It has been generated successfully based on your OpenAPI spec. However, it is not yet ready for production use. Here are some next steps:
- 🛠 Make your SDK feel handcrafted by customizing it
- ♻️ Refine your SDK quickly by iterating locally with the Speakeasy CLI
- 🎁 Publish your SDK to package managers by configuring automatic publishing
- ✨ When ready to productionize, delete this section from the README
pip install log10pyimport log10
s = log10.Log10(
log10_token="<YOUR_API_KEY_HERE>",
)
res = s.sessions.create(x_log10_organization='<value>')
if res.object is not None:
# handle response
pass- create - Create a completion
- update - Update completion by id.
- list_ungraded - List ungraded completions i.e. completions that have not been associated with feedback but matches task selector.
- create - Create a session
A parameter is configured globally. This parameter may be set on the SDK client instance itself during initialization. When configured as an option during SDK initialization, This global value will be used as the default on the operations that use it. When such operations are called, there is a place in each to override the global value, if needed.
For example, you can set X-Log10-Organization to '<value>' at SDK initialization and then you do not have to pass the same value on calls to operations like update. But if you want to do so you may, which will locally override the global setting. See the example code below for a demonstration.
The following global parameter is available.
| Name | Type | Required | Description |
|---|---|---|---|
| x_log10_organization | str | The x_log10_organization parameter. |
import log10
from log10.models import components
s = log10.Log10(
log10_token="<YOUR_API_KEY_HERE>",
)
res = s.completions.update(completion_id='<value>', completion=components.Completion(
organization_id='<value>',
request=components.CreateChatCompletionRequest(
messages=[
components.ChatCompletionRequestFunctionMessage(
role=components.ChatCompletionRole.SYSTEM,
content='<value>',
name='<value>',
),
],
model='gpt-4-turbo',
n=1,
response_format=components.ResponseFormat(
type=components.CreateChatCompletionRequestType.JSON_OBJECT,
),
temperature=1,
top_p=1,
user='user-1234',
),
response=components.CreateChatCompletionResponse(
id='<id>',
choices=[
components.Choices(
finish_reason=components.FinishReason.TOOL_CALLS,
index=15652,
message=components.ChatCompletionResponseMessage(
content='<value>',
role=components.ChatCompletionRole.USER,
),
logprobs=components.Logprobs(
content=[
components.ChatCompletionTokenLogprob(
token='<value>',
logprob=7084.55,
bytes=[
991464,
],
top_logprobs=[
components.TopLogprobs(
token='<value>',
logprob=2703.24,
bytes=[
627690,
],
),
],
),
],
),
),
],
created=684199,
model='gpt-4-turbo',
object=components.Object.CHAT_COMPLETION,
),
), x_log10_organization='<value>')
if res.completion is not None:
# handle response
passHandling errors in this SDK should largely match your expectations. All operations return a response object or raise an error. If Error objects are specified in your OpenAPI Spec, the SDK will raise the appropriate Error type.
| Error Object | Status Code | Content Type |
|---|---|---|
| errors.SDKError | 4xx-5xx | / |
import log10
from log10.models import components, errors
s = log10.Log10(
log10_token="<YOUR_API_KEY_HERE>",
)
res = None
try:
res = s.completions.create(completion=components.Completion(
organization_id='<value>',
request=components.CreateChatCompletionRequest(
messages=[
components.ChatCompletionRequestAssistantMessage(
role=components.ChatCompletionRole.ASSISTANT,
),
],
model='gpt-4-turbo',
n=1,
response_format=components.ResponseFormat(
type=components.CreateChatCompletionRequestType.JSON_OBJECT,
),
temperature=1,
top_p=1,
user='user-1234',
),
response=components.CreateChatCompletionResponse(
id='<id>',
choices=[
components.Choices(
finish_reason=components.FinishReason.CONTENT_FILTER,
index=859213,
message=components.ChatCompletionResponseMessage(
content='<value>',
role=components.ChatCompletionRole.ASSISTANT,
),
logprobs=components.Logprobs(
content=[
components.ChatCompletionTokenLogprob(
token='<value>',
logprob=2884.08,
bytes=[
134365,
],
top_logprobs=[
components.TopLogprobs(
token='<value>',
logprob=7865.46,
bytes=[
69025,
],
),
],
),
],
),
),
],
created=996706,
model='gpt-4-turbo',
object=components.Object.CHAT_COMPLETION,
),
), x_log10_organization='<value>')
except errors.SDKError as e:
# handle exception
raise(e)
if res.any is not None:
# handle response
passYou can override the default server globally by passing a server index to the server_idx: int optional parameter when initializing the SDK client instance. The selected server will then be used as the default on the operations that use it. This table lists the indexes associated with the available servers:
