API#

Documentation#

The REST API documentation can be found on hyperbee docs.

Installation#

pip install hyperbee

Usage#

import os
from hyperbee import Hive

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

chat_completion = client.chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": "Say this is a test",
        }
    ],
    model="hive",
)

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

Async usage#

Simply import AsyncHive instead of Hive and use await with each API call:

import os
import asyncio
from hyperbee import AsyncHive

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


async def main() -> None:
    chat_completion = await client.chat.completions.create(
        messages=[
            {
                "role": "user",
                "content": "Say this is a test",
            }
        ],
        model="hive",
    )


asyncio.run(main())

Functionality between the synchronous and asynchronous clients is otherwise identical.

Streaming Responses#

We provide support for streaming responses using Server Side Events (SSE).

from hyperbee import Hive

client = Hive()

stream = client.chat.completions.create(
    model="hive",
    messages=[{"role": "user", "content": "Say this is a test"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

The async client uses the exact same interface.

from hyperbee import AsyncHive

client = AsyncHive()


async def main():
    stream = await client.chat.completions.create(
        model="hive",
        messages=[{"role": "user", "content": "Say this is a test"}],
        stream=True,
    )
    async for chunk in stream:
        print(chunk.choices[0].delta.content or "", end="")


asyncio.run(main())

Module-level client#

[!IMPORTANT] We highly recommend instantiating client instances instead of relying on the global client.

We also expose a global client instance that is accessible in a similar fashion to versions prior to v1.

import hyperbee

# optional; defaults to `os.environ['HIVE_API_KEY']`
hyperbee.api_key = '...'

# all client options can be configured just like the `Hive` instantiation counterpart
hyperbee.base_url = "https://..."
hyperbee.default_headers = {"x-foo": "true"}

completion = hyperbee.chat.completions.create(
    model="hive",
    messages=[
        {
            "role": "user",
            "content": "How do I output all files in a directory using Python?",
        },
    ],
)
print(completion.choices[0].message.content)

The API is the exact same as the standard client instance based API.

This is intended to be used within REPLs or notebooks for faster iteration, not in application code.

We recommend that you always instantiate a client (e.g., with client = Hive()) in application code because:

  • It can be difficult to reason about where client options are configured

  • It’s not possible to change certain client options without potentially causing race conditions

  • It’s harder to mock for testing purposes

  • It’s not possible to control cleanup of network connections

Using types#

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

  • Serializing back into JSON, model.model_dump_json(indent=2, exclude_unset=True)

  • Converting to a dictionary, model.model_dump(exclude_unset=True)

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.

Nested params#

Nested parameters are dictionaries, typed using TypedDict, for example:

from hyperbee import Hive

client = Hive()

completion = client.chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": "Can you generate an example json object describing a fruit?",
        }
    ],
    model="hive",
    response_format={"type": "json_object"},
)

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 hyperbee.APIConnectionError is raised.

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

All errors inherit from hyperbee.APIError.

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 hyperbee import Hive

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

# Or, configure per-request:
client.with_options(max_retries=5).chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": "How can I get the name of the current day in Node.js?",
        }
    ],
    model="hive",
)

Timeouts#

By default requests time out after 10 minutes. You can configure this with a timeout option, which accepts a float or an `httpx.Timeout <https://www.python-httpx.org/advanced/#fine-tuning-the-configuration>`__ object:

from hyperbee import Hive

# Configure the default for all requests:
client = Hive(
    # 20 seconds (default is 10 minutes)
    timeout=20.0,
)

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

# Override per-request:
client.with_options(timeout=5 * 1000).chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": "How can I list all files in a directory using Python?",
        }
    ],
    model="hive",
)

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 <https://docs.python.org/3/library/logging.html>`__ module.

You can enable logging by setting the environment variable HIVE_LOG to debug.

$ export HIVE_LOG=debug

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 hyperbee import Hive

client = Hive()
response = client.chat.completions.with_raw_response.create(
    messages=[{
        "role": "user",
        "content": "Say this is a test",
    }],
    model="hive",
)
print(response.headers.get('X-My-Header'))

completion = response.parse()  # get the object that `chat.completions.create()` would have returned
print(completion)

These methods return an `LegacyAPIResponse <https://github.com/openai/openai-python/tree/main/src/openai/_legacy_response.py>`__ object. This is a legacy class as we’re changing it slightly in the next major version.

For the sync client this will mostly be the same with the exception of content & text will be methods instead of properties. In the async client, all methods will be async.

A migration script will be provided & the migration in general should be smooth.

.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.

As such, .with_streaming_response methods return a different `APIResponse <https://github.com/openai/openai-python/tree/main/src/openai/_response.py>`__ object, and the async client returns an `AsyncAPIResponse <https://github.com/openai/openai-python/tree/main/src/openai/_response.py>`__ object.

with client.chat.completions.with_streaming_response.create(
    messages=[
        {
            "role": "user",
            "content": "Say this is a test",
        }
    ],
    model="hive",
) 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.

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 hyperbee import Hive

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

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.

Requirements#

Python 3.7 or higher.