Bespoke Labs Python API library

The Bespoke Labs Python library provides convenient access to the Bespoke Labs REST API from any Python 3.8+ application. The library includes type definitions for all request params and response fields, and offers both synchronous and asynchronous clients powered by httpx.

It is generated with Stainless.

Documentation

The REST API documentation can be found on docs.bespokelabs.ai. The full API of this library can be found in api.md.

Installation

# install from PyPI
pip install bespokelabs

Usage

The full API of this library can be found in api.md.

import os
from bespokelabs import BespokeLabs

client = BespokeLabs(
    api_key=os.environ.get("BESPOKE_API_KEY"),  # This is the default and can be omitted
)

factcheck = client.minicheck.factcheck.create(
    claim="claim",
    context="context",
)
print(factcheck.support_prob)

While you can provide an api_key keyword argument, we recommend using python-dotenv to add BESPOKE_API_KEY="My API Key" to your .env file so that your API key is not stored in source control.

Nimble

Nimble is available through the same client and BESPOKE_API_KEY as MiniCheck:

from bespokelabs import BespokeLabs

with BespokeLabs() as client:
    result = client.nimble.system_one(
        state="Please refund the duplicate payment.",
        questions={
            "refund": {"type": "noul", "instructions": "Does the customer request a refund?"},
            "department": {
                "type": "choice",
                "instructions": "Which department should handle this request?",
                "criteria": {"billing": "Payments and refunds", "technical": "Software bugs"},
            },
            "urgency": {
                "type": "score",
                "instructions": "Assess operational urgency.",
                "criteria": ["Service works normally", "Partial outage", "Complete outage"],
            },
        },
    )
    print(result.nouls["refund"].noul)
    print(result.choices["department"].choice)
    print(result.scores["urgency"].score)

The default client sends POST /v1/nimble/systemone to https://api.bespokelabs.ai. For a custom deployment, set base_url or BESPOKE_LABS_BASE_URL to a gateway exposing the same route. This route differs from a standalone Nimble model server's /v1/systemone. A custom gateway without the route returns 404; one without a configured model server returns 503.

Noul returns the probability of true. Choice returns a selected option and the probability of each option. Score returns the expected zero-based rubric index: for three levels, its range is 0–2. Confidence measures distribution concentration, not calibrated correctness. There are at most 64 questions per request and 2–26 candidates per Choice or Score. The default model is nimble-latest; pass model= to select another server-supported model.

Answers are typed and available through result.answers, or through result.nouls, result.choices, and result.scores. Question types are exported from bespokelabs.types.nimble. No separate bespokelabs-nimble installation is needed.

The same resource is available on AsyncBespokeLabs:

from bespokelabs import AsyncBespokeLabs

async def check_refund():
    async with AsyncBespokeLabs() as client:
        result = await client.nimble.system_one(
            state="Please refund the duplicate payment.",
            questions={"refund": {"type": "noul", "instructions": "Refund requested?"}},
        )
        return result.nouls["refund"].noul

The standard SDK options work for Nimble, including with_options, retries, per-call timeouts, client.nimble.with_raw_response.system_one(...), and client.nimble.with_streaming_response.system_one(...). Streaming here controls HTTP body reading; it does not produce incremental model answers. Increase the request timeout for slow responses (for example, timeout=180.0). A longer timeout does not make a server wait when it immediately returns an overload or startup error such as 503 or 529; those responses use the SDK's configured retry policy.

Async usage

Simply import AsyncBespokeLabs instead of BespokeLabs and use await with each API call:

import os
import asyncio
from bespokelabs import AsyncBespokeLabs

client = AsyncBespokeLabs(
    api_key=os.environ.get("BESPOKE_API_KEY"),  # This is the default and can be omitted
)


async def main() -> None:
    factcheck = await client.minicheck.factcheck.create(
        claim="claim",
        context="context",
    )
    print(factcheck.support_prob)


asyncio.run(main())

Functionality between the synchronous and asynchronous clients is otherwise identical.

Using types

Nested request parameters are TypedDicts. Responses are Pydantic models which also provide helper methods for things like:

• Serializing back into JSON, model.to_json()
• Converting to a dictionary, model.to_dict()

Typed requests and responses provide autocomplete and documentation within your editor. If you would like to see type errors in VS Code to help catch bugs earlier, set python.analysis.typeCheckingMode to basic.

Handling errors

When the library is unable to connect to the API (for example, due to network connection problems or a timeout), a subclass of bespokelabs.APIConnectionError is raised.

When the API returns a non-success status code (that is, 4xx or 5xx response), a subclass of bespokelabs.APIStatusError is raised, containing status_code and response properties.

All errors inherit from bespokelabs.APIError.

import bespokelabs
from bespokelabs import BespokeLabs

client = BespokeLabs()

try:
    client.minicheck.factcheck.create(
        claim="claim",
        context="context",
    )
except bespokelabs.APIConnectionError as e:
    print("The server could not be reached")
    print(e.__cause__)  # an underlying Exception, likely raised within httpx.
except bespokelabs.RateLimitError as e:
    print("A 429 status code was received; we should back off a bit.")
except bespokelabs.APIStatusError as e:
    print("Another non-200-range status code was received")
    print(e.status_code)
    print(e.response)

Error codes are as followed:

Status Code	Error Type
400	BadRequestError
401	AuthenticationError
403	PermissionDeniedError
404	NotFoundError
422	UnprocessableEntityError
429	RateLimitError
>=500	InternalServerError
N/A	APIConnectionError

Retries

Certain errors are automatically retried 2 times by default, with a short exponential backoff. Connection errors (for example, due to a network connectivity problem), 408 Request Timeout, 409 Conflict, 429 Rate Limit, and >=500 Internal errors are all retried by default.

