| Name | opperai JSON |
| Version |
1.3.0
JSON |
| download |
| home_page | None |
| Summary | Python Client SDK Generated by Speakeasy. |
| upload_time | 2025-10-08 07:49:43 |
| maintainer | None |
| docs_url | None |
| author | Speakeasy |
| requires_python | >=3.9.2 |
| license | None |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# opperai
<div align="left">
<a href="https://www.speakeasy.com/?utm_source=opperai&utm_campaign=python"><img src="https://custom-icon-badges.demolab.com/badge/-Built%20By%20Speakeasy-212015?style=for-the-badge&logoColor=FBE331&logo=speakeasy&labelColor=545454" /></a>
<a href="https://opensource.org/licenses/MIT">
<img src="https://img.shields.io/badge/License-MIT-blue.svg" style="width: 100px; height: 28px;" />
</a>
</div>
<!-- Start Summary [summary] -->
## Summary
[](https://opper.ai/)
Welcome to the OpperAI python SDK
Opper is a task completion platform for building reliable AI integrations. The Opper platform builds a happy path for declarative programming with AI models, combined with in context reinforcement learning, observability and cost tracking all in one platform - for reliable results in no time!
This SDK is generated using Speakeasy, read our detailed docs with many guides and examples at
[](https://docs.opper.ai)
<!-- End Summary [summary] -->
<!-- Start Table of Contents [toc] -->
## Table of Contents
<!-- $toc-max-depth=2 -->
- [opperai](#opperai)
- [Summary](#summary)
- [Table of Contents](#table-of-contents)
- [SDK Installation](#sdk-installation)
- [PIP](#pip)
- [Poetry / UV](#poetry--uv)
- [SDK Example Usage](#sdk-example-usage)
- [First steps](#first-steps)
- [Example](#example)
- [Authentication](#authentication)
- [Available Resources and Operations](#available-resources-and-operations)
- [analytics](#analytics)
- [datasets](#datasets)
- [datasets.entries](#datasetsentries)
- [embeddings](#embeddings)
- [functions](#functions)
- [functions.revisions](#functionsrevisions)
- [knowledge](#knowledge)
- [language\_models](#language_models)
- [Opper SDK](#opper-sdk)
- [span\_metrics](#span_metrics)
- [spans](#spans)
- [traces](#traces)
- [Server-sent event streaming](#server-sent-event-streaming)
- [Retries](#retries)
- [Error Handling](#error-handling)
- [Example](#example-1)
- [Custom HTTP Client](#custom-http-client)
- [Resource Management](#resource-management)
- [Debugging](#debugging)
- [Development](#development)
- [Maturity](#maturity)
- [Contributions](#contributions)
- [SDK Created by Speakeasy](#sdk-created-by-speakeasy)
<!-- End Table of Contents [toc] -->
<!-- Start SDK Installation [installation] -->
## SDK Installation
### PIP
*PIP* is the default package installer for Python, enabling easy installation and management of packages from PyPI via the command line.
```bash
pip install opperai
```
### Poetry / UV
If you use [UV](https://docs.astral.sh/uv/)
```bash
uv add opperai
```
Poetry
```bash
poetry add opperai
```
## SDK Example Usage
[](https://docs.opper.ai)
### First steps
Log in at [opper](platform.opper.ai) and create your own API key in the top right menu. Each api key is associated with a project, you will have all calls, functions, indexes and traces associated with this project. There is a default project for each organization but it is recommended to create a new project to better being able to separate the different applications and environments.
For many **examples** and **guides** of how to use our sdks check out our examples folder [examples](./examples/)
### Example
```python
from opperai import Opper
# Our SDK supports Pydantic to provide structured output
from pydantic import BaseModel
import os
# Define the output structure
class RoomDescription(BaseModel):
room_count: int
view: str
bed_size: str
hotel_name: str
def main():
opper = Opper(http_bearer=os.getenv("OPPER_API_KEY"))
# Complete a task
completion = opper.call(
name="extractRoom",
instructions="Extract details about the room from the provided text",
input="The Grand Hotel offers a luxurious suite with 3 spacious rooms, each providing a breathtaking view of the ocean. The suite includes a king-sized bed, an en-suite bathroom, and a private balcony for an unforgettable stay.",
output_schema=RoomDescription,
)
print(completion.json_payload)
#{'room_count': 3, 'view': 'ocean', 'bed_size': 'king-sized', 'hotel_name': 'The Grand Hotel'}
main()
```
</br>
The same SDK client can also be used to make asychronous requests by importing asyncio. Just add `_async` to the call
<details closed>
<summary>Async example</summary>
```python
# Asynchronous Example
import asyncio
import os
from opperai import Opper
from pydantic import BaseModel
# Define the output structure
class RoomDescription(BaseModel):
room_count: int
view: str
bed_size: str
hotel_name: str
async def main():
opper = Opper(http_bearer=os.getenv("OPPER_API_KEY"))
# Complete a task asynchronously
completion = await opper.call_async(
name="extractRoom",
instructions="Extract details about the room from the provided text",
input="The Grand Hotel offers a luxurious suite with 3 spacious rooms, each providing a breathtaking view of the ocean. The suite includes a king-sized bed, an en-suite bathroom, and a private balcony for an unforgettable stay.",
output_schema=RoomDescription,
)
print(completion.json_payload)
# {'room_count': 3, 'view': 'ocean', 'bed_size': 'king-sized', 'hotel_name': 'The Grand Hotel'}
# Run the async main function
asyncio.run(main())
```
</details>
<!-- End SDK Example Usage [usage] -->
<!-- Start Authentication [security] -->
## Authentication
See our authenthication docs [auth](https://docs.opper.ai/api-reference/authentication)
This SDK supports the following security scheme globally:
| Name | Type | Scheme | Environment Variable |
| ------------- | ---- | ----------- | -------------------- |
| `http_bearer` | http | HTTP Bearer | `OPPER_HTTP_BEARER` |
