Difference between revisions of "Create ChatGPT Connection"
(→Prompting) |
|||
| (11 intermediate revisions by the same user not shown) | |||
| Line 10: | Line 10: | ||
When viewing the ChatGPT connection, the number of tokens used up to that point will be displayed. |
When viewing the ChatGPT connection, the number of tokens used up to that point will be displayed. |
||
| + | [[File:ChatGPTtokenCount.png|center|600px]] |
||
| − | When ChatGPT is used for translation, the number of tokens will be shown in the log file for that translation. |
||
| + | |||
| + | When ChatGPT is used for translation, the number of tokens will be shown in the log file for that translation. The total tokens used for the project will be tracked on the Localyzer page. |
||
| + | |||
| + | [[File:ProjectTokenCount.png|center|177px]] |
||
= Prompting = |
= Prompting = |
||
| + | For best results with an LLM, prompting is recommended. Localyzer allows for three levels of prompting: |
||
| − | == Context Prompting == |
||
| + | See: [[Prompting]] |
||
| − | If the ChatGPT connection is configured with an InContext server, then when a context has been associated with a string (See [[String Manager / Context | Individual_Project_Tasks#Context_Capture]]), the context will be passed to ChatGPT to provide the necessary information to better translate that string. |
||
| − | == |
+ | == Context Prompting == |
| + | If the ChatGPT connection is configured with an InContext server, then when a context has been associated with a string (See [[Individual_Project_Tasks#Context_Capture | String Manager / Context]]), the context will be passed to ChatGPT to provide the necessary information to better translate that string. |
||
| − | == MultiLingual Triangulation == |
||
Latest revision as of 22:25, 10 December 2025
The connection to ChatGPT is based on a API token the customer must enter when creating the configuration. To obtain your key from ChatGPT, please refer to the following page:
Below is a view of the Edit page:
Token Count
When viewing the ChatGPT connection, the number of tokens used up to that point will be displayed.
When ChatGPT is used for translation, the number of tokens will be shown in the log file for that translation. The total tokens used for the project will be tracked on the Localyzer page.
Prompting
For best results with an LLM, prompting is recommended. Localyzer allows for three levels of prompting:
See: Prompting
Context Prompting
If the ChatGPT connection is configured with an InContext server, then when a context has been associated with a string (See String Manager / Context), the context will be passed to ChatGPT to provide the necessary information to better translate that string.
