kilm-aiplatform 0.0.1

No project description provided

AI Platform Python API library

The AI Platform Python library provides convenient access to the AI Platform REST API from any Python 3.7+ 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.aiplatform.com. The full API of this library can be found in api.md.

Installation

# install from this staging repo
pip install git+https://zalogit2.zing.vn/nlp/kilm/libs/aiplatform-python.git

[!NOTE] Once this package is published to PyPI, this will become: pip install --pre aiplatform

Usage

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

from aiplatform import AIPlatform

client = AIPlatform()

response: ChatCompletion = client.chat.completions.create(
    model="kilm-legal-chat-analyzer-stg",
    messages=[
        {
            "role": "system",
            "content": "You are a legal traffic assistant."
        },
        {
            "role": "user",
            "content": "Đi xe đạp ngược chiều"
        }
    ]
)

print(response.model_dump_json())

Async usage

Simply import AsyncAI Platform instead of AI Platform and use await with each API call:

import asyncio

from aiplatform import AsyncAIPlatform

client = AsyncAIPlatform()


async def main() -> None:
    response: ChatCompletion = client.chat.completions.create(
        model="kilm-legal-chat-analyzer-stg",
        messages=[
            {
                "role": "system",
                "content": "You are a legal traffic assistant."
            },
            {
                "role": "user",
                "content": "Đi xe đạp ngược chiều"
            }
        ]
    )

    print(response.model_dump_json())


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 aiplatform.APIConnectionError is raised.

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

All errors inherit from aiplatform.APIError.

import aiplatform
from aiplatform import AIPlatform

client = AIPlatform()

try:
    client.chat.completions.create(
        model="kilm-legal-chat-analyzer-stg",
        messages=[
            {
                "role": "system",
                "content": "You are a legal traffic assistant."
            },
            {
                "role": "user",
                "content": "Đi xe đạp ngược chiều"
            }
        ]
    )
except aiplatform.APIConnectionError as e:
    print("The server could not be reached")
    print(e.__cause__)  # an underlying Exception, likely raised within httpx.
except aiplatform.RateLimitError as e:
    print("A 429 status code was received; we should back off a bit.")
except aiplatform.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 aiplatform import AIPlatform

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

# Or, configure per-request:
client.with_options(max_retries=5).chat.completions.create(
    model="kilm-legal-chat-analyzer-stg",
    messages=[
        {
            "role": "system",
            "content": "You are a legal traffic assistant."
        },
        {
            "role": "user",
            "content": "Đi xe đạp ngược chiều"
        }
    ]
)

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 aiplatform import AIPlatform

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

# More granular control:
client = AIPlatform(
    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(
    model="kilm-legal-chat-analyzer-stg",
    messages=[
        {
            "role": "system",
            "content": "You are a legal traffic assistant."
        },
        {
            "role": "user",
            "content": "Đi xe đạp ngược chiều"
        }
    ]
)

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 AIPLATFORM_LOG to debug.

$ export AIPLATFORM_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 aiplatform import AIPlatform

client = AIPlatform()
response = client.chat.completions.with_raw_response.create(
    model="kilm-legal-chat-analyzer-stg",
    messages=[
        {
            "role": "system",
            "content": "You are a legal traffic assistant."
        },
        {
            "role": "user",
            "content": "Đi xe đạp ngược chiều"
        }
    ]
)
print(response.headers.get('X-My-Header'))

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

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.chat.completions.with_streaming_response.create(
    model="kilm-legal-chat-analyzer-stg",
    messages=[
        {
            "role": "system",
            "content": "You are a legal traffic assistant."
        },
        {
            "role": "user",
            "content": "Đi xe đạp ngược chiều"
        }
    ]
) 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

from aiplatform import AIPlatform, DefaultHttpxClient

client = AIPlatform(
    # Or use the `AIPLATFORM_BASE_URL` env var
    base_url="http://my.test.server.example.com:8083",
    http_client=DefaultHttpxClient(
        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.

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.

Requirements

Python 3.7 or higher.