To authenticate with the API the `http_bearer` parameter must be set when initializing the SDK client instance. For example:
```python
from opperai import Opper
import os
http_bearer="YOUR_API_KEY"
opper = Opper(http_bearer)
```
<!-- End Authentication [security] -->
<!-- Start Available Resources and Operations [operations] -->
## Available Resources and Operations
<details open>
<summary>Available methods</summary>
### [analytics](docs/sdks/analytics/README.md)
* [get_usage](docs/sdks/analytics/README.md#get_usage) - Usage
### [datasets](docs/sdks/datasets/README.md)
* [create_entry](docs/sdks/datasets/README.md#create_entry) - Create Dataset Entry
* [list_entries](docs/sdks/datasets/README.md#list_entries) - List Dataset Entries
* [get_entry](docs/sdks/datasets/README.md#get_entry) - Get Dataset Entry
* [delete_entry](docs/sdks/datasets/README.md#delete_entry) - Delete Dataset Entry
* [query_entries](docs/sdks/datasets/README.md#query_entries) - Query Dataset Entries
#### [datasets.entries](docs/sdks/entries/README.md)
* [update](docs/sdks/entries/README.md#update) - Update Dataset Entry
### [embeddings](docs/sdks/embeddings/README.md)
* [create](docs/sdks/embeddings/README.md#create) - Create Embedding
### [functions](docs/sdks/functions/README.md)
* [create](docs/sdks/functions/README.md#create) - Create Function
* [list](docs/sdks/functions/README.md#list) - List Functions
* [get](docs/sdks/functions/README.md#get) - Get Function
* [update](docs/sdks/functions/README.md#update) - Update Function
* [delete](docs/sdks/functions/README.md#delete) - Delete Function
* [get_by_name](docs/sdks/functions/README.md#get_by_name) - Get Function By Name
* [get_by_revision](docs/sdks/functions/README.md#get_by_revision) - Get Function By Revision
* [call](docs/sdks/functions/README.md#call) - Call Function
* [stream](docs/sdks/functions/README.md#stream) - Stream Function
* [call_revision](docs/sdks/functions/README.md#call_revision) - Call Function Revision
* [stream_revision](docs/sdks/functions/README.md#stream_revision) - Stream Function Revision
#### [functions.revisions](docs/sdks/revisions/README.md)
* [list](docs/sdks/revisions/README.md#list) - List Function Revisions
### [knowledge](docs/sdks/knowledge/README.md)
* [create](docs/sdks/knowledge/README.md#create) - Create Knowledge Base
* [list](docs/sdks/knowledge/README.md#list) - List Knowledge Bases
* [get](docs/sdks/knowledge/README.md#get) - Get Knowledge Base
* [delete](docs/sdks/knowledge/README.md#delete) - Delete Knowledge Base
* [get_by_name](docs/sdks/knowledge/README.md#get_by_name) - Get Knowledge Base By Name
* [get_upload_url](docs/sdks/knowledge/README.md#get_upload_url) - Get Upload Url
* [register_file_upload](docs/sdks/knowledge/README.md#register_file_upload) - Register File Upload
* [delete_file](docs/sdks/knowledge/README.md#delete_file) - Delete File From Knowledge Base
* [query](docs/sdks/knowledge/README.md#query) - Query Knowledge Base
* [add](docs/sdks/knowledge/README.md#add) - Add
### [language_models](docs/sdks/languagemodels/README.md)
* [list](docs/sdks/languagemodels/README.md#list) - List Models
* [register_custom](docs/sdks/languagemodels/README.md#register_custom) - Register Custom Model
* [list_custom](docs/sdks/languagemodels/README.md#list_custom) - List Custom Models
* [get_custom](docs/sdks/languagemodels/README.md#get_custom) - Get Custom Model
* [update_custom](docs/sdks/languagemodels/README.md#update_custom) - Update Custom Model
* [delete_custom](docs/sdks/languagemodels/README.md#delete_custom) - Delete Custom Model
* [get_custom_by_name](docs/sdks/languagemodels/README.md#get_custom_by_name) - Get Custom Model By Name
### [Opper SDK](docs/sdks/opper/README.md)
* [call](docs/sdks/opper/README.md#call) - Function Call
* [stream](docs/sdks/opper/README.md#stream) - Function Stream
### [span_metrics](docs/sdks/spanmetrics/README.md)
* [create_metric](docs/sdks/spanmetrics/README.md#create_metric) - Create Metric
* [list](docs/sdks/spanmetrics/README.md#list) - List Metrics
* [get](docs/sdks/spanmetrics/README.md#get) - Get Metric
* [update_metric](docs/sdks/spanmetrics/README.md#update_metric) - Update Metric
* [delete](docs/sdks/spanmetrics/README.md#delete) - Delete Metric
### [spans](docs/sdks/spans/README.md)
* [create](docs/sdks/spans/README.md#create) - Create Span
* [get](docs/sdks/spans/README.md#get) - Get Span
* [update](docs/sdks/spans/README.md#update) - Update Span
* [delete](docs/sdks/spans/README.md#delete) - Delete Span
* [save_examples](docs/sdks/spans/README.md#save_examples) - Save To Dataset
### [traces](docs/sdks/traces/README.md)
* [list](docs/sdks/traces/README.md#list) - List Traces
* [get](docs/sdks/traces/README.md#get) - Get Trace
</details>
<!-- End Available Resources and Operations [operations] -->
<!-- Start Server-sent event streaming [eventstream] -->
## Server-sent event streaming
[Server-sent events][mdn-sse] are used to stream content from certain
operations. These operations will expose the stream as [Generator][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.
```python
from opperai import Opper
import os
opper = Opper(http_bearer=os.getenv("OPPER_API_KEY"))
def stream_call():
"""Print the assistant’s answer as it streams back from Opper."""
outer = opper.stream(
name="python/sdk/bare-minimum-with-stream",
instructions="answer the following question",
input="what are some uses of 42",
)
# Pull out the inner EventStream object in one line.
stream = next(value for key, value in outer if key == "result")
# Read each Server-Sent Event and emit the delta text.
for event in stream: # event: ServerSentEvent
delta = getattr(event.data, "delta", None)
if delta: # skip keep-alives, etc.
print(delta, end="", flush=True)
```
The stream is also a [Context Manager][context-manager] and can be used with the `with` statement and will close the underlying connection when the context is exited.
