File size: 9,209 Bytes
32b70a7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 | openapi: 3.1.0
info:
# Do not change the title, if the title changes, the import paths will be broken
title: Api
version: 0.1.0
description: Io HST Search Engine API
servers:
- url: /api
description: Base API path
tags:
- name: health
description: Health operations
- name: search
description: Io search synthesis
- name: model
description: Io neural model inference
- name: feedback
description: User feedback for evolutionary learning
paths:
/healthz:
get:
operationId: healthCheck
tags: [health]
summary: Health check
description: Returns server health status
responses:
"200":
description: Healthy
content:
application/json:
schema:
$ref: "#/components/schemas/HealthStatus"
/search:
post:
operationId: search
tags: [search]
summary: Search and synthesize
description: Runs the HST search engine across 200+ sources and returns a synthesized answer
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/SearchInput"
responses:
"200":
description: Synthesized search result
content:
application/json:
schema:
$ref: "#/components/schemas/SearchResult"
"400":
description: Bad request
/model/generate:
post:
operationId: modelGenerate
tags: [model]
summary: Generate text from Io neural model
description: Runs inference on the Io HST checkpoint
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/ModelInput"
responses:
"200":
description: Generated text
content:
application/json:
schema:
$ref: "#/components/schemas/ModelResult"
"503":
description: Model not available
/feedback:
post:
operationId: submitFeedback
tags: [feedback]
summary: Submit thumbs up/down for a search answer
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/FeedbackInput"
responses:
"200":
description: Recorded
content:
application/json:
schema:
$ref: "#/components/schemas/FeedbackResult"
"400":
description: Bad request
/feedback/stats:
get:
operationId: feedbackStats
tags: [feedback]
summary: Aggregate feedback stats
responses:
"200":
description: Stats
content:
application/json:
schema:
$ref: "#/components/schemas/FeedbackStats"
/model/finetune:
post:
operationId: modelFineTune
tags: [model]
summary: Start light CPU fine-tuning of the Io checkpoint
requestBody:
required: false
content:
application/json:
schema:
$ref: "#/components/schemas/FineTuneInput"
responses:
"200":
description: Started
content:
application/json:
schema:
$ref: "#/components/schemas/FineTuneState"
"400":
description: Bad request
/model/finetune/status:
get:
operationId: modelFineTuneStatus
tags: [model]
summary: Fine-tune status
responses:
"200":
description: Status
content:
application/json:
schema:
$ref: "#/components/schemas/FineTuneState"
/model/status:
get:
operationId: modelStatus
tags: [model]
summary: Model status
responses:
"200":
description: Model status
content:
application/json:
schema:
$ref: "#/components/schemas/ModelStatus"
components:
schemas:
HealthStatus:
type: object
properties:
status:
type: string
required:
- status
SearchInput:
type: object
required:
- query
properties:
query:
type: string
minLength: 1
maxLength: 500
target:
type: integer
minimum: 1
maximum: 12
default: 6
SearchResult:
type: object
required:
- answer
- sources
- query
properties:
answer:
type: string
sources:
type: array
items:
type: string
topUrl:
type: ["string", "null"]
query:
type: string
intent:
type: string
selfReferential:
type: boolean
sourceCount:
type: integer
processingMs:
type: integer
ModelInput:
type: object
required:
- prompt
properties:
prompt:
type: string
minLength: 1
maxLength: 1500
maxTokens:
type: integer
minimum: 1
maximum: 1024
default: 200
temperature:
type: number
minimum: 0.01
maximum: 2.0
default: 0.85
topK:
type: integer
minimum: 1
maximum: 200
default: 50
topP:
type: number
minimum: 0.01
maximum: 1.0
default: 0.95
repetitionPenalty:
type: number
minimum: 1.0
maximum: 2.0
default: 1.15
presencePenalty:
type: number
minimum: 0.0
maximum: 2.0
default: 0.0
nSamples:
type: integer
minimum: 1
maximum: 8
default: 1
ModelResult:
type: object
required:
- text
- step
properties:
text:
type: string
step:
type: integer
checkpoint:
type: string
coherenceScore:
type: number
bestOfN:
type: integer
bestScore:
type: number
error:
type: ["string", "null"]
FeedbackInput:
type: object
required:
- query
- rating
properties:
query:
type: string
minLength: 1
maxLength: 500
rating:
type: string
enum: [up, down]
sources:
type: array
items:
type: string
answer:
type: string
maxLength: 8000
FeedbackResult:
type: object
required:
- ok
- ts
properties:
ok:
type: boolean
ts:
type: integer
FeedbackStats:
type: object
required:
- totalFeedback
- totalUp
- totalDown
- sources
properties:
totalFeedback:
type: integer
totalUp:
type: integer
totalDown:
type: integer
sources:
type: array
items:
type: object
required: [source, up, down, multiplier]
properties:
source:
type: string
up:
type: integer
down:
type: integer
multiplier:
type: number
FineTuneInput:
type: object
properties:
steps:
type: integer
minimum: 1
maximum: 200
default: 30
lr:
type: number
minimum: 0.0000001
maximum: 0.001
default: 0.00001
seqLen:
type: integer
minimum: 64
maximum: 1024
default: 256
FineTuneState:
type: object
required:
- status
properties:
status:
type: string
enum: [idle, running, success, failed]
startedAt:
type: ["integer", "null"]
finishedAt:
type: ["integer", "null"]
steps:
type: integer
currentStep:
type: integer
loss:
type: ["number", "null"]
avgLoss:
type: ["number", "null"]
error:
type: ["string", "null"]
checkpointOut:
type: ["string", "null"]
activeCheckpoint:
type: string
fineTunedExists:
type: boolean
guideStats:
type: object
additionalProperties: true
log:
type: array
items:
type: object
additionalProperties: true
ok:
type: boolean
ModelStatus:
type: object
required:
- available
- message
properties:
available:
type: boolean
message:
type: string
step:
type: ["integer", "null"]
checkpoint:
type: ["string", "null"]
|