orq-ai-sdk 4.5.0rc5

Python Client SDK for the Orq API.

orq-ai-sdk

Developer-friendly & type-safe Python SDK specifically catered to leverage orq-ai-sdk API.

Summary

orq.ai API: orq.ai API documentation

For more information about the API: orq.ai Documentation

Table of Contents

• orq-ai-sdk
  • SDK Installation
  • IDE Support
  • SDK Example Usage
  • Authentication
  • Available Resources and Operations
  • Server-sent event streaming
  • File uploads
  • Retries
  • Error Handling
  • Server Selection
  • Custom HTTP Client
  • Resource Management
  • Debugging
• Development
  • Maturity
  • Contributions

SDK Installation

[!NOTE] Python version upgrade policy

Once a Python version reaches its official end of life date, a 3-month grace period is provided for users to upgrade. Following this grace period, the minimum python version supported in the SDK will be updated.

The SDK can be installed with uv, pip, or poetry package managers.

uv

uv is a fast Python package installer and resolver, designed as a drop-in replacement for pip and pip-tools. It's recommended for its speed and modern Python tooling capabilities.

uv add orq-ai-sdk

PIP

PIP is the default package installer for Python, enabling easy installation and management of packages from PyPI via the command line.

pip install orq-ai-sdk

Poetry

Poetry is a modern tool that simplifies dependency management and package publishing by using a single pyproject.toml file to handle project metadata and dependencies.

poetry add orq-ai-sdk

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 orq-ai-sdk 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 = [
#     "orq-ai-sdk",
# ]
# ///

from orq_ai_sdk import Orq

sdk = Orq(
  # 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 orq_ai_sdk import Orq
import os


with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    res = orq.contacts.create(external_id="user_12345", display_name="Jane Smith", email="[e-mail]", avatar_url="https://example.com/avatars/jane-smith.jpg", tags=[
        "premium",
        "beta-user",
        "enterprise",
    ], metadata={
        "department": "Engineering",
        "role": "Senior Developer",
        "subscription_tier": "premium",
        "last_login": "2024-01-15T10:30:00Z",
    })

    # Handle response
    print(res)

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

# Asynchronous Example
import asyncio
from orq_ai_sdk import Orq
import os

async def main():

    async with Orq(
        api_key=os.getenv("ORQ_API_KEY", ""),
    ) as orq:

        res = await orq.contacts.create_async(external_id="user_12345", display_name="Jane Smith", email="[e-mail]", avatar_url="https://example.com/avatars/jane-smith.jpg", tags=[
            "premium",
            "beta-user",
            "enterprise",
        ], metadata={
            "department": "Engineering",
            "role": "Senior Developer",
            "subscription_tier": "premium",
            "last_login": "2024-01-15T10:30:00Z",
        })

        # Handle response
        print(res)

asyncio.run(main())

Authentication

Per-Client Security Schemes

This SDK supports the following security scheme globally:

Name	Type	Scheme	Environment Variable
api_key	http	HTTP Bearer	ORQ_API_KEY

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

from orq_ai_sdk import Orq
import os


with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    res = orq.contacts.create(external_id="user_12345", display_name="Jane Smith", email="[e-mail]", avatar_url="https://example.com/avatars/jane-smith.jpg", tags=[
        "premium",
        "beta-user",
        "enterprise",
    ], metadata={
        "department": "Engineering",
        "role": "Senior Developer",
        "subscription_tier": "premium",
        "last_login": "2024-01-15T10:30:00Z",
    })

    # Handle response
    print(res)

Available Resources and Operations

Available methods

Agents

• create - Create agent
• list - List agents
• delete - Delete agent
• retrieve - Retrieve agent
• update - Update agent
• invoke - Execute an agent task :warning: Deprecated
• run - Run an agent with configuration :warning: Deprecated
• stream_run - Run agent with streaming response :warning: Deprecated
• stream - Stream agent execution in real-time :warning: Deprecated