<details closed>
<summary> Context Manager Stream Example</summary>
```python
from opperai import Opper
import os
with Opper(
http_bearer=os.getenv("OPPER_HTTP_BEARER", ""),
) as opper:
res = opper.stream(name="add_numbers", instructions="Calculate the sum of two numbers", input_schema={
"properties": {
"x": {
"title": "X",
"type": "integer",
},
"y": {
"title": "Y",
"type": "integer",
},
},
"required": [
"x",
"y",
],
"title": "OpperInputExample",
"type": "object",
}, output_schema={
"properties": {
"sum": {
"title": "Sum",
"type": "integer",
},
},
"required": [
"sum",
],
"title": "OpperOutputExample",
"type": "object",
}, input={
"x": 4,
"y": 5,
}, examples=[
{
"input": {
"x": 1,
"y": 3,
},
"output": {
"sum": 4,
},
"comment": "Adds two numbers",
},
], parent_span_id="123e4567-e89b-12d3-a456-426614174000", tags={
"project": "project_456",
"user": "company_123",
}, configuration={})
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
```
[mdn-sse]: https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events
[generator]: https://book.pythontips.com/en/latest/generators.html
[context-manager]: https://book.pythontips.com/en/latest/context_managers.html
</details>
<!-- End Server-sent event streaming [eventstream] -->
<!-- Start Retries [retries] -->
## 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:
```python
from opperai import Opper
from opperai.utils import BackoffStrategy, RetryConfig
import os
with Opper(
http_bearer=os.getenv("OPPER_HTTP_BEARER", ""),
) as opper:
res = opper.call(name="add_numbers", instructions="Calculate the sum of two numbers", input_schema={
"properties": {
"x": {
"title": "X",
"type": "integer",
},
"y": {
"title": "Y",
"type": "integer",
},
},
"required": [
"x",
"y",
],
"title": "OpperInputExample",
"type": "object",
}, output_schema={
"properties": {
"sum": {
"title": "Sum",
"type": "integer",
},
},
"required": [
"sum",
],
"title": "OpperOutputExample",
"type": "object",
}, input={
"x": 4,
"y": 5,
}, examples=[
{
"input": {
"x": 1,
"y": 3,
},
"output": {
"sum": 4,
},
"comment": "Adds two numbers",
},
], parent_span_id="123e4567-e89b-12d3-a456-426614174000", tags={
"project": "project_456",
"user": "company_123",
}, configuration={},
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:
```python
from opperai import Opper
from opperai.utils import BackoffStrategy, RetryConfig
import os
with Opper(
retry_config=RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False),
http_bearer=os.getenv("OPPER_HTTP_BEARER", ""),
) as opper:
res = opper.call(name="add_numbers", instructions="Calculate the sum of two numbers", input_schema={
"properties": {
"x": {
"title": "X",
"type": "integer",
},
"y": {
"title": "Y",
"type": "integer",
},
},
"required": [
"x",
"y",
],
"title": "OpperInputExample",
"type": "object",
}, output_schema={
"properties": {
"sum": {
"title": "Sum",
"type": "integer",
},
},
"required": [
"sum",
],
"title": "OpperOutputExample",
"type": "object",
}, input={
"x": 4,
"y": 5,
}, examples=[
{
"input": {
"x": 1,
"y": 3,
},
"output": {
"sum": 4,
},
"comment": "Adds two numbers",
},
], parent_span_id="123e4567-e89b-12d3-a456-426614174000", tags={
"project": "project_456",
"user": "company_123",
}, configuration={})
# Handle response
print(res)
```
<!-- End Retries [retries] -->
<!-- Start Error Handling [errors] -->
## Error Handling
Check our detailed [error handling](https://docs.opper.ai/api-reference/errors)
Handling errors in this SDK should largely match your expectations. All operations return a response object or raise an exception.
By default, an API error will raise a errors.APIError exception, which has the following properties:
| Property | Type | Description |
|-----------------|------------------|-----------------------|
| `.status_code` | *int* | The HTTP status code |
| `.message` | *str* | The error message |
| `.raw_response` | *httpx.Response* | The raw HTTP response |
| `.body` | *str* | The response content |
When custom error responses are specified for an operation, the SDK may also raise their associated exceptions. You can refer to respective *Errors* tables in SDK docs for more details on possible exception types for each operation. For example, the `call_async` method may raise the following exceptions:
| Error Type | Status Code | Content Type |
| ----------------------------- | ----------- | ---------------- |
| errors.BadRequestError | 400 | application/json |
| errors.UnauthorizedError | 401 | application/json |
| errors.NotFoundError | 404 | application/json |
| errors.RequestValidationError | 422 | application/json |
| errors.APIError | 4XX, 5XX | \*/\* |
### Example
```python
from opperai import Opper, errors
import os
with Opper(
http_bearer=os.getenv("OPPER_HTTP_BEARER", ""),
) as opper:
res = None
try:
res = opper.call(name="add_numbers", instructions="Calculate the sum of two numbers", input_schema={
"properties": {
"x": {
"title": "X",
"type": "integer",
},
"y": {
"title": "Y",
"type": "integer",
},
},
"required": [
"x",
"y",
],
"title": "OpperInputExample",
"type": "object",
}, output_schema={
"properties": {
"sum": {
"title": "Sum",
"type": "integer",
},
},
"required": [
"sum",
],
"title": "OpperOutputExample",
"type": "object",
}, input={
"x": 4,
"y": 5,
}, examples=[
{
"input": {
"x": 1,
"y": 3,
},
"output": {
"sum": 4,
},
"comment": "Adds two numbers",
},
], parent_span_id="123e4567-e89b-12d3-a456-426614174000", tags={
"project": "project_456",
"user": "company_123",
}, configuration={})
# Handle response
print(res)
except errors.BadRequestError as e:
# handle e.data: errors.BadRequestErrorData
raise(e)
except errors.UnauthorizedError as e:
# handle e.data: errors.UnauthorizedErrorData
raise(e)
except errors.NotFoundError as e:
# handle e.data: errors.NotFoundErrorData
raise(e)
except errors.RequestValidationError as e:
# handle e.data: errors.RequestValidationErrorData
raise(e)
except errors.APIError as e:
# handle exception
raise(e)
```
<!-- End Error Handling [errors] -->
## Custom HTTP Client
The Python SDK makes API calls using the [httpx](https://www.python-httpx.org/) 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:
```python
from opperai import Opper
import httpx
http_client = httpx.Client(headers={"x-custom-header": "someValue"})
s = Opper(client=http_client)
```
or you could wrap the client with your own custom logic:
```python
from opperai import Opper
from opperai.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 = Opper(async_client=CustomClient(httpx.AsyncClient()))
```
<!-- End Custom HTTP Client [http-client] -->
<!-- Start Resource Management [resource-management] -->
## Resource Management
The `Opper` 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][context-manager] and reuse it across the application.
