DeepSieve Python SDK

Developer-friendly & type-safe Python SDK for the DeepSieve /v1 API — cited deep-research runs, dataset sync, reports, chat and webhooks.

Install: pip install deepsieve · Quickstart: SDK(bearer_auth="ds_live_...") already targets the hosted product at https://deepsieve.ai. You only need the Server Selection section below if you self-host or are testing against staging.

Summary

DeepSieve API: The agent-facing DeepSieve /v1 API — cited deep-research runs, dataset sync, reports, chat, webhooks, keys.

Table of Contents

• DeepSieve Python SDK
  • SDK Installation
  • IDE Support
  • SDK Example Usage
  • Authentication
  • Available Resources and Operations
  • Retries
  • Error Handling
  • Server Selection
  • Custom HTTP Client
  • Resource Management
  • Debugging
• Development
  • Maturity
  • Contributions

SDK Installation

pip install deepsieve

uv add deepsieve

poetry add deepsieve

Shell and script usage with uv

You can use this SDK in a Python shell with uv and the uvx command that comes with it like so:

uvx --from deepsieve python

It's also possible to write a standalone Python script without needing to set up a whole project like so:

#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.10"
# dependencies = [
#     "deepsieve",
# ]
# ///

from deepsieve import SDK

sdk = SDK(
  # SDK arguments
)

# Rest of script here...

Once that is saved to a file, you can run it with uv run script.py where script.py can be replaced with the actual file name.

IDE Support

PyCharm

Generally, the SDK will work well with most IDEs out of the box. However, when using PyCharm, you can enjoy much better integration with Pydantic by installing an additional plugin.

• PyCharm Pydantic Plugin

SDK Example Usage

Example

# Synchronous Example
from deepsieve import SDK


with SDK(
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.v1_meta.v1_meta_get_me()

    # Handle response
    print(res)

The same SDK client can also be used to make asynchronous requests by importing asyncio.

# Asynchronous Example
import asyncio
from deepsieve import SDK

async def main():

    async with SDK(
        bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
    ) as sdk:

        res = await sdk.v1_meta.v1_meta_get_me_async()

        # Handle response
        print(res)

asyncio.run(main())

Authentication

Per-Client Security Schemes

This SDK supports the following security scheme globally:

Name	Type	Scheme
bearer_auth	http	HTTP Bearer

To authenticate with the API the bearer_auth parameter must be set when initializing the SDK client instance. For example:

from deepsieve import SDK


with SDK(
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.v1_meta.v1_meta_get_me()

    # Handle response
    print(res)

Per-Operation Security Schemes

Some operations in this SDK require the security scheme to be specified at the request level. For example:

from deepsieve import SDK, models


with SDK() as sdk:

    res = sdk.v1_research.v1_research_retry_run(security=models.V1ResearchRetryRunSecurity(

    ), run_id="ff9a2cab-d83a-4cb3-952e-86118864883e")

    # Handle response
    print(res)

Available Resources and Operations

Available methods

V1Audit

• v1_audit_list_audit_events - Read the org's audit trail (Pro+)

V1Auth

• v1_auth_start_device_authorization - Begin a CLI device authorization
• v1_auth_claim_device_token - Poll for the approved credential

V1Blueprints

• v1_blueprints_list_blueprints - List the Blueprints you can read
• v1_blueprints_get_blueprint - Read one Blueprint's schema
• v1_blueprints_read_blueprint_entity - Read (and incrementally sync) one entity's rows in a named Blueprint
• v1_blueprints_export_blueprint - Export a named Blueprint's whole dataset (NDJSON / JSON / CSV)
• v1_blueprints_propose_change - Ask what a change to the named Blueprint would be (writes nothing)
• v1_blueprints_start_onboarding - Start Blueprint onboarding from a natural-language prompt (202)
• v1_blueprints_get_onboarding - Poll an onboarding session (draft + follow-ups)
• v1_blueprints_answer_onboarding - Answer one follow-up question
• v1_blueprints_chat_onboarding - One synchronous adjustments-chat turn on the draft
• v1_blueprints_get_onboarding_chat - The persisted adjustments-chat thread (scope blueprint:read)
• v1_blueprints_adjust_onboarding - Adjust the draft in natural language (202) — DEPRECATED, use /chat ⚠️ Deprecated
• v1_blueprints_approve_onboarding - Approve the draft and instantiate it (202)