| # | Server | Variables |
|---|---|---|
| 0 | https://log10.io |
None |
import log10
from log10.models import components
s = log10.Log10(
server_idx=0,
log10_token="<YOUR_API_KEY_HERE>",
)
res = s.completions.create(completion=components.Completion(
organization_id='<value>',
request=components.CreateChatCompletionRequest(
messages=[
components.ChatCompletionRequestAssistantMessage(
role=components.ChatCompletionRole.ASSISTANT,
),
],
model='gpt-4-turbo',
n=1,
response_format=components.ResponseFormat(
type=components.CreateChatCompletionRequestType.JSON_OBJECT,
),
temperature=1,
top_p=1,
user='user-1234',
),
response=components.CreateChatCompletionResponse(
id='<id>',
choices=[
components.Choices(
finish_reason=components.FinishReason.CONTENT_FILTER,
index=859213,
message=components.ChatCompletionResponseMessage(
content='<value>',
role=components.ChatCompletionRole.ASSISTANT,
),
logprobs=components.Logprobs(
content=[
components.ChatCompletionTokenLogprob(
token='<value>',
logprob=2884.08,
bytes=[
134365,
],
top_logprobs=[
components.TopLogprobs(
token='<value>',
logprob=7865.46,
bytes=[
69025,
],
),
],
),
],
),
),
],
created=996706,
model='gpt-4-turbo',
object=components.Object.CHAT_COMPLETION,
),
), x_log10_organization='<value>')
if res.any is not None:
# handle response
passThe default server can also be overridden globally by passing a URL to the server_url: str optional parameter when initializing the SDK client instance. For example:
import log10
from log10.models import components
s = log10.Log10(
server_url="https://log10.io",
log10_token="<YOUR_API_KEY_HERE>",
)
res = s.completions.create(completion=components.Completion(
organization_id='<value>',
request=components.CreateChatCompletionRequest(
messages=[
components.ChatCompletionRequestAssistantMessage(
role=components.ChatCompletionRole.ASSISTANT,
),
],
model='gpt-4-turbo',
n=1,
response_format=components.ResponseFormat(
type=components.CreateChatCompletionRequestType.JSON_OBJECT,
),
temperature=1,
top_p=1,
user='user-1234',
),
response=components.CreateChatCompletionResponse(
id='<id>',
choices=[
components.Choices(
finish_reason=components.FinishReason.CONTENT_FILTER,
index=859213,
message=components.ChatCompletionResponseMessage(
content='<value>',
role=components.ChatCompletionRole.ASSISTANT,
),
logprobs=components.Logprobs(
content=[
components.ChatCompletionTokenLogprob(
token='<value>',
logprob=2884.08,
bytes=[
134365,
],
top_logprobs=[
components.TopLogprobs(
token='<value>',
logprob=7865.46,
bytes=[
69025,
],
),
],
),
],
),
),
],
created=996706,
model='gpt-4-turbo',
object=components.Object.CHAT_COMPLETION,
),
), x_log10_organization='<value>')
if res.any is not None:
# handle response
passThe Python SDK makes API calls using the requests 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 a custom requests.Session object.
For example, you could specify a header for every request that this sdk makes as follows:
import log10
import requests
http_client = requests.Session()
http_client.headers.update({'x-custom-header': 'someValue'})
s = log10.Log10(client=http_client)This SDK supports the following security scheme globally:
| Name | Type | Scheme |
|---|---|---|
log10_token |
apiKey | API key |
To authenticate with the API the log10_token parameter must be set when initializing the SDK client instance. For example:
import log10
from log10.models import components
s = log10.Log10(
log10_token="<YOUR_API_KEY_HERE>",
)
res = s.completions.create(completion=components.Completion(
organization_id='<value>',
request=components.CreateChatCompletionRequest(
messages=[
components.ChatCompletionRequestAssistantMessage(
role=components.ChatCompletionRole.ASSISTANT,
),
],
model='gpt-4-turbo',
n=1,
response_format=components.ResponseFormat(
type=components.CreateChatCompletionRequestType.JSON_OBJECT,
),
temperature=1,
top_p=1,
user='user-1234',
),
response=components.CreateChatCompletionResponse(
id='<id>',
choices=[
components.Choices(
finish_reason=components.FinishReason.CONTENT_FILTER,
index=859213,
message=components.ChatCompletionResponseMessage(
content='<value>',
role=components.ChatCompletionRole.ASSISTANT,
),
logprobs=components.Logprobs(
content=[
components.ChatCompletionTokenLogprob(
token='<value>',
logprob=2884.08,
bytes=[
134365,
],
top_logprobs=[
components.TopLogprobs(
token='<value>',
logprob=7865.46,
bytes=[
69025,
],
),
],
),
],
),
),
],
created=996706,
model='gpt-4-turbo',
object=components.Object.CHAT_COMPLETION,
),
), x_log10_organization='<value>')
if res.any is not None:
# handle response
passThis 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.
While we value open-source contributions to this SDK, this library is generated programmatically. Feel free to open a PR or a Github issue as a proof of concept and we'll do our best to include it in a future release!