[context-manager]: https://docs.python.org/3/reference/datamodel.html#context-managers
```python
from opperai import Opper
import os
def main():
with Opper(
http_bearer=os.getenv("OPPER_HTTP_BEARER", ""),
) as opper:
# Rest of application here...
# Or when using async:
async def amain():
async with Opper(
http_bearer=os.getenv("OPPER_HTTP_BEARER", ""),
) as opper:
# Rest of application here...
```
<!-- End Resource Management [resource-management] -->
<!-- Start Debugging [debug] -->
## 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.
```python
from opperai import Opper
import logging
logging.basicConfig(level=logging.DEBUG)
s = Opper(debug_logger=logging.getLogger("opperai"))
```
You can also enable a default debug logger by setting an environment variable `OPPER_DEBUG` to true.
<!-- End Debugging [debug] -->
<!-- Placeholder for Future Speakeasy SDK Sections -->
# 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](https://www.speakeasy.com/?utm_source=opperai&utm_campaign=python)
Raw data
{
"_id": null,
"home_page": null,
"name": "opperai",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9.2",
"maintainer_email": null,
"keywords": null,
"author": "Speakeasy",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/e0/97/56093572ef2c911560beeb66991ed0cb6dba82f330f0fd815da05c00f887/opperai-1.3.0.tar.gz",
"platform": null,
"description": "# opperai\n\n\n\n<div align=\"left\">\n <a href=\"https://www.speakeasy.com/?utm_source=opperai&utm_campaign=python\"><img src=\"https://custom-icon-badges.demolab.com/badge/-Built%20By%20Speakeasy-212015?style=for-the-badge&logoColor=FBE331&logo=speakeasy&labelColor=545454\" /></a>\n <a href=\"https://opensource.org/licenses/MIT\">\n <img src=\"https://img.shields.io/badge/License-MIT-blue.svg\" style=\"width: 100px; height: 28px;\" />\n </a>\n</div>\n\n\n<!-- Start Summary [summary] -->\n## Summary\n[](https://opper.ai/)\n\nWelcome to the OpperAI python SDK\n\n\n\nOpper is a task completion platform for building reliable AI integrations. The Opper platform builds a happy path for declarative programming with AI models, combined with in context reinforcement learning, observability and cost tracking all in one platform - for reliable results in no time!\n\nThis SDK is generated using Speakeasy, read our detailed docs with many guides and examples at \n[](https://docs.opper.ai)\n\n<!-- End Summary [summary] -->\n\n<!-- Start Table of Contents [toc] -->\n## Table of Contents\n<!-- $toc-max-depth=2 -->\n- [opperai](#opperai)\n - [Summary](#summary)\n - [Table of Contents](#table-of-contents)\n - [SDK Installation](#sdk-installation)\n - [PIP](#pip)\n - [Poetry / UV](#poetry--uv)\n - [SDK Example Usage](#sdk-example-usage)\n - [First steps](#first-steps)\n - [Example](#example)\n - [Authentication](#authentication)\n - [Available Resources and Operations](#available-resources-and-operations)\n - [analytics](#analytics)\n - [datasets](#datasets)\n - [datasets.entries](#datasetsentries)\n - [embeddings](#embeddings)\n - [functions](#functions)\n - [functions.revisions](#functionsrevisions)\n - [knowledge](#knowledge)\n - [language\\_models](#language_models)\n - [Opper SDK](#opper-sdk)\n - [span\\_metrics](#span_metrics)\n - [spans](#spans)\n - [traces](#traces)\n - [Server-sent event streaming](#server-sent-event-streaming)\n - [Retries](#retries)\n - [Error Handling](#error-handling)\n - [Example](#example-1)\n - [Custom HTTP Client](#custom-http-client)\n - [Resource Management](#resource-management)\n - [Debugging](#debugging)\n- [Development](#development)\n - [Maturity](#maturity)\n - [Contributions](#contributions)\n - [SDK Created by Speakeasy](#sdk-created-by-speakeasy)\n\n<!-- End Table of Contents [toc] -->\n\n<!-- Start SDK Installation [installation] -->\n## SDK Installation\n\n\n### PIP\n\n*PIP* is the default package installer for Python, enabling easy installation and management of packages from PyPI via the command line.\n\n```bash\npip install opperai\n```\n\n### Poetry / UV\n\nIf you use [UV](https://docs.astral.sh/uv/)\n\n```bash\nuv add opperai\n```\n\n\nPoetry\n\n```bash\npoetry add opperai\n```\n\n\n\n\n## SDK Example Usage\n[](https://docs.opper.ai)\n\n### First steps\nLog in at [opper](platform.opper.ai) and create your own API key in the top right menu. Each api key is associated with a project, you will have all calls, functions, indexes and traces associated with this project. There is a default project for each organization but it is recommended to create a new project to better being able to separate the different applications and environments.\n\n\nFor many **examples** and **guides** of how to use our sdks check out our examples folder [examples](./examples/)\n\n### Example\n\n```python\nfrom opperai import Opper\n# Our SDK supports Pydantic to provide structured output\nfrom pydantic import BaseModel\nimport os\n\n# Define the output structure\nclass RoomDescription(BaseModel):\n room_count: int\n view: str\n bed_size: str\n hotel_name: str\n\ndef main():\n opper = Opper(http_bearer=os.getenv(\"OPPER_API_KEY\"))\n\n # Complete a task\n completion = opper.call(\n name=\"extractRoom\",\n instructions=\"Extract details about the room from the provided text\",\n input=\"The Grand Hotel offers a luxurious suite with 3 spacious rooms, each providing a breathtaking view of the ocean. The suite includes a king-sized bed, an en-suite bathroom, and a private balcony for an unforgettable stay.