Details
-
Sub-task
-
Resolution: Unresolved
-
None
-
None
-
High
-
Empty show more show less
Description
Parallel to OpenAI Assistants, we support OpenAI "Pseudo Training". Pseudo Training basically is a non-trainable Model, where a trainings system-message is sent alongside every translation request. To achieve this, the following adjustments have to be made (the basics are already there):
- A different Icon (Maybe a spanner without "Database") is added as the last action-icon behind non-trainable models.
- This icon is greyed out when no pseudo-training is attached, otherwise fully colored
- When the icon is clicked, a dialog opens to select the pseudo-training
Pseudo training window
- on top, the selected sysmessages are shown as list of their names with a button to remove them (with confirmation-dialog)
- Below is a button "Add system message" that opens a selector (the same as in the trainings window) to add a system-message
Data Model
There will be a new table to associate sysmessages with languageresources directly:
LEK_openai_pseudotraining_assoc
Holds the association between a languageresource and sys-messages. Generally, a training can have several sys-messages. The general presence of the training is captured in the specific data of the language-resource, see MittagQI\Translate5\Plugins\OpenAI\Api\Model\SPECIFICDATA_JOBKEY
When the prop "openAiPseudoTrained" in the specific data of the LR is set to 1, this indicates an active pseudotraining, otherwise 0. This steers also the icon being greyed out or not
columns: ( id | languageresourceId | sysmsgId )
Attachments
Activity
| Status | Original: Open [ 10002 ] | New: Selected for dev [ 10100 ] |
| Assignee | Original: Volodymyr Kyianenko [ volodymyr@mittagqi.com ] | New: Pavel Perminov [ pavelperminov ] |
| Description |
Original:
Parallel to OpenAI Assistants, we support OpenAI "Pseudo Training". Pseudo Training basically is a non-trainable Model, where a trainings system-message is sent alongside every translation request. To achieve this, the following adjustments have to be made (the basics are already there):
* A different Icon (Maybe a spanner without "Database") is added as the last action-icon behind non-trainable models. * This icon is greyed out when no pseudo-training is attached, otherwise fully colored * When the icon is clicked, a dialog opens to select the pseudo-training *Pseudo training window* * on top, the selected sysmessages are shown as list of their names with a button to remove them (with confirmation-dialog) * Below is a button "Add system message" that opens a selector (the same as in the trainings window) to add a system-message Data Model There will be a new table to associate sysmessages with languageresources directly: *LEK_openai_pseudotraining_assoc* Holds the association between a languageresource and sys-messages. Generally, a training can have several sys-messages. The general presence of the training is captured in the specific data of the language-resource, see MittagQI\Translate5\Plugins\OpenAI\Api\Model\SPECIFICDATA_JOBKEY When the prop "openAiPseudoTrained" is set to 1, this indicates an active pseudotraining, otherwise 1. This steers also the icon being greyed out or not {code:java} columns: ( id | languageresourceId | sysmsgId ) {code} |
New:
Parallel to OpenAI Assistants, we support OpenAI "Pseudo Training". Pseudo Training basically is a non-trainable Model, where a trainings system-message is sent alongside every translation request. To achieve this, the following adjustments have to be made (the basics are already there):
* A different Icon (Maybe a spanner without "Database") is added as the last action-icon behind non-trainable models. * This icon is greyed out when no pseudo-training is attached, otherwise fully colored * When the icon is clicked, a dialog opens to select the pseudo-training *Pseudo training window* * on top, the selected sysmessages are shown as list of their names with a button to remove them (with confirmation-dialog) * Below is a button "Add system message" that opens a selector (the same as in the trainings window) to add a system-message h3. *Data Model* There will be a new table to associate sysmessages with languageresources directly: *LEK_openai_pseudotraining_assoc* Holds the association between a languageresource and sys-messages. Generally, a training can have several sys-messages. The general presence of the training is captured in the specific data of the language-resource, see MittagQI\Translate5\Plugins\OpenAI\Api\Model\SPECIFICDATA_JOBKEY When the prop "openAiPseudoTrained" in the specific data of the LR is set to 1, this indicates an active pseudotraining, otherwise 0. This steers also the icon being greyed out or not {code:java} columns: ( id | languageresourceId | sysmsgId ) {code} |
| Description |
Original:
Parallel to OpenAI Assistants, we support OpenAI "Pseudo Training". Pseudo Training basically is a non-trainable Model, where a trainings system-message is sent alongside every translation request. To achieve this, the following adjustments have to be made (the basics are already there):
* A different Icon (Maybe a spanner without "Database") is added as the last action-icon behind non-trainable models. * When the icon is clicked, a dialog opens to select the pseudo-training *Pseudo training window* * on top, the selected sysmessages are shown as list of their names with a button to remove * Below is a button "Add system message" that opens a selector (the same as in the trainings window) to add a system-message |
New:
Parallel to OpenAI Assistants, we support OpenAI "Pseudo Training". Pseudo Training basically is a non-trainable Model, where a trainings system-message is sent alongside every translation request. To achieve this, the following adjustments have to be made (the basics are already there):
