Keymate-ai Python API Docs | dltHub

Keymate-ai is a privacy-focused AI memory and knowledge-base platform for storing, organizing, and querying documents, web pages, and notes. The REST API base URL is https://dialogue-engine.keymate.ai/api and all requests require a Bearer token (integration/API key) in the Authorization header.

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 Keymate-ai data in under 10 minutes.

---

What data can I load from Keymate-ai?

Here are some of the endpoints you can load from Keymate-ai:

---

How do I authenticate with the Keymate-ai API?

Include an HTTP header: Authorization: Bearer <YOUR_API_TOKEN>. Integration tokens or API keys are generated from the Keymate web app (account/integrations or team settings) and used as a bearer credential for API calls.

1. Get your credentials

1. Sign in to https://app.keymate.ai with your account. 2. Go to Account or Team/Organization settings (or Integrations). 3. Find 'API keys', 'Integrations' or 'Developer' section. 4. Create a new API key / integration token; copy the value. 5. Store the token securely and use it in the Authorization header as 'Bearer '.

2. Add them to .dlt/secrets.toml

Copy
[sources.keymate_ai_source]
api_key = "your_keymate_api_token_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 Keymate-ai 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 keymate_ai_pipeline.py

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

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

Inspect your pipeline and data:

Copy
dlt pipeline keymate_ai_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 collections and search from the Keymate-ai 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 keymate_ai_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://dialogue-engine.keymate.ai/api",
            "auth": {
                "type": "bearer",
                "token": api_key,
            },
        },
        "resources": [
            {"name": "collections", "endpoint": {"path": "api/collections", "data_selector": "data"}},
            {"name": "search", "endpoint": {"path": "api/search", "data_selector": "results"}}
        ],
    }
    yield from rest_api_resources(config)


def get_data() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="keymate_ai_pipeline",
        destination="duckdb",
        dataset_name="keymate_ai_data",
    )
    load_info = pipeline.run(keymate_ai_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("keymate_ai_pipeline").dataset()
sessions_df = data.collections.df()
print(sessions_df.head())

SQL (DuckDB example):

Copy
SELECT * FROM keymate_ai_data.collections LIMIT 10;

In a marimo or Jupyter notebook:

Copy
import dlt

data = dlt.pipeline("keymate_ai_pipeline").dataset()
data.collections.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 Keymate-ai 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 your Authorization header uses 'Bearer ' and that the token has not expired or been revoked. Generate a new token in the web app's Integrations/API Keys section.

Rate limiting and 429 responses

The API may enforce rate limits for integrations. If you receive 429 Too Many Requests, implement exponential backoff and retry after the Retry-After header.

Pagination quirks

Endpoints that return lists typically paginate results; check for 'next' or 'cursor' fields in the response and use provided cursors for subsequent GETs. If responses include 'data' or 'items' arrays, iterate pages until empty.

Integration / Make.com errors

When using the Make.com connector, validate collection IDs and file formats. Check Make scenario logs for detailed request/response payloads and errors.

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