\",\n output_schema=RoomDescription,\n )\n\n print(completion.json_payload)\n #{'room_count': 3, 'view': 'ocean', 'bed_size': 'king-sized', 'hotel_name': 'The Grand Hotel'}\n\nmain()\n```\n</br>\n\nThe same SDK client can also be used to make asychronous requests by importing asyncio. Just add `_async` to the call\n<details closed>\n<summary>Async example</summary>\n\n```python\n# Asynchronous Example\nimport asyncio\nimport os\nfrom opperai import Opper\nfrom pydantic import BaseModel\n\n# Define the output structure\nclass RoomDescription(BaseModel):\n room_count: int\n view: str\n bed_size: str\n hotel_name: str\n\nasync def main():\n opper = Opper(http_bearer=os.getenv(\"OPPER_API_KEY\"))\n\n # Complete a task asynchronously\n completion = await opper.call_async(\n name=\"extractRoom\",\n instructions=\"Extract details about the room from the provided text\",\n input=\"The Grand Hotel offers a luxurious suite with 3 spacious rooms, each providing a breathtaking view of the ocean. The suite includes a king-sized bed, an en-suite bathroom, and a private balcony for an unforgettable stay.\",\n output_schema=RoomDescription,\n )\n\n print(completion.json_payload)\n # {'room_count': 3, 'view': 'ocean', 'bed_size': 'king-sized', 'hotel_name': 'The Grand Hotel'}\n\n# Run the async main function\nasyncio.run(main())\n```\n</details>\n<!-- End SDK Example Usage [usage] -->\n\n<!-- Start Authentication [security] -->\n## Authentication\n\nSee our authenthication docs [auth](https://docs.opper.ai/api-reference/authentication)\n\nThis SDK supports the following security scheme globally:\n\n| Name | Type | Scheme | Environment Variable |\n| ------------- | ---- | ----------- | -------------------- |\n| `http_bearer` | http | HTTP Bearer | `OPPER_HTTP_BEARER` |\n\nTo authenticate with the API the `http_bearer` parameter must be set when initializing the SDK client instance. For example:\n```python\nfrom opperai import Opper\nimport os\n\nhttp_bearer=\"YOUR_API_KEY\"\nopper = Opper(http_bearer)\n\n```\n<!-- End Authentication [security] -->\n\n<!-- Start Available Resources and Operations [operations] -->\n## Available Resources and Operations\n\n<details open>\n<summary>Available methods</summary>\n\n### [analytics](docs/sdks/analytics/README.md)\n\n* [get_usage](docs/sdks/analytics/README.md#get_usage) - Usage\n\n### [datasets](docs/sdks/datasets/README.md)\n\n* [create_entry](docs/sdks/datasets/README.md#create_entry) - Create Dataset Entry\n* [list_entries](docs/sdks/datasets/README.md#list_entries) - List Dataset Entries\n* [get_entry](docs/sdks/datasets/README.md#get_entry) - Get Dataset Entry\n* [delete_entry](docs/sdks/datasets/README.md#delete_entry) - Delete Dataset Entry\n* [query_entries](docs/sdks/datasets/README.md#query_entries) - Query Dataset Entries\n\n#### [datasets.entries](docs/sdks/entries/README.md)\n\n* [update](docs/sdks/entries/README.md#update) - Update Dataset Entry\n\n### [embeddings](docs/sdks/embeddings/README.md)\n\n* [create](docs/sdks/embeddings/README.md#create) - Create Embedding\n\n### [functions](docs/sdks/functions/README.md)\n\n* [create](docs/sdks/functions/README.md#create) - Create Function\n* [list](docs/sdks/functions/README.md#list) - List Functions\n* [get](docs/sdks/functions/README.md#get) - Get Function\n* [update](docs/sdks/functions/README.md#update) - Update Function\n* [delete](docs/sdks/functions/README.md#delete) - Delete Function\n* [get_by_name](docs/sdks/functions/README.md#get_by_name) - Get Function By Name\n* [get_by_revision](docs/sdks/functions/README.md#get_by_revision) - Get Function By Revision\n* [call](docs/sdks/functions/README.md#call) - Call Function\n* [stream](docs/sdks/functions/README.md#stream) - Stream Function\n* [call_revision](docs/sdks/functions/README.md#call_revision) - Call Function Revision\n* [stream_revision](docs/sdks/functions/README.md#stream_revision) - Stream Function Revision\n\n#### [functions.revisions](docs/sdks/revisions/README.md)\n\n* [list](docs/sdks/revisions/README.md#list) - List Function Revisions\n\n### [knowledge](docs/sdks/knowledge/README.md)\n\n* [create](docs/sdks/knowledge/README.md#create) - Create Knowledge Base\n* [list](docs/sdks/knowledge/README.md#list) - List Knowledge Bases\n* [get](docs/sdks/knowledge/README.md#get) - Get Knowledge Base\n* [delete](docs/sdks/knowledge/README.md#delete) - Delete Knowledge Base\n* [get_by_name](docs/sdks/knowledge/README.md#get_by_name) - Get Knowledge Base By Name\n* [get_upload_url](docs/sdks/knowledge/README.md#get_upload_url) - Get Upload Url\n* [register_file_upload](docs/sdks/knowledge/README.md#register_file_upload) - Register File Upload\n* [delete_file](docs/sdks/knowledge/README.md#delete_file) - Delete File From Knowledge Base\n* [query](docs/sdks/knowledge/README.md#query) - Query Knowledge Base\n* [add](docs/sdks/knowledge/README.md#add) - Add\n\n### [language_models](docs/sdks/languagemodels/README.md)\n\n* [list](docs/sdks/languagemodels/README.md#list) - List Models\n* [register_custom](docs/sdks/languagemodels/README.md#register_custom) - Register Custom