dottxt
Integration with Dottxt's API.
Dottxt
Bases: Model
Thin wrapper around the dottxt.client.Dottxt
client.
This wrapper is used to convert the input and output types specified by the
users at a higher level to arguments to the dottxt.client.Dottxt
client.
Source code in outlines/models/dottxt.py
102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 |
|
__init__(client, model_name=None, model_revision=None)
Parameters:
Name | Type | Description | Default |
---|---|---|---|
client
|
Dottxt
|
A |
required |
model_name
|
Optional[str]
|
The name of the model to use. |
None
|
model_revision
|
Optional[str]
|
The revision of the model to use. |
None
|
Source code in outlines/models/dottxt.py
generate(model_input, output_type=None, **inference_kwargs)
Generate text using Dottxt.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
model_input
|
str
|
The prompt based on which the model will generate a response. |
required |
output_type
|
Optional[Any]
|
The desired format of the response generated by the model. The output type must be of a type that can be converted to a JSON schema. |
None
|
**inference_kwargs
|
Any
|
Additional keyword arguments to pass to the client. |
{}
|
Returns:
Type | Description |
---|---|
str
|
The text generated by the model. |
Source code in outlines/models/dottxt.py
generate_stream(model_input, output_type=None, **inference_kwargs)
Not available for Dottxt.
Source code in outlines/models/dottxt.py
DottxtTypeAdapter
Bases: ModelTypeAdapter
Type adapter for the Dottxt
model.
Source code in outlines/models/dottxt.py
format_input(model_input)
Format the prompt to pass to the client.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
model_input
|
str
|
The input provided by the user. |
required |
Returns:
Type | Description |
---|---|
str
|
The input to pass to the client. |
Source code in outlines/models/dottxt.py
format_output_type(output_type=None)
Format the output type to pass to the client.
TODO: int
, float
and other Python types could be supported via
JSON Schema.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
output_type
|
Optional[Any]
|
The output type provided by the user. |
None
|
Returns:
Type | Description |
---|---|
str
|
The output type to pass to the client. |
Source code in outlines/models/dottxt.py
from_dottxt(client, model_name=None, model_revision=None)
Create an Outlines Dottxt
model instance from a dottxt.Dottxt
client instance.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
client
|
Dottxt
|
A |
required |
model_name
|
Optional[str]
|
The name of the model to use. |
None
|
model_revision
|
Optional[str]
|
The revision of the model to use. |
None
|
Returns:
Type | Description |
---|---|
Dottxt
|
An Outlines |