Chat Completion (NVIDIA NIM) activity
An activity that creates text output for a chat conversation in NVIDIA NIM.

Configure the Chat Completion activity
Examples
- (External) AgilePoint NX Connector For NVIDIA NIM
- Examples - Step-by-step use case examples, information about what types of examples are provided in the AgilePoint NX Product Documentation, and other resources where you can find more examples.
Prerequisites
- AgilePoint NX OnDemand (public cloud), AgilePoint NX PrivateCloud, or AgilePoint NX OnPremises v9.0 Software Update 1 or higher.
Good to Know
- To send an email notification, click
Advanced
>
Email Notifications
. For more information, refer to Email Notifications screen (Process Activities).
- In most text fields, you can use process data variables as an alternative to literal data values.
- You can configure whether this activity waits for other activities before it runs.
For more information, refer to How Do I Configure an Activity to Wait for Other Incoming Activities?
- This section shows the configuration settings on the configuration screens for this activity. Other configuration settings apply to system activities. For more information, refer to:
How to Start
- Open Process Builder.
For information about how to open this screen, refer to Process Builder.

- In Process Builder, in the Activity Library,
open the NVIDIA NIM tab.

- On the NVIDIA NIM > Activities tab,
drag the Chat Completion
activity onto your process.

General Configuration
Specifies the basic settings for the Chat Completion activity.

Good to Know
- Documentation for this screen is provided for completeness. The fields are mostly self-explanatory.
Fields
| Field Name | Definition |
|---|---|
|
Display Name |
|
|
Description |
|
Chat Completion Configuration > Model Properties tab
Configures the LLM to generate text output.

Fields
| Field Name | Definition |
|---|---|
|
NVIDIA NIM |
|
|
Create |
|
|
Model |
|
Use Model Configured In Access Token |
|
|
Frequency Penalty |
|
|
Presence Penalty |
|
|
Maximum Token Length |
|
|
Stop Sequences |
|
|
Temperature |
|
|
Nucleus Sampling (top_p) |
|
Chat Completion Configuration > System Instruction tab
Configures the system instruction that is used to guide the LLM to generate text output.

Fields
| Field Name | Definition |
|---|---|
|
NVIDIA NIM |
|
|
Create |
|
Set System Instruction |
|
Chat Completion Configuration > System Instruction > Goals/Mission tab
Specifies the goals or rules for the LLM to generate text output.

Fields
| Field Name | Definition |
|---|---|
|
Goals / Mission |
|
Chat Completion Configuration > System Instruction > Skills tab
Specifies the skills or roles for the LLM used to generate text output.

Fields
| Field Name | Definition |
|---|---|
|
Skills |
|
Chat Completion Configuration > System Instruction > Input tab
Specifies the input content the LLM used to generate text output.

Fields
| Field Name | Definition |
|---|---|
|
Input |
|
Chat Completion Configuration > System Instruction > Instruction tab
Specifies any guidance or information to refine the response of the model to generate text output.

Fields
| Field Name | Definition |
|---|---|
|
Instruction |
|
Chat Completion Configuration > System Instruction > Quality Verification tab
Specifies any guidance or information to verify the accuracy of the generated text output.

Fields
| Field Name | Definition |
|---|---|
|
Quality Verification |
|
Chat Completion Configuration > System Instruction > Output tab
Specifies the output format the LLM used to generate text output.

Fields
| Field Name | Definition |
|---|---|
|
Output |
|
Chat Completion Configuration > Request tab
Specifies how to connect the request data from the LLM to the AgilePoint process schema.

Fields
| Field Name | Definition |
|---|---|
|
NVIDIA NIM |
|
|
Create |
|
|
Message Content / Map JSON Request To App Schema |
|
Chat Completion Configuration > Response tab
Specifies where to store the response from the LLM.

Fields
| Field Name | Definition |
|---|---|
|
NVIDIA NIM |
|
|
Create |
|
|
Map NVIDIA NIM Response To App Schema / Map JSON Response To App Schema |
|
|
Store Response JSON In This Variable |
|
|
Store Response Content In This Variable (String) |