Model\n* [list_custom](docs/sdks/languagemodels/README.md#list_custom) - List Custom Models\n* [get_custom](docs/sdks/languagemodels/README.md#get_custom) - Get Custom Model\n* [update_custom](docs/sdks/languagemodels/README.md#update_custom) - Update Custom Model\n* [delete_custom](docs/sdks/languagemodels/README.md#delete_custom) - Delete Custom Model\n* [get_custom_by_name](docs/sdks/languagemodels/README.md#get_custom_by_name) - Get Custom Model By Name\n\n### [Opper SDK](docs/sdks/opper/README.md)\n\n* [call](docs/sdks/opper/README.md#call) - Function Call\n* [stream](docs/sdks/opper/README.md#stream) - Function Stream\n\n### [span_metrics](docs/sdks/spanmetrics/README.md)\n\n* [create_metric](docs/sdks/spanmetrics/README.md#create_metric) - Create Metric\n* [list](docs/sdks/spanmetrics/README.md#list) - List Metrics\n* [get](docs/sdks/spanmetrics/README.md#get) - Get Metric\n* [update_metric](docs/sdks/spanmetrics/README.md#update_metric) - Update Metric\n* [delete](docs/sdks/spanmetrics/README.md#delete) - Delete Metric\n\n### [spans](docs/sdks/spans/README.md)\n\n* [create](docs/sdks/spans/README.md#create) - Create Span\n* [get](docs/sdks/spans/README.md#get) - Get Span\n* [update](docs/sdks/spans/README.md#update) - Update Span\n* [delete](docs/sdks/spans/README.md#delete) - Delete Span\n* [save_examples](docs/sdks/spans/README.md#save_examples) - Save To Dataset\n\n### [traces](docs/sdks/traces/README.md)\n\n* [list](docs/sdks/traces/README.md#list) - List Traces\n* [get](docs/sdks/traces/README.md#get) - Get Trace\n\n</details>\n<!-- End Available Resources and Operations [operations] -->\n\n<!-- Start Server-sent event streaming [eventstream] -->\n## Server-sent event streaming\n\n[Server-sent events][mdn-sse] are used to stream content from certain\noperations. These operations will expose the stream as [Generator][generator] that\ncan be consumed using a simple `for` loop. The loop will\nterminate when the server no longer has any events to send and closes the\nunderlying connection. \n\n```python\nfrom opperai import Opper\nimport os\n\n\nopper = Opper(http_bearer=os.getenv(\"OPPER_API_KEY\"))\n\ndef stream_call():\n \"\"\"Print the assistant\u2019s answer as it streams back from Opper.\"\"\"\n outer = opper.stream(\n name=\"python/sdk/bare-minimum-with-stream\",\n instructions=\"answer the following question\",\n input=\"what are some uses of 42\",\n )\n\n # Pull out the inner EventStream object in one line.\n stream = next(value for key, value in outer if key == \"result\")\n\n # Read each Server-Sent Event and emit the delta text.\n for event in stream: # event: ServerSentEvent\n delta = getattr(event.data, \"delta\", None)\n if delta: # skip keep-alives, etc.\n print(delta, end=\"\", flush=True)\n\n```\n\n\n\nThe stream is also a [Context Manager][context-manager] and can be used with the `with` statement and will close the underlying connection when the context is exited.\n<details closed>\n<summary> Context Manager Stream Example</summary>\n\n\n```python\nfrom opperai import Opper\nimport os\n\n\nwith Opper(\n http_bearer=os.getenv(\"OPPER_HTTP_BEARER\", \"\"),\n) as opper:\n\n res = opper.stream(name=\"add_numbers\", instructions=\"Calculate the sum of two numbers\", input_schema={\n \"properties\": {\n \"x\": {\n \"title\": \"X\",\n \"type\": \"integer\",\n },\n \"y\": {\n \"title\": \"Y\",\n \"type\": \"integer\",\n },\n },\n \"required\": [\n \"x\",\n \"y\",\n ],\n \"title\": \"OpperInputExample\",\n \"type\": \"object\",\n }, output_schema={\n \"properties\": {\n \"sum\": {\n \"title\": \"Sum\",\n \"type\": \"integer\",\n },\n },\n \"required\": [\n \"sum\",\n ],\n \"title\": \"OpperOutputExample\",\n \"type\": \"object\",\n }, input={\n \"x\": 4,\n \"y\": 5,\n }, examples=[\n {\n \"input\": {\n \"x\": 1,\n \"y\": 3,\n },\n \"output\": {\n \"sum\": 4,\n },\n \"comment\": \"Adds two numbers\",\n },\n ], parent_span_id=\"123e4567-e89b-12d3-a456-426614174000\", tags={\n \"project\": \"project_456\",\n \"user\": \"company_123\",\n }, configuration={})\n\n with res as event_stream:\n for event in event_stream:\n # handle event\n print(event, flush=True)\n\n```\n\n[mdn-sse]: https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events\n[generator]: https://book.pythontips.com/en/latest/generators.html\n[context-manager]: https://book.pythontips.com/en/latest/context_managers.html\n</details>\n<!-- End Server-sent event streaming [eventstream] -->\n\n<!-- Start Retries [retries] -->\n## Retries\n\nSome 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.