Noxtua AI (Preview)
Europe's first sovereign Legal AI. You can chat with Noxtua to analyze, review, and summarize legal documents
This connector is available in the following products and regions:
| Service | Class | Regions |
|---|---|---|
| Copilot Studio | Premium | All Power Automate regions except the following: - US Government (GCC) - US Government (GCC High) - China Cloud operated by 21Vianet - US Department of Defense (DoD) |
| Logic Apps | Standard | All Logic Apps regions except the following: - Azure Government regions - Azure China regions - US Department of Defense (DoD) |
| Power Apps | Premium | All Power Apps regions except the following: - US Government (GCC) - US Government (GCC High) - China Cloud operated by 21Vianet - US Department of Defense (DoD) |
| Power Automate | Premium | All Power Automate regions except the following: - US Government (GCC) - US Government (GCC High) - China Cloud operated by 21Vianet - US Department of Defense (DoD) |
| Contact | |
|---|---|
| Name | Simon Joecks |
| URL | https://xayn.com/contact |
| simon.joecks@xayn.com |
| Connector Metadata | |
|---|---|
| Publisher | Xayn |
| Website | https://noxtua.com |
| Privacy policy | https://framerusercontent.com/assets/fwm9XXFQHi2B3WyWfZKBBLz3UYw.pdf |
| Categories | AI |
Noxtua Connector
The Noxtua AI Connector is a Connector for the current version of the Noxtua API. It enables authors to send a text prompt to Noxtua. It then fetches the streamed responses from the Noxtua API and returns it as a proper string containing the complete prompt completion.
| Contact | |
|---|---|
| Name | Noxtua |
| URL | https://noxtua.com |
| support@noxtua.com |
Prerequisites
- A Noxtua tenant id
- A Noxtua API key
Supported Operations
Currently, there only is one supported action Complete a chat
Complete a chat
Here you can send a text prompt that will be completed by the Noxtua AI
Known issues and limitations
The API returns an array of messages, but in the Power Automate setting, you will be typically expecting just one message. To extract the first message's content as a string, initialize a new variable after the Connector action and get the message's content e.g. with: first(outputs('Complete_a_chat')?['body/choices'])['message']['content']
Creating a connection
The connector supports the following authentication types:
| Default | Parameters for creating connection. | All regions | Not shareable |
Default
Applicable: All regions
Parameters for creating connection.
This is not shareable connection. If the power app is shared with another user, another user will be prompted to create new connection explicitly.
| Name | Type | Description | Required |
|---|---|---|---|
| Your API Key | securestring | Enter your Noxtua API Key | True |
Throttling Limits
| Name | Calls | Renewal Period |
|---|---|---|
| API calls per connection | 100 | 60 seconds |
Actions
| Complete a chat |
Send messages and receive a model response from the Noxtua AI. |
Complete a chat
Send messages and receive a model response from the Noxtua AI.
Parameters
| Name | Key | Required | Type | Description |
|---|---|---|---|---|
|
Tenant ID
|
tenant-id | True | string |
Your Noxtua tenant |
|
Maximum Completion Tokens
|
max_completion_tokens | integer |
The maximum number of tokens of the output you will receive |
|
|
Message
|
content | True | string |
This is the chat message you send to Noxtua and that will be completed |
|
Model
|
model | string |
The model you want to use to create a completion |
|
|
Temperature
|
temperature | float |
Value typically between 0 and 2. Higher values mean more creativity, but also more randomness |
|
|
Top p
|
top_p | float |
Value between 0 and 1. Higher values mean more creativity, but also more randomness |
Returns
| Name | Path | Type | Description |
|---|---|---|---|
|
choices
|
choices | array of object |
The choices. First item contains the completion under message/content |
|
Index
|
choices.index | integer |
Index of the completion message |
|
Content
|
choices.message.content | string |
Content of the completion message |
|
Finish Reason
|
choices.finish_reason | string |
The reason why the completion finished. "Stop" indicates success |
|
Prompt tokens
|
usage.prompt_tokens | integer |
Number of tokens in the prompt |
|
Completion tokens
|
usage.completion_tokens | integer |
Number of tokens in your completion |
|
Total Tokens
|
usage.total_tokens | integer |
All tokens in the dialogue |