Replicate Provider API Reference¶
The ReplicateProvider
class implements the AIProvider
interface for the Replicate service. It provides methods for text generation and chat functionality using models hosted on Replicate.
Class Definition¶
Bases: AIProvider
Replicate-specific implementation of the AIProvider abstract base class.
This class provides methods to interact with Replicate's AI models for text generation and chat functionality.
Attributes:
Name | Type | Description |
---|---|---|
client |
ReplicateClientProtocol
|
The Replicate client used for making API calls. |
Parameters:
Name | Type | Description | Default |
---|---|---|---|
api_key |
str
|
The API key for authenticating with Replicate. |
required |
Raises:
Type | Description |
---|---|
ImportError
|
If the Replicate package is not installed. |
Examples:
Initialize the Replicate provider:
Source code in clientai/replicate/provider.py
35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 |
|
chat(messages, model, return_full_response=False, stream=False, **kwargs)
¶
Engage in a chat conversation using a specified Replicate model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
messages |
List[Message]
|
A list of message dictionaries, each containing 'role' and 'content'. |
required |
model |
str
|
The name or identifier of the Replicate model to use. |
required |
return_full_response |
bool
|
If True, return the full response object. If False, return only the generated text. Defaults to False. |
False
|
stream |
bool
|
If True, return an iterator for streaming responses. Defaults to False. |
False
|
**kwargs |
Any
|
Additional keyword arguments to pass to the Replicate API. |
{}
|
Returns:
Name | Type | Description |
---|---|---|
ReplicateGenericResponse |
ReplicateGenericResponse
|
The chat response, full response object, |
ReplicateGenericResponse
|
or an iterator for streaming responses. |
Examples:
Chat (message content only):
messages = [
{"role": "user", "content": "What is the capital of France?"},
{"role": "assistant", "content": "The capital is Paris."},
{"role": "user", "content": "What is its population?"}
]
response = provider.chat(
messages,
model="meta/llama-2-70b-chat:latest",
)
print(response)
Chat (full response):
response = provider.chat(
messages,
model="meta/llama-2-70b-chat:latest",
return_full_response=True
)
print(response["output"])
Chat (streaming):
for chunk in provider.chat(
messages,
model="meta/llama-2-70b-chat:latest",
stream=True
):
print(chunk, end="", flush=True)
Source code in clientai/replicate/provider.py
259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 |
|
generate_text(prompt, model, return_full_response=False, stream=False, **kwargs)
¶
Generate text based on a given prompt using a specified Replicate model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
prompt |
str
|
The input prompt for text generation. |
required |
model |
str
|
The name or identifier of the Replicate model to use. |
required |
return_full_response |
bool
|
If True, return the full response object. If False, return only the generated text. Defaults to False. |
False
|
stream |
bool
|
If True, return an iterator for streaming responses. Defaults to False. |
False
|
**kwargs |
Any
|
Additional keyword arguments to pass to the Replicate API. |
{}
|
Returns:
Name | Type | Description |
---|---|---|
ReplicateGenericResponse |
ReplicateGenericResponse
|
The generated text, full response object, |
ReplicateGenericResponse
|
or an iterator for streaming responses. |
Examples:
Generate text (text only):
response = provider.generate_text(
"Explain quantum computing",
model="meta/llama-2-70b-chat:latest",
)
print(response)
Generate text (full response):
response = provider.generate_text(
"Explain quantum computing",
model="meta/llama-2-70b-chat:latest",
return_full_response=True
)
print(response["output"])
Generate text (streaming):
for chunk in provider.generate_text(
"Explain quantum computing",
model="meta/llama-2-70b-chat:latest",
stream=True
):
print(chunk, end="", flush=True)
Source code in clientai/replicate/provider.py
180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 |
|