tamu-edu/GPT Generate (Azure)
GPT generation using Azure with OIDC authentication
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| api-base-url | The OpenAI base URL of the API endpoint. | yes | — |
| azure-client-id | The client ID of the service principal that will be used for OIDC authentication. | yes | — |
| azure-subscription-id | The ID of the subscription that will be used for OIDC authentication. | yes | — |
| azure-tenant-id | The ID of the tenant that will be used for OIDC authentication. | no | 68f381e3-46da-47b9-ba57-6f322b8f0da1 |
| frequency_penalty | A value between 0 and 2. Reduce the chance of repeating a token proportionally based on how often it has appeared in the text so far. This decreases the likelihood of repeating the exact same text in a response. | no | 0 |
| gpt-model-deployment-name | The name of the model deployment as specified during creation in Azure. | yes | — |
| max_tokens | Set a limit on the number of tokens per model response. The API supports a maximum of 4000 tokens shared between the prompt (including system message, examples, message history, and user query) and the model's response. One token is roughly 4 characters for typical English text. | no | 800 |
| presence_penalty | A value between 0 and 2. Reduce the chance of repeating any token that has appeared in the text at all so far. This increases the likelihood of introducing new topics in a response. | no | 0 |
| prompt | The prompt provided to GPT | yes | — |
| temperature | A value between 0 and 1. Controls randomness. Lowering the temperature means that the model will produce more repetitive and deterministic responses. Increasing the temperature will result in more unexpected or creative responses. Try adjusting temperature or Top P but not both. | no | 1 |
| top_probabilities | A value between 0 and 2. Similar to temperature, this controls randomness but uses a different method. Lowering Top P will narrow the model's token selection to likelier tokens. Increasing Top P will let the model choose from tokens with both high and low likelihood. Try adjusting temperature or Top P but not both. | no | .5 |
Outputs
| name | description |
|---|---|
| generated-response | The GPT generated response |