\n\nTo change the default retry strategy for a single API call, simply provide a `RetryConfig` object to the call:\n```python\nfrom opperai import Opper\nfrom opperai.utils import BackoffStrategy, RetryConfig\nimport os\n\n\nwith Opper(\n http_bearer=os.getenv(\"OPPER_HTTP_BEARER\", \"\"),\n) as opper:\n\n res = opper.call(name=\"add_numbers\", instructions=\"Calculate the sum of two numbers\", input_schema={\n \"properties\": {\n \"x\": {\n \"title\": \"X\",\n \"type\": \"integer\",\n },\n \"y\": {\n \"title\": \"Y\",\n \"type\": \"integer\",\n },\n },\n \"required\": [\n \"x\",\n \"y\",\n ],\n \"title\": \"OpperInputExample\",\n \"type\": \"object\",\n }, output_schema={\n \"properties\": {\n \"sum\": {\n \"title\": \"Sum\",\n \"type\": \"integer\",\n },\n },\n \"required\": [\n \"sum\",\n ],\n \"title\": \"OpperOutputExample\",\n \"type\": \"object\",\n }, input={\n \"x\": 4,\n \"y\": 5,\n }, examples=[\n {\n \"input\": {\n \"x\": 1,\n \"y\": 3,\n },\n \"output\": {\n \"sum\": 4,\n },\n \"comment\": \"Adds two numbers\",\n },\n ], parent_span_id=\"123e4567-e89b-12d3-a456-426614174000\", tags={\n \"project\": \"project_456\",\n \"user\": \"company_123\",\n }, configuration={},\n RetryConfig(\"backoff\", BackoffStrategy(1, 50, 1.1, 100), False))\n\n # Handle response\n print(res)\n\n```\n\nIf 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:\n```python\nfrom opperai import Opper\nfrom opperai.utils import BackoffStrategy, RetryConfig\nimport os\n\n\nwith Opper(\n retry_config=RetryConfig(\"backoff\", BackoffStrategy(1, 50, 1.1, 100), False),\n http_bearer=os.getenv(\"OPPER_HTTP_BEARER\", \"\"),\n) as opper:\n\n res = opper.call(name=\"add_numbers\", instructions=\"Calculate the sum of two numbers\", input_schema={\n \"properties\": {\n \"x\": {\n \"title\": \"X\",\n \"type\": \"integer\",\n },\n \"y\": {\n \"title\": \"Y\",\n \"type\": \"integer\",\n },\n },\n \"required\": [\n \"x\",\n \"y\",\n ],\n \"title\": \"OpperInputExample\",\n \"type\": \"object\",\n }, output_schema={\n \"properties\": {\n \"sum\": {\n \"title\": \"Sum\",\n \"type\": \"integer\",\n },\n },\n \"required\": [\n \"sum\",\n ],\n \"title\": \"OpperOutputExample\",\n \"type\": \"object\",\n }, input={\n \"x\": 4,\n \"y\": 5,\n }, examples=[\n {\n \"input\": {\n \"x\": 1,\n \"y\": 3,\n },\n \"output\": {\n \"sum\": 4,\n },\n \"comment\": \"Adds two numbers\",\n },\n ], parent_span_id=\"123e4567-e89b-12d3-a456-426614174000\", tags={\n \"project\": \"project_456\",\n \"user\": \"company_123\",\n }, configuration={})\n\n # Handle response\n print(res)\n\n```\n<!-- End Retries [retries] -->\n\n<!-- Start Error Handling [errors] -->\n## Error Handling\n\nCheck our detailed [error handling](https://docs.opper.ai/api-reference/errors)\n\nHandling errors in this SDK should largely match your expectations. All operations return a response object or raise an exception.\n\nBy default, an API error will raise a errors.APIError exception, which has the following properties:\n\n| Property | Type | Description |\n|-----------------|------------------|-----------------------|\n| `.status_code` | *int* | The HTTP status code |\n| `.message` | *str* | The error message |\n| `.raw_response` | *httpx.Response* | The raw HTTP response |\n| `.body` | *str* | The response content |\n\nWhen custom error responses are specified for an operation, the SDK may also raise their associated exceptions. You can refer to respective *Errors* tables in SDK docs for more details on possible exception types for each operation. For example, the `call_async` method may raise the following exceptions:\n\n| Error Type | Status Code | Content Type |\n| ----------------------------- | ----------- | ---------------- |\n| errors.BadRequestError | 400 | application/json |\n| errors.UnauthorizedError | 401 | application/json |\n| errors.NotFoundError | 404 | application/json |\n| errors.RequestValidationError | 422 | application/json |\n| errors.APIError | 4XX, 5XX | \\*/\\* |\n\n### Example\n\n```python\nfrom opperai import Opper, errors\nimport os\n\n\nwith Opper(\n http_bearer=os.getenv(\"OPPER_HTTP_BEARER\", \"\"),\n) as opper:\n res = None\n try:\n\n res = opper.call(name=\"add_numbers\", instructions=\"Calculate the sum of two numbers\", input_schema={\n \"properties\": {\n \"x\": {\n \"title\": \"X\",\n \"type\": \"integer\",\n },\n \"y\": {\n \"title\": \"Y\",\n \"type\": \"integer\",\n },\n },\n \"required\": [\n \"x\",\n \"y\",\n ],\n \"title\": \"OpperInputExample\",\n \"type\": \"object\",\n }, output_schema={\n \"properties\": {\n \"sum\": {\n \"title\": \"Sum\",\n \"type\": \"integer\",\n },\n },\n \"required\": [\n \"sum\",\n ],\n \"title\": \"OpperOutputExample\",\n \"type\": \"object\",\n }, input={\n \"x\": 4,\n \"y\": 5,\n }, examples=[\n {\n \"input\": {\n \"x\": 1,\n \"y\": 3,\n },\n \"output\": {\n \"sum\": 4,\n },\n \"comment\": \"Adds two numbers\",\n },\n ], parent_span_id=\"123e4567-e89b-12d3-a456-426614174000\", tags={\n \"project\": \"project_456\",\n \"user\": \"company_123\",\n }, configuration={})\n\n # Handle response\n print(res)\n\n except errors.BadRequestError as e:\n # handle e.data: errors.BadRequestErrorData\n raise(e)\n except errors.UnauthorizedError as e:\n # handle e.data: errors.UnauthorizedErrorData\n raise(e)\n except errors.NotFoundError as e:\n # handle e.data: errors.NotFoundErrorData\n raise(e)\n except errors.RequestValidationError as e:\n # handle e.data: errors.RequestValidationErrorData\n raise(e)\n except errors.APIError as e:\n # handle exception\n raise(e)\n```\n<!-- End Error Handling [errors] -->\n\n## Custom HTTP Client\n\nThe Python SDK makes API calls using the [httpx](https://www.python-httpx.org/) 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.\nDepending 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.\nThis 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.