Agents.Responses

• create - Create response

Annotations

• create - Annotate a span
• delete - Remove an annotation from a span

Chunking

• parse - Parse text

Contacts

• create - Update user information

Datasets

• list - List datasets
• create - Create a dataset
• retrieve - Retrieve a dataset
• update - Update a dataset
• delete - Delete a dataset
• list_datapoints - List datapoints
• create_datapoint - Create a datapoint
• retrieve_datapoint - Retrieve a datapoint
• update_datapoint - Update a datapoint
• delete_datapoint - Delete a datapoint
• clear - Delete all datapoints

Deployments

• invoke - Invoke
• list - List all deployments
• get_config - Get config
• stream - Stream

Deployments.Metrics

• create - Add metrics

Evals

• all - Get all Evaluators
• create - Create an Evaluator
• update - Update an Evaluator
• delete - Delete an Evaluator
• invoke - Invoke a Custom Evaluator

Evaluators

• get_v2_evaluators_id_versions - List evaluator versions

Feedback

• create - Submit feedback

Files

• create - Create file
• list - List all files
• get - Retrieve a file
• delete - Delete file

Identities

• list - List identities
• create - Create an identity
• retrieve - Retrieve an identity
• update - Update an identity
• delete - Delete an identity

Knowledge

• list - List all knowledge bases
• create - Create a knowledge
• retrieve - Retrieves a knowledge base
• update - Updates a knowledge
• delete - Deletes a knowledge
• search - Search knowledge base
• list_datasources - List all datasources
• create_datasource - Create a new datasource
• retrieve_datasource - Retrieve a datasource
• delete_datasource - Deletes a datasource
• update_datasource - Update a datasource
• create_chunks - Create chunks for a datasource
• list_chunks - List all chunks for a datasource
• delete_chunks - Delete multiple chunks
• list_chunks_paginated - List chunks with offset-based pagination
• get_chunks_count - Get chunks total count
• update_chunk - Update a chunk
• delete_chunk - Delete a chunk
• retrieve_chunk - Retrieve a chunk

MemoryStores

• list - List memory stores
• create - Create memory store
• retrieve - Retrieve memory store
• update - Update memory store
• delete - Delete memory store
• list_memories - List all memories
• create_memory - Create a new memory
• retrieve_memory - Retrieve a specific memory
• update_memory - Update a specific memory
• delete_memory - Delete a specific memory
• list_documents - List all documents for a memory
• create_document - Create a new memory document
• retrieve_document - Retrieve a specific memory document
• update_document - Update a specific memory document
• delete_document - Delete a specific memory document

Models

• list - List models

Prompts

• list - List all prompts
• create - Create a prompt
• retrieve - Retrieve a prompt
• update - Update a prompt
• delete - Delete a prompt
• list_versions - List all prompt versions
• get_version - Retrieve a prompt version

Remoteconfigs

• retrieve - Retrieve a remote config

Router

• ocr - Extracts text content while maintaining document structure and hierarchy

Router.Audio.Speech

• create - Create speech

Router.Audio.Transcriptions

• create - Create transcription

Router.Audio.Translations

• create - Create translation

Router.Chat.Completions

• create - Create chat completion

Router.Completions

• create - Create completion

Router.Embeddings

• create - Create embeddings

Router.Images.Edits

• create - Create image edit

Router.Images.Generations

• create - Create image

Router.Images.Variations

• create - Create image variation

Router.Moderations

• create - Create moderation

Router.Rerank

• create - Create rerank

Router.Responses

• create - Create response

Tools

• list - List tools
• create - Create tool
• update - Update tool
• delete - Delete tool
• retrieve - Retrieve tool
• get_v2_tools_tool_id_versions - List tool versions
• get_v2_tools_tool_id_versions_version_id_ - Get tool version

Server-sent event streaming

Server-sent events are used to stream content from certain operations. These operations will expose the stream as Generator that can be consumed using a simple for loop. The loop will terminate when the server no longer has any events to send and closes the underlying connection.

