OpenAI API provider: Difference between revisions
From MoodleDocs
Update OpenAI documentation |
No edit summary |
||
| Line 5: | Line 5: | ||
Moodle integration with OpenAI provides a service that lets people use advanced AI tools like generate a text, generate an image or summarize a text. | Moodle integration with OpenAI provides a service that lets people use advanced AI tools like generate a text, generate an image or summarize a text. | ||
More information about OpenAI can be found on the following link | More information about OpenAI can be found on the following link https://platform.openai.com | ||
==== Requirements: ==== | ==== Requirements: ==== | ||
| Line 16: | Line 16: | ||
# Click on the "OpenAI API Provider" settings link. | # Click on the "OpenAI API Provider" settings link. | ||
# In the “Settings” area proceed to configure the following: | # In the “Settings” area proceed to configure the following: | ||
#* OpenAI API key: You can get the key from your OpenAI account / API Keys (OpenAI API keys). | #* OpenAI API key: You can get the key from your OpenAI account / API Keys ([https://platform.openai.com/account/api-keys OpenAI API keys]). | ||
#* OpenAI organization ID: You can get it from your OpenAI account / Organization settings page (OpenAI account). | #* OpenAI organization ID: You can get it from your OpenAI account / Organization settings page ([https://platform.openai.com/account/org-settings OpenAI account]). | ||
#* Set site-wide rate limit: Limit the number of requests that the OpenAI API provider can receive across the entire site every hour. | #* Set site-wide rate limit: Limit the number of requests that the OpenAI API provider can receive across the entire site every hour. | ||
#* Maximum number of site-wide requests can be configured after enable “Set site-wide rate limit” | #* Maximum number of site-wide requests can be configured after enable “Set site-wide rate limit” | ||
| Line 23: | Line 23: | ||
#* Maximum number of requests per user can be configured after enable “Set user rate limit” | #* Maximum number of requests per user can be configured after enable “Set user rate limit” | ||
# In the “Actions” area enable all actions by clicking on their “Enabled” toggle. | # In the “Actions” area enable all actions by clicking on their “Enabled” toggle. | ||
.[[File:OpenAI.jpg|none|thumb|600x600px|OpenAI Dashboard]] | |||
[[File:OpenAI.jpg|none|thumb|600x600px|OpenAI]] | |||
==== Configuring OpenAI API provider actions ==== | ==== Configuring OpenAI API provider actions ==== | ||
| Line 33: | Line 32: | ||
'''Generate text''': You can configure the following settings: | '''Generate text''': You can configure the following settings: | ||
* AI model: OpenAI API is powered by a diverse set of models with different capabilities and price points. There is more information about OpenAI models in the following link | * AI model: OpenAI API is powered by a diverse set of models with different capabilities and price points. There is more information about OpenAI models in the following link https://platform.openai.com/docs/models As default is set to “GPT-4o” but it can be change for any other compatible model, see your settings organization limits for more information (https://platform.openai.com/settings/organization/limits) | ||
* API endpoint. Please ensure your API endpoint is compatible with your Model, see more information in the following link | * API endpoint. Please ensure your API endpoint is compatible with your Model, see more information in the following link https://platform.openai.com/docs/models/model-endpoint-compatibility | ||
* System instruction: There are some system instructions as default, but this can be adapted to your needs. | * System instruction: There are some system instructions as default, but this can be adapted to your needs. | ||
'''Summarise text:''' The required configuration is the same as for the Generate text action. | |||
'''Summarise text:''' The required configuration is the same as for the Generate text action. | |||
'''Generate image''': You can configure the following settings: | '''Generate image''': You can configure the following settings: | ||
* AI model: As default is set to “dall-e-3” but it can be changed for any other image generation compatible model. See more information in the following link | * AI model: As default is set to “dall-e-3” but it can be changed for any other image generation compatible model. See more information in the following link https://platform.openai.com/docs/models/dall-e | ||
* API endpoint: Please ensure your API endpoint is compatible with your Model. | * API endpoint: Please ensure your API endpoint is compatible with your Model. | ||
Revision as of 19:00, 15 October 2024
Note: This page is a work-in-progress. Feedback and suggested improvements are welcome. Please join the discussion on moodle.org or use the page comments.
Moodle integration with OpenAI provides a service that lets people use advanced AI tools like generate a text, generate an image or summarize a text.
More information about OpenAI can be found on the following link https://platform.openai.com
Requirements:
An OpenAI account with access to the API key (Usage limits and pricing tiers are dependent on the level of access and the volume of queries).
Configuring OpenAI API provider settings
- Go to Admin -> General -> AI -> AI providers
- Enable the "OpenAI API Provider" by clicking on the “Enabled” toggle.
- Click on the "OpenAI API Provider" settings link.
- In the “Settings” area proceed to configure the following:
- OpenAI API key: You can get the key from your OpenAI account / API Keys (OpenAI API keys).
- OpenAI organization ID: You can get it from your OpenAI account / Organization settings page (OpenAI account).
- Set site-wide rate limit: Limit the number of requests that the OpenAI API provider can receive across the entire site every hour.
- Maximum number of site-wide requests can be configured after enable “Set site-wide rate limit”
- Set user rate limit
- Maximum number of requests per user can be configured after enable “Set user rate limit”
- In the “Actions” area enable all actions by clicking on their “Enabled” toggle.
.
Configuring OpenAI API provider actions
Access to the Settings link on each action to configure them.
Generate text: You can configure the following settings:
- AI model: OpenAI API is powered by a diverse set of models with different capabilities and price points. There is more information about OpenAI models in the following link https://platform.openai.com/docs/models As default is set to “GPT-4o” but it can be change for any other compatible model, see your settings organization limits for more information (https://platform.openai.com/settings/organization/limits)
- API endpoint. Please ensure your API endpoint is compatible with your Model, see more information in the following link https://platform.openai.com/docs/models/model-endpoint-compatibility
- System instruction: There are some system instructions as default, but this can be adapted to your needs.
Summarise text: The required configuration is the same as for the Generate text action.
Generate image: You can configure the following settings:
- AI model: As default is set to “dall-e-3” but it can be changed for any other image generation compatible model. See more information in the following link https://platform.openai.com/docs/models/dall-e
- API endpoint: Please ensure your API endpoint is compatible with your Model.
Now we should be able to use OpenAI provider for the AI placements available in our Moodle instance: Course Assistance and HTML Text Editor Placements. Don't forget to enable and configure AI Placements settings.
