ollama
Integration with the ollama
library.
AsyncOllama
Bases: AsyncModel
Thin wrapper around the ollama.AsyncClient
client.
This wrapper is used to convert the input and output types specified by the
users at a higher level to arguments to the ollama.AsyncClient
client.
Source code in outlines/models/ollama.py
210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 |
|
__init__(client, model_name=None)
Parameters:
Name | Type | Description | Default |
---|---|---|---|
client
|
AsyncClient
|
The |
required |
model_name
|
Optional[str]
|
The name of the model to use. |
None
|
Source code in outlines/models/ollama.py
generate(model_input, output_type=None, **kwargs)
async
Generate text using Ollama.
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
|
**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/ollama.py
generate_stream(model_input, output_type=None, **kwargs)
async
Stream text using Ollama.
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
|
**kwargs
|
Any
|
Additional keyword arguments to pass to the client. |
{}
|
Returns:
Type | Description |
---|---|
Iterator[str]
|
An iterator that yields the text generated by the model. |
Source code in outlines/models/ollama.py
Ollama
Bases: Model
Thin wrapper around the ollama.Client
client.
This wrapper is used to convert the input and output types specified by the
users at a higher level to arguments to the ollama.Client
client.
Source code in outlines/models/ollama.py
116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 |
|
__init__(client, model_name=None)
Parameters:
Name | Type | Description | Default |
---|---|---|---|
client
|
Client
|
The |
required |
model_name
|
Optional[str]
|
The name of the model to use. |
None
|
Source code in outlines/models/ollama.py
generate(model_input, output_type=None, **kwargs)
Generate text using Ollama.
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
|
**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/ollama.py
generate_stream(model_input, output_type=None, **kwargs)
Stream text using Ollama.
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
|
**kwargs
|
Any
|
Additional keyword arguments to pass to the client. |
{}
|
Returns:
Type | Description |
---|---|
Iterator[str]
|
An iterator that yields the text generated by the model. |
Source code in outlines/models/ollama.py
OllamaTypeAdapter
Bases: ModelTypeAdapter
Type adapter for the Ollama
model.
Source code in outlines/models/ollama.py
format_input(model_input)
Generate the prompt argument to pass to the model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
model_input
|
Union[str, Vision]
|
The input provided by the user. |
required |
Returns:
Type | Description |
---|---|
dict
|
The model input to be passed to the client. |
Source code in outlines/models/ollama.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 |
---|---|
Optional[str]
|
The formatted output type to be passed to the model. |
Source code in outlines/models/ollama.py
format_str_model_input(model_input)
format_vision_model_input(model_input)
Format the vision model input to pass to the client.
from_ollama(client, model_name=None)
Create an Outlines Ollama
model instance from an ollama.Client
or ollama.AsyncClient
instance.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
client
|
Union[Client, AsyncClient]
|
A |
required |
model_name
|
Optional[str]
|
The name of the model to use. |
None
|
Returns:
Type | Description |
---|---|
Union[Ollama, AsyncOllama]
|
An Outlines |