Sapling Python API Docs | dltHub

Sapling is a platform for building language model applications (grammar/phrase edits, autocomplete/completions, spellcheck, detection, and reporting). The REST API base URL is https://api.sapling.ai/api/v1 and all requests require a 32-character API key (can be passed as key param or Bearer token).

dlt is an open-source Python library that handles authentication, pagination, and schema evolution automatically. dlthub provides AI context files that enable code assistants to generate production-ready pipelines. Install with uv pip install "dlt[workspace]" and start loading Sapling data in under 10 minutes.

---

What data can I load from Sapling?

Here are some of the endpoints you can load from Sapling:

---

How do I authenticate with the Sapling API?

Provide your 32-character API key either as key=<API_KEY> request parameter or in the Authorization header as a Bearer token (Authorization: Bearer <API_KEY>). If both supplied, the key parameter takes precedence.

1. Get your credentials

1. Sign in or register at https://sapling.ai. 2) Go to your API settings/dashboard (https://sapling.ai/api_settings). 3) Click "Generate Key" under the API section. 4) Copy the 32-character key and store it securely.

2. Add them to .dlt/secrets.toml

Copy
[sources.sapling_source]
api_key = "your_32_char_api_key_here"

dlt reads this automatically at runtime — never hardcode tokens in your pipeline script. For production environments, see setting up credentials with dlt for environment variable and vault-based options.

---

How do I set up and run the pipeline?

Set up a virtual environment and install dlt:

Copy
uv venv && source .venv/bin/activate
uv pip install "dlt[workspace]"

1. Install the dlt AI Workbench:

Copy
dlt ai init --agent <your-agent> # <agent>: claude | cursor | codex

This installs project rules, a secrets management skill, appropriate ignore files, and configures the dlt MCP server for your agent. Learn more →

2. Install the rest-api-pipeline toolkit:

Copy
dlt ai toolkit rest-api-pipeline install

This loads the skills and context about dlt the agent uses to build the pipeline iteratively, efficiently, and safely. The agent uses MCP tools to inspect credentials — it never needs to read your secrets.toml directly. Learn more →

3. Start LLM-assisted coding:

Use /find-source to load data from the Sapling API into DuckDB.

The rest-api-pipeline toolkit takes over from here — it reads relevant API documentation, presents you with options for which endpoints to load, and follows a structured workflow to scaffold, debug, and validate the pipeline step by step.

4. Run the pipeline:

Copy
python sapling_pipeline.py

If everything is configured correctly, you'll see output like this:

Copy
Pipeline sapling_pipeline load step completed in 0.26 seconds
1 load package(s) were loaded to destination duckdb and into dataset sapling_data
The duckdb destination used duckdb:/sapling.duckdb location to store data
Load package 1749667187.541553 is LOADED and contains no failed jobs

Inspect your pipeline and data:

Copy
dlt pipeline sapling_pipeline show

This opens the Pipeline Dashboard where you can verify pipeline state, load metrics, schema (tables, columns, types), and query the loaded data directly.

---

Python pipeline example

This example loads edits and complete from the Sapling API into DuckDB. It mirrors the endpoint and data selector configuration from the table above:

Copy
import dlt
from dlt.sources.rest_api import RESTAPIConfig, rest_api_resources

@dlt.source
def sapling_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://api.sapling.ai/api/v1",
            "auth": {
                "type": "bearer",
                "token": api_key,
            },
        },
        "resources": [
            {"name": "edits", "endpoint": {"path": "api/v1/edits", "data_selector": "edits"}},
            {"name": "complete", "endpoint": {"path": "api/v1/complete", "data_selector": "completions"}}
        ],
    }
    yield from rest_api_resources(config)


def get_data() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="sapling_pipeline",
        destination="duckdb",
        dataset_name="sapling_data",
    )
    load_info = pipeline.run(sapling_source())
    print(load_info)

To add more endpoints, append entries from the resource table to the "resources" list using the same name, path, and data_selector pattern.

---

How do I query the loaded data?

Once the pipeline runs, dlt creates one table per resource. You can query with Python or SQL.

Python (pandas DataFrame):

Copy
import dlt

data = dlt.pipeline("sapling_pipeline").dataset()
sessions_df = data.edits.df()
print(sessions_df.head())

SQL (DuckDB example):

Copy
SELECT * FROM sapling_data.edits LIMIT 10;

In a marimo or Jupyter notebook:

Copy
import dlt

data = dlt.pipeline("sapling_pipeline").dataset()
data.edits.df().head()

See how to explore your data in marimo Notebooks and how to query your data in Python with dataset.

---

What destinations can I load Sapling data to?

dlt supports loading into any of these destinations — only the destination parameter changes:

Change the destination in dlt.pipeline(destination="snowflake") and add credentials in .dlt/secrets.toml. See the full destinations list.

---

Troubleshooting

Authentication failures

If you receive 401/403 responses, verify you are using the 32-character API key and supplying it either as key parameter or in the Authorization: Bearer <API_KEY> header. Note that a provided key parameter takes precedence over the Authorization header.

Rate limits and quota

Trial/dev keys are limited (example: 50,000 characters per 24 hours). Production keys are usage-billed. For reporting on quota usage, use the api_quota_usage reporting endpoint to inspect current quota and usage.

Pagination and response shapes

Most core NLP endpoints return a single response describing suggestions rather than paginated lists. Reporting endpoint api_endpoint_usage returns nested dictionaries under the "data" key keyed by endpoint names; api_quota_usage returns quota/usage at top-level. When expecting lists: edits -> "edits" array; chunk_text/chunk_html -> "chunks" array; spellcheck returns a top-level list of edits per the SDK docs.

Common error responses

• 401 Unauthorized / 403 Forbidden: invalid/missing API key. - 429 Too Many Requests: rate limited (enforce backoff). - 400 Bad Request: invalid parameters (missing required fields like text/query). - 500+ Server Errors: retry with exponential backoff.

Ensure that the API key is valid to avoid 401 Unauthorized errors. Also, verify endpoint paths and parameters to avoid 404 Not Found errors.

---

Next steps

Continue your data engineering journey with the other toolkits of the dltHub AI Workbench:

• data-exploration — Build custom notebooks, charts, and dashboards for deeper analysis with marimo notebooks.
• dlthub-runtime — Deploy, schedule, and monitor your pipeline in production.

Copy
dlt ai toolkit data-exploration install
dlt ai toolkit dlthub-runtime install

• How to deploy a pipeline
• How to explore your data in marimo Notebooks
• How to query your data in Python with dataset
• Join the dlt community on Slack