KBRaiN SDK API
The KBRaiN SDK API is a Python library that provides a simple interface to interact with the KBRaiN services. It includes methods for account creation, key generation, and interacting with the OpenAI chat service.
Installation
To install the KBRaiN SDK API, use pip:
pip install kbrainsdk
Usage
See the kbrainsdk/examples/example.ipynb Jupyter notebook for more examples.
Here are a few:
First, import the library and create an instance of the API client:
from kbrainsdk.api import KBRaiNAPI
kbrain = KBRaiNAPI(account_id='your_account_id', api_key='your_api_key', base_url="kbrain_base_url")
We recommend using environment variables or a tool like Azure Key Vault to inject your api key, do not commit your api key to any source control for security reasons.
You can also skip passing in values to the constructor and KBRaiN will reference your environment variables if they are defined with the following names:
KBRAIN_BASE_URL
KBRAIN_ACCOUNT_ID
KBRAIN_API_KEY
OpenAI Chat
To interact with the OpenAI chat API, use the openai_chat method. This method takes the same arguments as the OpenAI API as of version 1.3.3. You can see the API documentation at OpenAI for details.
Here is an example:
messages = [{
'role': 'system',
'content': 'You are a helpful assistant.'
}, {
'role': 'user',
'content': 'What is the air speed velocity of an unladen swallow?'
}]
model_name = 'gpt-3.5-turbo' # Replace with the model name in the targeted Azure OpenAI Resource. This should be chat for gpt-3x and chat-4 for gpt4.
model_type = 'openai' # Replace with your model type
deployment_id = 'chat'
response = kbrain.llms.openai_chat(messages, model_name, model_type, deployment_id)
print(response["response"])
print(response["tokens"])
OpenAI Completion
To interact with the OpenAI completions API, use the openai_completion method. This method takes the same arguments as the OpenAI API as of version 1.3.3. You can see the API documentation at OpenAI for details.
Here is an example:
prompt = "Translate this into Spanish: Hello World!"
model_name = 'gpt-3.5-instruct' # Replace with the model name in the targeted Azure OpenAI Resource. This should be chat for gpt-3x and chat-4 for gpt4.
model_type = 'openai' # Replace with your model type
deployment_id = 'instruct'
response = kbrain.llms.openai_completion(prompt, model_name, model_type, deployment_id)
print(response["response"])
print(response["tokens"])
Dataset Features
To interact with the Dataset features, follow the example below:
email = "<your users email>"
token = "<your users authentication token into your app>"
client_id = "<your apps client_id>"
oauth_secret = "<your apps oauth secret>"
tenant_id = "<your apps tenant id>"
response = kbrain.datasets.list_datasets(email, token, client_id, oauth_secret, tenant_id)
License
Copyright 2023, KBR Inc.
1 maintainer
Metadata
1 maintainer
Release files for kbrainsdk 0.23.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| kbrainsdk-0.23.4.tar.gz | 13.2 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| kbrainsdk-0.23.4-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 32.2 kB
Release files / kbrainsdk-0.23.4.tar.gz
| Download URL | kbrainsdk-0.23.4.tar.gz |
|---|---|
| Size | 13.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
8c8ff96a71583bcc5c942b33e4591dd244c75e45ddbf0bebb7c7493421b12683
|
|
BLAKE2b-256 checksum How to use checksums |
9b1c58f9ceb6505f70d97dc79a8ef295bbfe24c9e936fa1b565ab05d42c46bfb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.7.1 CPython/3.11.6 Linux/5.15.153.1-microsoft-standard-WSL2
|
Release files / kbrainsdk-0.23.4-py3-none-any.whl
| Download URL | kbrainsdk-0.23.4-py3-none-any.whl |
|---|---|
| Size | 19.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
06c5f3b17a8ace62e0bfb716c468b9473dd4a5be222d794bbd3e2348347b80f6
|
|
BLAKE2b-256 checksum How to use checksums |
42598280d96875423a286f66d8370c44acb6408d368ee4d88fc7f951df6335af
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.7.1 CPython/3.11.6 Linux/5.15.153.1-microsoft-standard-WSL2
|
Security for kbrainsdk 0.23.4
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