\n\nFor example, you could specify a header for every request that this sdk makes as follows:\n```python\nfrom opperai import Opper\nimport httpx\n\nhttp_client = httpx.Client(headers={\"x-custom-header\": \"someValue\"})\ns = Opper(client=http_client)\n```\n\nor you could wrap the client with your own custom logic:\n```python\nfrom opperai import Opper\nfrom opperai.httpclient import AsyncHttpClient\nimport httpx\n\nclass CustomClient(AsyncHttpClient):\n client: AsyncHttpClient\n\n def __init__(self, client: AsyncHttpClient):\n self.client = client\n\n async def send(\n self,\n request: httpx.Request,\n *,\n stream: bool = False,\n auth: Union[\n httpx._types.AuthTypes, httpx._client.UseClientDefault, None\n ] = httpx.USE_CLIENT_DEFAULT,\n follow_redirects: Union[\n bool, httpx._client.UseClientDefault\n ] = httpx.USE_CLIENT_DEFAULT,\n ) -> httpx.Response:\n request.headers[\"Client-Level-Header\"] = \"added by client\"\n\n return await self.client.send(\n request, stream=stream, auth=auth, follow_redirects=follow_redirects\n )\n\n def build_request(\n self,\n method: str,\n url: httpx._types.URLTypes,\n *,\n content: Optional[httpx._types.RequestContent] = None,\n data: Optional[httpx._types.RequestData] = None,\n files: Optional[httpx._types.RequestFiles] = None,\n json: Optional[Any] = None,\n params: Optional[httpx._types.QueryParamTypes] = None,\n headers: Optional[httpx._types.HeaderTypes] = None,\n cookies: Optional[httpx._types.CookieTypes] = None,\n timeout: Union[\n httpx._types.TimeoutTypes, httpx._client.UseClientDefault\n ] = httpx.USE_CLIENT_DEFAULT,\n extensions: Optional[httpx._types.RequestExtensions] = None,\n ) -> httpx.Request:\n return self.client.build_request(\n method,\n url,\n content=content,\n data=data,\n files=files,\n json=json,\n params=params,\n headers=headers,\n cookies=cookies,\n timeout=timeout,\n extensions=extensions,\n )\n\ns = Opper(async_client=CustomClient(httpx.AsyncClient()))\n```\n<!-- End Custom HTTP Client [http-client] -->\n\n<!-- Start Resource Management [resource-management] -->\n## Resource Management\n\nThe `Opper` 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][context-manager] and reuse it across the application.\n\n[context-manager]: https://docs.python.org/3/reference/datamodel.html#context-managers\n\n```python\nfrom opperai import Opper\nimport os\ndef main():\n\n with Opper(\n http_bearer=os.getenv(\"OPPER_HTTP_BEARER\", \"\"),\n ) as opper:\n # Rest of application here...\n\n\n# Or when using async:\nasync def amain():\n\n async with Opper(\n http_bearer=os.getenv(\"OPPER_HTTP_BEARER\", \"\"),\n ) as opper:\n # Rest of application here...\n```\n<!-- End Resource Management [resource-management] -->\n\n<!-- Start Debugging [debug] -->\n## Debugging\n\nYou can setup your SDK to emit debug logs for SDK requests and responses.\n\nYou can pass your own logger class directly into your SDK.\n```python\nfrom opperai import Opper\nimport logging\n\nlogging.basicConfig(level=logging.DEBUG)\ns = Opper(debug_logger=logging.getLogger(\"opperai\"))\n```\n\nYou can also enable a default debug logger by setting an environment variable `OPPER_DEBUG` to true.\n<!-- End Debugging [debug] -->\n\n<!-- Placeholder for Future Speakeasy SDK Sections -->\n\n# Development\n\n## Maturity\n\nThis SDK is in beta, and there may be breaking changes between versions without a major version update. Therefore, we recommend pinning usage\nto a specific package version. This way, you can install the same version each time without breaking changes unless you are intentionally\nlooking for the latest version.\n\n## Contributions\n\nWhile 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. \nWe 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. \n\n### SDK Created by [Speakeasy](https://www.speakeasy.com/?utm_source=opperai&utm_campaign=python)\n\n",
"bugtrack_url": null,
"license": null,
"summary": "Python Client SDK Generated by Speakeasy.",
"version": "1.3.0",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "786c5b92938ea68b66458d202b1824a60c79e83cd05d04b256be003cfc0ba5a2",
"md5": "2e0a47f16e38368ab059b6bda986edd4",
"sha256": "1fcc366cc73932db68a479980e0d2d460d81a4bcad186a2d85635839fd474c86"
},
"downloads": -1,
"filename": "opperai-1.3.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "2e0a47f16e38368ab059b6bda986edd4",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9.2",
"size": 250215,
"upload_time": "2025-10-08T07:49:42",
"upload_time_iso_8601": "2025-10-08T07:49:42.402580Z",
"url": "https://files.pythonhosted.org/packages/78/6c/5b92938ea68b66458d202b1824a60c79e83cd05d04b256be003cfc0ba5a2/opperai-1.3.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "e09756093572ef2c911560beeb66991ed0cb6dba82f330f0fd815da05c00f887",
"md5": "895a20b9012f41841bb77f3487596670",
"sha256": "d329a9924e62f0086568a822c34a49086e783eaf45b3b0b98a318bfd85b3d659"
},
"downloads": -1,
"filename": "opperai-1.3.0.tar.gz",
"has_sig": false,
"md5_digest": "895a20b9012f41841bb77f3487596670",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9.2",
"size": 108393,
"upload_time": "2025-10-08T07:49:43",
"upload_time_iso_8601": "2025-10-08T07:49:43.876357Z",
"url": "https://files.pythonhosted.org/packages/e0/97/56093572ef2c911560beeb66991ed0cb6dba82f330f0fd815da05c00f887/opperai-1.3.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-08 07:49:43",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "opperai"
}