You can use the max_retries option to configure or disable retry settings:

from bespokelabs import BespokeLabs

# Configure the default for all requests:
client = BespokeLabs(
    # default is 2
    max_retries=0,
)

# Or, configure per-request:
client.with_options(max_retries=5).minicheck.factcheck.create(
    claim="claim",
    context="context",
)

Timeouts

By default requests time out after 1 minute. You can configure this with a timeout option, which accepts a float or an httpx.Timeout object:

from bespokelabs import BespokeLabs

# Configure the default for all requests:
client = BespokeLabs(
    # 20 seconds (default is 1 minute)
    timeout=20.0,
)

# More granular control:
client = BespokeLabs(
    timeout=httpx.Timeout(60.0, read=5.0, write=10.0, connect=2.0),
)

# Override per-request:
client.with_options(timeout=5.0).minicheck.factcheck.create(
    claim="claim",
    context="context",
)

On timeout, an APITimeoutError is thrown.

Note that requests that time out are retried twice by default.

Advanced

Logging

We use the standard library logging module.

You can enable logging by setting the environment variable BESPOKE_LABS_LOG to info.

$ export BESPOKE_LABS_LOG=info

Or to debug for more verbose logging.

How to tell whether None means null or missing

In an API response, a field may be explicitly null, or missing entirely; in either case, its value is None in this library. You can differentiate the two cases with .model_fields_set:

if response.my_field is None:
  if 'my_field' not in response.model_fields_set:
    print('Got json like {}, without a "my_field" key present at all.')
  else:
    print('Got json like {"my_field": null}.')

Accessing raw response data (e.g. headers)

The "raw" Response object can be accessed by prefixing .with_raw_response. to any HTTP method call, e.g.,

from bespokelabs import BespokeLabs

client = BespokeLabs()
response = client.minicheck.factcheck.with_raw_response.create(
    claim="claim",
    context="context",
)
print(response.headers.get('X-My-Header'))

factcheck = response.parse()  # get the object that `minicheck.factcheck.create()` would have returned
print(factcheck.support_prob)

These methods return an APIResponse object.

The async client returns an AsyncAPIResponse with the same structure, the only difference being awaitable methods for reading the response content.

.with_streaming_response

The above interface eagerly reads the full response body when you make the request, which may not always be what you want.

To stream the response body, use .with_streaming_response instead, which requires a context manager and only reads the response body once you call .read(), .text(), .json(), .iter_bytes(), .iter_text(), .iter_lines() or .parse(). In the async client, these are async methods.

with client.minicheck.factcheck.with_streaming_response.create(
    claim="claim",
    context="context",
) as response:
    print(response.headers.get("X-My-Header"))

    for line in response.iter_lines():
        print(line)

The context manager is required so that the response will reliably be closed.

Making custom/undocumented requests

This library is typed for convenient access to the documented API.

If you need to access undocumented endpoints, params, or response properties, the library can still be used.

Undocumented endpoints

To make requests to undocumented endpoints, you can make requests using client.get, client.post, and other http verbs. Options on the client will be respected (such as retries) will be respected when making this request.

import httpx

response = client.post(
    "/foo",
    cast_to=httpx.Response,
    body={"my_param": True},
)

print(response.headers.get("x-foo"))

Undocumented request params

If you want to explicitly send an extra param, you can do so with the extra_query, extra_body, and extra_headers request options.

Undocumented response properties

To access undocumented response properties, you can access the extra fields like response.unknown_prop. You can also get all the extra fields on the Pydantic model as a dict with response.model_extra.

Configuring the HTTP client

You can directly override the httpx client to customize it for your use case, including:

• Support for proxies
• Custom transports
• Additional advanced functionality

import httpx
from bespokelabs import BespokeLabs, DefaultHttpxClient

client = BespokeLabs(
    # Or use the `BESPOKE_LABS_BASE_URL` env var
    base_url="http://my.test.server.example.com:8083",
    http_client=DefaultHttpxClient(
        proxy="http://my.test.proxy.example.com",
        transport=httpx.HTTPTransport(local_address="0.0.0.0"),
    ),
)

You can also customize the client on a per-request basis by using with_options():

client.with_options(http_client=DefaultHttpxClient(...))

Managing HTTP resources

By default the library closes underlying HTTP connections whenever the client is garbage collected. You can manually close the client using the .close() method if desired, or with a context manager that closes when exiting.

from bespokelabs import BespokeLabs

with BespokeLabs() as client:
  # make requests here
  ...

# HTTP client is now closed

Versioning

This package generally follows SemVer conventions, though certain backwards-incompatible changes may be released as minor versions:

1. Changes that only affect static types, without breaking runtime behavior.
2. Changes to library internals which are technically public but not intended or documented for external use. (Please open a GitHub issue to let us know if you are relying on such internals.)
3. Changes that we do not expect to impact the vast majority of users in practice.

We take backwards-compatibility seriously and work hard to ensure you can rely on a smooth upgrade experience.

We are keen for your feedback; please open an issue with questions, bugs, or suggestions.

Determining the installed version

If you've upgraded to the latest version but aren't seeing any new features you were expecting then your python environment is likely still using an older version.

You can determine the version that is being used at runtime with:

import bespokelabs
print(bespokelabs.__version__)

Requirements

Python 3.8 or higher.

Contributing

See the contributing documentation.