* A different Icon (Maybe a spanner without "Database") is added as the last action-icon behind non-trainable models. * This icon is greyed out when no pseudo-training is attached, otherwise fully colored * When the icon is clicked, a dialog opens to select the pseudo-training *Pseudo training window* * on top, the selected sysmessages are shown as list of their names with a button to remove them (with confirmation-dialog) * Below is a button "Add system message" that opens a selector (the same as in the trainings window) to add a system-message Data Model There will be a new table to associate sysmessages with languageresources directly: *LEK_openai_pseudotraining_assoc* Holds the association between a languageresource and sys-messages. Generally, a training can have several sys-messages. The general presence of the training is captured in the specific data of the language-resource, see MittagQI\Translate5\Plugins\OpenAI\Api\Model\SPECIFICDATA_JOBKEY When the prop "openAiPseudoTrained" is set to 1, this indicates an active pseudotraining, otherwise 1. This steers also the icon being greyed out or not {code:java} columns: ( id | languageresourceId | sysmsgId ) {code} |
| Description |
Original:
Parallel to OpenAI Assistants, we support OpenAI "Pseudo Training". Pseudo Training basically is a non-trainable Model, where a trainings system-message is sent alongside every translation request. To achieve this, the following adjustments have to be made (the basics are already there):
* A different Icon (Maybe a spanner without "Database") is added as the last action-icon behind non-trainable models. * When the icon is clicked, a dialog opens to select the pseudo-training *Pseudo training window* * on top, the selected sysmessages are shown as list of their names with a button to remove * Below is a button "Add system message" that opens a selector (the same as in the trainings window) to add a system-message The data-model is just the same as for normal-trainings: Via |
New:
Parallel to OpenAI Assistants, we support OpenAI "Pseudo Training". Pseudo Training basically is a non-trainable Model, where a trainings system-message is sent alongside every translation request. To achieve this, the following adjustments have to be made (the basics are already there):
* A different Icon (Maybe a spanner without "Database") is added as the last action-icon behind non-trainable models. * When the icon is clicked, a dialog opens to select the pseudo-training *Pseudo training window* * on top, the selected sysmessages are shown as list of their names with a button to remove * Below is a button "Add system message" that opens a selector (the same as in the trainings window) to add a system-message |
| Description |
Original:
Parallel to OpenAI Assistants, we support OpenAI "Pseudo Training". Pseudo Training basically is a non-trainable Model, where a trainings system-message is sent alongside every translation request. To achieve this, the following adjustments have to be made (the basics are already there):
* A different Icon (Maybe a spanner without "Database") is added as the last action-icon behaind non-trainable models. It is greyed out normally, full color when a pseudo-training is active * When the icon is clicked, a dialog opens to select the pseudo-training |
New:
Parallel to OpenAI Assistants, we support OpenAI "Pseudo Training". Pseudo Training basically is a non-trainable Model, where a trainings system-message is sent alongside every translation request. To achieve this, the following adjustments have to be made (the basics are already there):
* A different Icon (Maybe a spanner without "Database") is added as the last action-icon behind non-trainable models. * When the icon is clicked, a dialog opens to select the pseudo-training *Pseudo training window* * on top, the selected sysmessages are shown as list of their names with a button to remove * Below is a button "Add system message" that opens a selector (the same as in the trainings window) to add a system-message The data-model is just the same as for normal-trainings: Via |
| Description |
Original:
Parallel to OpenAI Assistants, we support OpenAI "Pseudo Training". Pseudo Training basically is a non-trainable Model, where a trainings system-message is sent alongside every translation request. To achieve this, the following adjustments have to be made (the basics are already there):
* A different Icon (Maybe a spanner without "Database") is added as the last action-icon behaind non-trainable models. It is greyed out normally, full color when a pseudo-training is active |
New:
Parallel to OpenAI Assistants, we support OpenAI "Pseudo Training". Pseudo Training basically is a non-trainable Model, where a trainings system-message is sent alongside every translation request. To achieve this, the following adjustments have to be made (the basics are already there):
* A different Icon (Maybe a spanner without "Database") is added as the last action-icon behaind non-trainable models. It is greyed out normally, full color when a pseudo-training is active * When the icon is clicked, a dialog opens to select the pseudo-training |
| Description |
Original:
Parallel to OpenAI Assistants, we support OpenAI "Pseudo Training". Pseudo Training basically is a non-trainable Model, where a trainings system-message is sent alongside every translation request. To achieve this, the following adjustments have to be made (the basics are already there):
* TO BE DEFINED |
New:
Parallel to OpenAI Assistants, we support OpenAI "Pseudo Training". Pseudo Training basically is a non-trainable Model, where a trainings system-message is sent alongside every translation request. To achieve this, the following adjustments have to be made (the basics are already there):
* A different Icon (Maybe a spanner without "Database") is added as the last action-icon behaind non-trainable models. It is greyed out normally, full color when a pseudo-training is active |
| Description | Original: Parallel to OpenAI Assistants, we support OpenAI "Pseudo Training". Pseudo Training basically is a non-trainable Model, where a trainings system-message is sent alongside every translation request |
New:
Parallel to OpenAI Assistants, we support OpenAI "Pseudo Training". Pseudo Training basically is a non-trainable Model, where a trainings system-message is sent alongside every translation request. To achieve this, the following adjustments have to be made (the basics are already there):
* TO BE DEFINED |
| Summary | Original: TRANSLATE-4369 OpenAI GPT Training Improvements: Pseudo training | New: OpenAI GPT Training Improvements: Pseudo training |