V1Changes

• v1_changes_list_changes - List merges, renames, successor links and removed links, newest first
• v1_changes_undo_change - Undo a merge, a rename or a successor link

V1Chat

• v1_chat_send_message - Ask the research agent about a run (202)
• v1_chat_get_thread - Read the run's chat thread
• v1_chat_revert_action - Revert a data change a chat answer applied
• v1_chat_confirm_action - Apply a chat change that is waiting for confirmation
• v1_chat_dismiss_action - Decline a chat change that is waiting for confirmation

V1Data

• v1_data_export_dataset - Export the whole dataset (NDJSON / JSON / CSV)

V1Holds

• v1_holds_list_holds - List cells a user set on purpose, newest first
• v1_holds_apply_cell_finding - Take the newer value research found for a held cell
• v1_holds_release_cell - Stop protecting a held cell
• v1_holds_keep_cell_value - Keep the user's value and dismiss research's newer finding

V1Keys

• v1_keys_create_key - Mint an API key (secret revealed once)
• v1_keys_list_keys - List API keys (metadata only)
• v1_keys_revoke_key - Revoke an API key immediately
• v1_keys_rotate_key - Rotate an API key (24h grace window)

V1Lineage

• v1_lineage_read_column_changes - Change log for one column across records (newest first)
• v1_lineage_read_cell_changes - One cell's full change log (newest first)

V1Links

• v1_links_remove_link - Remove one many-to-many link from a record

V1Members

• v1_members_list_members - The org's roster and editor-seat usage (read-only)

V1Merges

• v1_merges_preview_merge - Preview marking rows as duplicates of one another
• v1_merges_create_merge - Mark rows as duplicates of one another and merge them

V1Meta

• v1_meta_get_me - Who am I? (key verification)

V1Reports

• v1_reports_list_reports_v1 - List saved reports
• v1_reports_create_report_v1 - Create a saved report
• v1_reports_report_columns_v1 - The selectable report-column vocabulary per entity
• v1_reports_get_report_v1 - Fetch one saved report
• v1_reports_update_report_v1 - Update a saved report's name or config
• v1_reports_delete_report_v1 - Delete a saved report
• v1_reports_report_tab_data_v1 - Read a report tab's cross-run rows

V1Research

• v1_research_create_run - Start a research run (async, 202)
• v1_research_list_runs - List research runs
• v1_research_get_run - Poll one research run
• v1_research_cancel_run - Request cancellation of a run
• v1_research_retry_run - Retry a failed, stopped or empty run
• v1_research_set_monitoring - Turn a report's monitoring on or off
• v1_research_get_reruns - The re-research waiting for approval on a report
• v1_research_approve_reruns - Approve the re-research waiting on a report (spends money)
• v1_research_set_reruns_auto_approve - Turn a report's auto-approve on or off
• v1_research_list_monitoring - Every actively-monitored report, what it costs, and what it duplicates
• v1_research_estimate_run - What would this run cost?

V1Webhooks

• v1_webhooks_create_webhook - Register a webhook endpoint (secret revealed once)
• v1_webhooks_list_webhooks - List webhook endpoints
• v1_webhooks_get_webhook - Fetch one webhook endpoint
• v1_webhooks_update_webhook - Update a webhook endpoint's URL or events
• v1_webhooks_disable_webhook - Disable a webhook endpoint
• v1_webhooks_ping_webhook - Queue a test ping delivery
• v1_webhooks_rotate_webhook - Rotate a webhook endpoint's signing secret
• v1_webhooks_enable_webhook - Re-enable a disabled webhook endpoint

Retries

Some of the endpoints in this SDK support retries. If you use the SDK without any configuration, it will fall back to the default retry strategy provided by the API. However, the default retry strategy can be overridden on a per-operation basis, or across the entire SDK.