The stream is also a Context Manager and can be used with the with statement and will close the underlying connection when the context is exited.

from orq_ai_sdk import Orq
import os


with Orq(
    environment="<value>",
    contact_id="<id>",
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    res = orq.deployments.stream(key="<key>", identity={
        "id": "contact_01ARZ3NDEKTSV4RRFFQ69G5FAV",
        "display_name": "Jane Doe",
        "email": "[e-mail]",
        "metadata": [
            {
                "department": "Engineering",
                "role": "Senior Developer",
            },
        ],
        "logo_url": "https://example.com/avatars/jane-doe.jpg",
        "tags": [
            "hr",
            "engineering",
        ],
    }, documents=[
        {
            "text": "The refund policy allows customers to return items within 30 days of purchase for a full refund.",
            "metadata": {
                "file_name": "refund_policy.pdf",
                "file_type": "application/pdf",
                "page_number": 1,
            },
        },
        {
            "text": "Premium members receive free shipping on all orders over $50.",
            "metadata": {
                "file_name": "membership_benefits.md",
                "file_type": "text/markdown",
            },
        },
    ])

    with res as event_stream:
        for event in event_stream:
            # handle event
            print(event, flush=True)

File uploads

Certain SDK methods accept file objects as part of a request body or multi-part request. It is possible and typically recommended to upload files as a stream rather than reading the entire contents into memory. This avoids excessive memory consumption and potentially crashing with out-of-memory errors when working with very large files. The following example demonstrates how to attach a file stream to a request.

[!TIP]

For endpoints that handle file uploads bytes arrays can also be used. However, using streams is recommended for large files.

from orq_ai_sdk import Orq
import os


with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    res = orq.files.create(file={
        "file_name": "example.file",
        "content": open("example.file", "rb"),
    }, purpose="retrieval")

    # Handle response
    print(res)

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 orq_ai_sdk import Orq
from orq_ai_sdk.utils import BackoffStrategy, RetryConfig
import os


with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    res = orq.contacts.create(external_id="user_12345", display_name="Jane Smith", email="[e-mail]", avatar_url="https://example.com/avatars/jane-smith.jpg", tags=[
        "premium",
        "beta-user",
        "enterprise",
    ], metadata={
        "department": "Engineering",
        "role": "Senior Developer",
        "subscription_tier": "premium",
        "last_login": "2024-01-15T10:30:00Z",
    },
        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 orq_ai_sdk import Orq
from orq_ai_sdk.utils import BackoffStrategy, RetryConfig
import os


with Orq(
    retry_config=RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False),
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    res = orq.contacts.create(external_id="user_12345", display_name="Jane Smith", email="[e-mail]", avatar_url="https://example.com/avatars/jane-smith.jpg", tags=[
        "premium",
        "beta-user",
        "enterprise",
    ], metadata={
        "department": "Engineering",
        "role": "Senior Developer",
        "subscription_tier": "premium",
        "last_login": "2024-01-15T10:30:00Z",
    })

    # Handle response
    print(res)

Error Handling

OrqError 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 orq_ai_sdk import Orq, models
import os


with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:
    res = None
    try:

        res = orq.evals.all(limit=10)

        # Handle response
        print(res)


    except models.OrqError 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, models.GetEvalsEvalsResponseBody):
            print(e.data.message)  # str

Error Classes

Primary error:

• OrqError: The base class for HTTP error responses.

Less common errors (31)

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 OrqError:

