Our API lets you transform any information - from documents to web pages - into structured data with just a few API calls.
Installation
First, install the Python client library:
We constantly push updates. Keep your client current with pip install structifyai --upgrade
Authentication
Get your API key from the Structify Dashboard and set it as an environment variable:
export STRUCTIFY_API_TOKEN="your_api_key"
from structify import Structify
# Uses STRUCTIFY_API_TOKEN env var automatically
client = Structify()
# Or provide explicitly
client = Structify(api_key="your_api_key")
Create Your First Dataset
Let’s build a simple book and author dataset in three steps:
1. Define Your Schema
Create tables for authors and books, plus a relationship between them:
from structify import Structify
from structify.types.table import Table, Property
from structify.types.dataset_descriptor import Relationship
client = Structify()
# Define entity tables
tables = [
Table(
name="author",
description="an individual who wrote a book",
properties=[
Property(name="name", description="The name of the author"),
Property(name="genre", description="The genre the author typically writes in"),
Property(name="birth_year", description="Year the author was born", prop_type="Integer")
]
),
Table(
name="book",
description="a book that has been written",
properties=[
Property(name="title", description="The title of the book"),
Property(name="publication_year", description="Year published", prop_type="Integer"),
Property(name="copies_sold", description="Number of copies sold", prop_type="Integer")
]
)
]
# Define relationships
relationships = [
Relationship(
name="authored_by",
description="Connects a book to its author",
source_table="book",
target_table="author"
)
]
# Create the dataset
client.datasets.create(
name="books",
description="Books and their authors",
tables=tables,
relationships=relationships
)
2. Add Initial Data
Add some authors to start with:
from structify.types import KnowledgeGraphParam, EntityParam
authors = ["J.K. Rowling", "Stephen King", "Harper Lee"]
for author_name in authors:
client.entities.add(
dataset="books",
kg=KnowledgeGraphParam(
entities=[
EntityParam(
id=0,
type="author",
properties={"name": author_name}
)
]
)
)
3. Enrich Your Dataset
Use Structify’s AI to find and add information:
# For each author, find their genre and books
for author in client.datasets.view_table(dataset="books", table="author"):
# Fill in missing properties
client.structure.enhance_property(
entity_id=author.id,
property_name="genre"
)
client.structure.enhance_property(
entity_id=author.id,
property_name="birth_year"
)
# Find books they've written
client.structure.enhance_relationship(
entity_id=author.id,
relationship_name="authored_by"
)
Complete Example
Here’s everything together in one script:
from structify import Structify
from structify.types import KnowledgeGraphParam, EntityParam
from structify.types.table import Table, Property
from structify.types.dataset_descriptor import Relationship
def create_book_dataset():
client = Structify()
# Step 1: Define schema
tables = [
Table(
name="author",
description="an individual who wrote a book",
properties=[
Property(name="name", description="The name of the author"),
Property(name="genre", description="The genre the author typically writes in"),
Property(name="birth_year", description="Year born", prop_type="Integer")
]
),
Table(
name="book",
description="a book that has been written",
properties=[
Property(name="title", description="The title of the book"),
Property(name="publication_year", description="Year published", prop_type="Integer"),
Property(name="copies_sold", description="Copies sold", prop_type="Integer")
]
)
]
relationships = [
Relationship(
name="authored_by",
description="Connects a book to its author",
source_table="book",
target_table="author"
)
]
# Create dataset
client.datasets.create(
name="books",
description="Books and their authors",
tables=tables,
relationships=relationships
)
# Step 2: Add authors
for author in ["J.K. Rowling", "Stephen King", "Harper Lee"]:
client.entities.add(
dataset="books",
kg=KnowledgeGraphParam(
entities=[EntityParam(id=0, type="author", properties={"name": author})]
)
)
# Step 3: Enrich with AI
for author in client.datasets.view_table(dataset="books", table="author"):
client.structure.enhance_property(entity_id=author.id, property_name="genre")
client.structure.enhance_relationship(entity_id=author.id, relationship_name="authored_by")
print("Dataset created and enriched!")
# View results
results = client.datasets.view_table(dataset="books", table="author", limit=10)
for author in results:
print(f"Author: {author.properties['name']}, Genre: {author.properties.get('genre', 'Unknown')}")
if __name__ == "__main__":
create_book_dataset()
What’s Next?
Now that you’ve created your first dataset, you can:
Key Capabilities
After reading our documentation, you’ll be able to:
- Create personalized datasets of your professional network
- Monitor changes in continuously updating datasets
- Extract structured data from SEC filings and pitch decks
- Automate notifications when new entities match your criteria
- Build structured datasets from any unstructured data source