To change the default retry strategy for a single API call, simply provide a RetryConfig object to the call:

from deepsieve import SDK
from deepsieve.utils import BackoffStrategy, RetryConfig


with SDK(
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.v1_meta.v1_meta_get_me(,
        RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False))

    # Handle response
    print(res)

If you'd like to override the default retry strategy for all operations that support retries, you can use the retry_config optional parameter when initializing the SDK:

from deepsieve import SDK
from deepsieve.utils import BackoffStrategy, RetryConfig


with SDK(
    retry_config=RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False),
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.v1_meta.v1_meta_get_me()

    # Handle response
    print(res)

Error Handling

SDKError is the base class for all HTTP error responses. It has the following properties:

Property	Type	Description
err.message	str	Error message
err.status_code	int	HTTP response status code eg 404
err.headers	httpx.Headers	HTTP response headers
err.body	str	HTTP body. Can be empty string if no body is returned.
err.raw_response	httpx.Response	Raw HTTP response
err.data		Optional. Some errors may contain structured data. See Error Classes.

Example

from deepsieve import SDK, errors


with SDK(
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:
    res = None
    try:

        res = sdk.v1_meta.v1_meta_get_me()

        # Handle response
        print(res)


    except errors.SDKError as e:
        # The base class for HTTP error responses
        print(e.message)
        print(e.status_code)
        print(e.body)
        print(e.headers)
        print(e.raw_response)

        # Depending on the method different errors may be thrown
        if isinstance(e, errors.V1Error):
            print(e.data.error)  # models.V1ErrorError

Error Classes

Primary errors:

• SDKError: The base class for HTTP error responses.
  • V1Error: The single error envelope for every /v1 response (and every unhandled 500 on any path). retriable is the load-bearing field — "should I try again?" is the one question an agent needs answered.

Less common errors (5)

Network errors:

• httpx.RequestError: Base class for request errors.
  • httpx.ConnectError: HTTP client was unable to make a request to a server.
  • httpx.TimeoutException: HTTP request timed out.

Inherit from SDKError:

• ResponseValidationError: Type mismatch between the response data and the expected Pydantic model. Provides access to the Pydantic validation error via the cause attribute.

Server Selection

Select Server by Index

You can override the default server globally by passing a server index to the server_idx: int optional parameter when initializing the SDK client instance. The selected server will then be used as the default on the operations that use it. This table lists the indexes associated with the available servers:

#	Server	Variables	Description
0	https://{deployment}	deployment
1	https://staging.deepsieve.ai		Staging
2	http://localhost:8200		Local development (Docker Compose)

If the selected server has variables, you may override its default values through the additional parameters made available in the SDK constructor:

Variable	Parameter	Default	Description
deployment	deployment: str	"deepsieve.ai"	Your DeepSieve deployment host — defaults to the hosted product; override it only if you self-host or use a custom domain

Example

from deepsieve import SDK


with SDK(
    server_idx=0,
    deployment="deepsieve.ai",
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.v1_meta.v1_meta_get_me()

    # Handle response
    print(res)

Override Server URL Per-Client

The default server can also be overridden globally by passing a URL to the server_url: str optional parameter when initializing the SDK client instance. For example:

from deepsieve import SDK


with SDK(
    server_url="http://localhost:8200",
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.v1_meta.v1_meta_get_me()

    # Handle response
    print(res)

Custom HTTP Client

The Python SDK makes API calls using the httpx HTTP library. In order to provide a convenient way to configure timeouts, cookies, proxies, custom headers, and other low-level configuration, you can initialize the SDK client with your own HTTP client instance. Depending on whether you are using the sync or async version of the SDK, you can pass an instance of HttpClient or AsyncHttpClient respectively, which are Protocol's ensuring that the client has the necessary methods to make API calls. This allows you to wrap the client with your own custom logic, such as adding custom headers, logging, or error handling, or you can just pass an instance of httpx.Client or httpx.AsyncClient directly.

