Predict
Make predictions based on a fine tuned model or default model.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
model_name |
str
|
The name of the model - which is referenced in the model_ids table alongside the model_id. |
required |
model_id |
str
|
The model id that is the output of the train API call - enables fine tuned models to be called. |
required |
question_text |
str
|
A string that contains the question. |
required |
context_text |
str
|
A string that contains additional text that can be concatenated to the question, if needed. |
None
|
document_files |
list[str]
|
A list of file paths to documents for document-based tasks for predictions. Example: ['path/to/file1.pdf', 'path/to/file2.pdf']. |
None
|
Returns:
| Name | Type | Description |
|---|---|---|
response |
dict
|
A JSON response from the API, including the |