Field
from scrapegraphai.graphs import DocumentScraperGraph

class Character(BaseModel):
    name: str = Field(description="Character name")
    role: str = Field(description="Role in the story")

class BookSummary(BaseModel):
    title: str = Field(description="Book title")
    summary: str = Field(description="Brief summary")
    characters: List[Character]
    themes: List[str]

document_graph = DocumentScraperGraph(
    prompt="Analyze this literary text",
    source=document_text,
    schema=BookSummary,
    config=graph_config,
)

result = document_graph.run()