For example, you could specify a header for every request that this sdk makes as follows:

from deepsieve import SDK
import httpx

http_client = httpx.Client(headers={"x-custom-header": "someValue"})
s = SDK(client=http_client)

or you could wrap the client with your own custom logic:

from deepsieve import SDK
from deepsieve.httpclient import AsyncHttpClient
import httpx

class CustomClient(AsyncHttpClient):
    client: AsyncHttpClient

    def __init__(self, client: AsyncHttpClient):
        self.client = client

    async def send(
        self,
        request: httpx.Request,
        *,
        stream: bool = False,
        auth: Union[
            httpx._types.AuthTypes, httpx._client.UseClientDefault, None
        ] = httpx.USE_CLIENT_DEFAULT,
        follow_redirects: Union[
            bool, httpx._client.UseClientDefault
        ] = httpx.USE_CLIENT_DEFAULT,
    ) -> httpx.Response:
        request.headers["Client-Level-Header"] = "added by client"

        return await self.client.send(
            request, stream=stream, auth=auth, follow_redirects=follow_redirects
        )

    def build_request(
        self,
        method: str,
        url: httpx._types.URLTypes,
        *,
        content: Optional[httpx._types.RequestContent] = None,
        data: Optional[httpx._types.RequestData] = None,
        files: Optional[httpx._types.RequestFiles] = None,
        json: Optional[Any] = None,
        params: Optional[httpx._types.QueryParamTypes] = None,
        headers: Optional[httpx._types.HeaderTypes] = None,
        cookies: Optional[httpx._types.CookieTypes] = None,
        timeout: Union[
            httpx._types.TimeoutTypes, httpx._client.UseClientDefault
        ] = httpx.USE_CLIENT_DEFAULT,
        extensions: Optional[httpx._types.RequestExtensions] = None,
    ) -> httpx.Request:
        return self.client.build_request(
            method,
            url,
            content=content,
            data=data,
            files=files,
            json=json,
            params=params,
            headers=headers,
            cookies=cookies,
            timeout=timeout,
            extensions=extensions,
        )

s = SDK(async_client=CustomClient(httpx.AsyncClient()))

httpx2 (Pydantic's httpx fork)

httpx2 is Pydantic's maintained fork of httpx. To run this SDK on httpx2, call alias_httpx() at your program's entry point, before importing the SDK, so every import httpx — including the ones inside the SDK — resolves to httpx2:

import httpx2

httpx2.alias_httpx()

from deepsieve import SDK

s = SDK()

An SDK can also be generated against httpx2 directly, so it depends on the fork instead of httpx, by setting python.httpClientLibrary: httpx2 in gen.yaml.

Resource Management

The SDK class implements the context manager protocol and registers a finalizer function to close the underlying sync and async HTTPX clients it uses under the hood. This will close HTTP connections, release memory and free up other resources held by the SDK. In short-lived Python programs and notebooks that make a few SDK method calls, resource management may not be a concern. However, in longer-lived programs, it is beneficial to create a single SDK instance via a context manager and reuse it across the application.

from deepsieve import SDK
def main():

    with SDK(
        bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
    ) as sdk:
        # Rest of application here...


# Or when using async:
async def amain():

    async with SDK(
        bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
    ) as sdk:
        # Rest of application here...

Debugging

You can setup your SDK to emit debug logs for SDK requests and responses.

You can pass your own logger class directly into your SDK.

from deepsieve import SDK
import logging

logging.basicConfig(level=logging.DEBUG)
s = SDK(debug_logger=logging.getLogger("deepsieve"))

Development

Maturity

This SDK is in beta, and there may be breaking changes between versions without a major version update. Therefore, we recommend pinning usage to a specific package version. This way, you can install the same version each time without breaking changes unless you are intentionally looking for the latest version.

Contributions

While we value open-source contributions to this SDK, this library is generated programmatically. Any manual changes added to internal files will be overwritten on the next generation. We look forward to hearing your feedback. Feel free to open a PR or an issue with a proof of concept and we'll do our best to include it in a future release.

SDK Created by Speakeasy