• HonoAPIError: Applicable to 9 of 109 methods.*
• InvokeEvalEvalsResponseBody: Bad request. Status code 400. Applicable to 1 of 109 methods.*
• GetEvalsEvalsResponseBody: Workspace ID is not found on the request. Status code 404. Applicable to 1 of 109 methods.*
• CreateEvalEvalsResponseBody: Workspace ID is not found on the request. Status code 404. Applicable to 1 of 109 methods.*
• UpdateEvalEvalsResponseBody: Workspace ID is not found on the request. Status code 404. Applicable to 1 of 109 methods.*
• DeleteEvalResponseBody: Workspace ID is not found on the request. Status code 404. Applicable to 1 of 109 methods.*
• InvokeEvalEvalsResponseResponseBody: Workspace ID is not found on the request. Status code 404. Applicable to 1 of 109 methods.*
• GetV2EvaluatorsIDVersionsEvaluatorsResponseBody: Evaluator not found. Status code 404. Applicable to 1 of 109 methods.*
• RetrieveIdentityIdentitiesResponseBody: Identity not found. Status code 404. Applicable to 1 of 109 methods.*
• UpdateIdentityIdentitiesResponseBody: Identity not found. Status code 404. Applicable to 1 of 109 methods.*
• DeleteIdentityResponseBody: Identity not found. Status code 404. Applicable to 1 of 109 methods.*
• DeleteAgentResponseBody: Agent not found. The specified agent key does not exist in the workspace or has already been deleted. Status code 404. Applicable to 1 of 109 methods.*
• RetrieveAgentRequestAgentsResponseBody: Agent not found. The specified agent key does not exist in the workspace or you do not have permission to access it. Status code 404. Applicable to 1 of 109 methods.*
• UpdateAgentAgentsResponseBody: Agent not found. The specified agent key does not exist in the workspace or you do not have permission to modify it. Status code 404. Applicable to 1 of 109 methods.*
• StreamRunAgentAgentsResponseBody: Model not found. Status code 404. Applicable to 1 of 109 methods.*
• StreamAgentAgentsResponseBody: Agent not found. Status code 404. Applicable to 1 of 109 methods.*
• UpdatePromptResponseBody: Prompt not found. Status code 404. Applicable to 1 of 109 methods.*
• DeletePromptResponseBody: Prompt not found. Status code 404. Applicable to 1 of 109 methods.*
• GetPromptVersionPromptsResponseBody: Not Found - The prompt or prompt version does not exist. Status code 404. Applicable to 1 of 109 methods.*
• UpdateToolToolsResponseBody: Tool not found. Status code 404. Applicable to 1 of 109 methods.*
• GetV2ToolsToolIDVersionsToolsResponseBody: Tool not found. Status code 404. Applicable to 1 of 109 methods.*
• GetV2ToolsToolIDVersionsVersionIDToolsResponseBody: Tool or version not found. Status code 404. Applicable to 1 of 109 methods.*
• CreateModerationRouterModerationsResponseBody: Returns validation error. Status code 422. Applicable to 1 of 109 methods.*
• CreateTranscriptionRouterAudioTranscriptionsResponseBody: Returns validation error. Status code 422. Applicable to 1 of 109 methods.*
• CreateTranslationRouterAudioTranslationsResponseBody: Returns validation error. Status code 422. Applicable to 1 of 109 methods.*
• InvokeEvalEvalsResponse500ResponseBody: Error running the evaluator. Status code 500. Applicable to 1 of 109 methods.*
• ResponseValidationError: Type mismatch between the response data and the expected Pydantic model. Provides access to the Pydantic validation error via the cause attribute.

* Check the method documentation to see if the error is applicable.

Server Selection

Override Server URL Per-Client

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

from orq_ai_sdk import Orq
import os


with Orq(
    server_url="https://my.orq.ai",
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    res = orq.contacts.create(external_id="user_12345", display_name="Jane Smith", email="[e-mail]", avatar_url="https://example.com/avatars/jane-smith.jpg", tags=[
        "premium",
        "beta-user",
        "enterprise",
    ], metadata={
        "department": "Engineering",
        "role": "Senior Developer",
        "subscription_tier": "premium",
        "last_login": "2024-01-15T10:30:00Z",
    })

    # 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 orq_ai_sdk import Orq
import httpx

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

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

from orq_ai_sdk import Orq
from orq_ai_sdk.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 = Orq(async_client=CustomClient(httpx.AsyncClient()))

Resource Management

The Orq 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 orq_ai_sdk import Orq
import os
def main():

    with Orq(
        api_key=os.getenv("ORQ_API_KEY", ""),
    ) as orq:
        # Rest of application here...


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

    async with Orq(
        api_key=os.getenv("ORQ_API_KEY", ""),
    ) as orq:
        # 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 orq_ai_sdk import Orq
import logging

logging.basicConfig(level=logging.DEBUG)
s = Orq(debug_logger=logging.getLogger("orq_ai_sdk"))

You can also enable a default debug logger by setting an environment variable ORQ_DEBUG to true.

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