xinference 0.14.0__py3-none-any.whl → 0.14.0.post1__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of xinference might be problematic. Click here for more details.

xinference/_version.py CHANGED
@@ -8,11 +8,11 @@ import json
8
8
 
9
9
  version_json = '''
10
10
  {
11
- "date": "2024-08-02T16:08:07+0800",
11
+ "date": "2024-08-05T11:58:50+0800",
12
12
  "dirty": false,
13
13
  "error": null,
14
- "full-revisionid": "dd85cfe015c9cd2d8110c79213640aa0e21f3a6a",
15
- "version": "0.14.0"
14
+ "full-revisionid": "111299317120411f407b015b2b7dbf8402aa35c8",
15
+ "version": "0.14.0.post1"
16
16
  }
17
17
  ''' # END VERSION_JSON
18
18
 
@@ -46,7 +46,7 @@ from fastapi.staticfiles import StaticFiles
46
46
  from PIL import Image
47
47
  from sse_starlette.sse import EventSourceResponse
48
48
  from starlette.responses import JSONResponse as StarletteJSONResponse
49
- from starlette.responses import RedirectResponse
49
+ from starlette.responses import PlainTextResponse, RedirectResponse
50
50
  from uvicorn import Config, Server
51
51
  from xoscar.utils import get_next_port
52
52
 
@@ -235,6 +235,13 @@ class RESTfulAPI:
235
235
  allow_headers=["*"],
236
236
  )
237
237
 
238
+ @self._app.exception_handler(500)
239
+ async def internal_exception_handler(request: Request, exc: Exception):
240
+ logger.exception("Handling request %s failed: %s", request.url, exc)
241
+ return PlainTextResponse(
242
+ status_code=500, content=f"Internal Server Error: {exc}"
243
+ )
244
+
238
245
  # internal interface
239
246
  self._router.add_api_route("/status", self.get_status, methods=["GET"])
240
247
  # conflict with /v1/models/{model_uid} below, so register this first
xinference/core/worker.py CHANGED
@@ -226,6 +226,7 @@ class WorkerActor(xo.StatelessActor):
226
226
  )
227
227
  from ..model.flexible import (
228
228
  FlexibleModelSpec,
229
+ generate_flexible_model_description,
229
230
  get_flexible_model_descriptions,
230
231
  register_flexible_model,
231
232
  unregister_flexible_model,
@@ -287,6 +288,7 @@ class WorkerActor(xo.StatelessActor):
287
288
  FlexibleModelSpec,
288
289
  register_flexible_model,
289
290
  unregister_flexible_model,
291
+ generate_flexible_model_description,
290
292
  ),
291
293
  }
292
294
 
@@ -151,8 +151,8 @@ class EmbeddingModel:
151
151
 
152
152
  patch_trust_remote_code()
153
153
  if (
154
- "gte-Qwen2" in self._model_spec.model_id
155
- or "gte-Qwen2" in self._model_spec.model_name
154
+ "gte" in self._model_spec.model_name.lower()
155
+ and "qwen2" in self._model_spec.model_name.lower()
156
156
  ):
157
157
  self._model = XSentenceTransformer(
158
158
  self._model_path,
@@ -260,8 +260,8 @@ class EmbeddingModel:
260
260
  device = model._target_device
261
261
 
262
262
  if (
263
- "gte-Qwen2" not in self._model_spec.model_id
264
- and "gte-Qwen2" not in self._model_spec.model_name
263
+ "gte" in self._model_spec.model_name.lower()
264
+ and "qwen2" in self._model_spec.model_name.lower()
265
265
  ):
266
266
  model.to(device)
267
267
 
@@ -342,8 +342,8 @@ class EmbeddingModel:
342
342
  return all_embeddings, all_token_nums
343
343
 
344
344
  if (
345
- "gte-Qwen2" in self._model_spec.model_id
346
- or "gte-Qwen2" in self._model_spec.model_name
345
+ "gte" in self._model_spec.model_name.lower()
346
+ and "qwen2" in self._model_spec.model_name.lower()
347
347
  ):
348
348
  all_embeddings, all_token_nums = encode(
349
349
  self._model,
@@ -1,14 +1,14 @@
1
1
  {
2
2
  "files": {
3
3
  "main.css": "./static/css/main.4bafd904.css",
4
- "main.js": "./static/js/main.af906659.js",
4
+ "main.js": "./static/js/main.ef2a203a.js",
5
5
  "static/media/icon.webp": "./static/media/icon.4603d52c63041e5dfbfd.webp",
6
6
  "index.html": "./index.html",
7
7
  "main.4bafd904.css.map": "./static/css/main.4bafd904.css.map",
8
- "main.af906659.js.map": "./static/js/main.af906659.js.map"
8
+ "main.ef2a203a.js.map": "./static/js/main.ef2a203a.js.map"
9
9
  },
10
10
  "entrypoints": [
11
11
  "static/css/main.4bafd904.css",
12
- "static/js/main.af906659.js"
12
+ "static/js/main.ef2a203a.js"
13
13
  ]
14
14
  }
@@ -1 +1 @@
1
- <!doctype html><html lang="en"><head><meta charset="utf-8"/><link rel="icon" href="./favicon.svg"/><meta name="viewport" content="width=device-width,initial-scale=1"/><meta name="theme-color" content="#000000"/><meta name="description" content="Web site created using create-react-app"/><link rel="apple-touch-icon" href="./logo192.png"/><link rel="manifest" href="./manifest.json"/><title>Xinference</title><script defer="defer" src="./static/js/main.af906659.js"></script><link href="./static/css/main.4bafd904.css" rel="stylesheet"></head><body><noscript>You need to enable JavaScript to run this app.</noscript><div id="root"></div></body></html>
1
+ <!doctype html><html lang="en"><head><meta charset="utf-8"/><link rel="icon" href="./favicon.svg"/><meta name="viewport" content="width=device-width,initial-scale=1"/><meta name="theme-color" content="#000000"/><meta name="description" content="Web site created using create-react-app"/><link rel="apple-touch-icon" href="./logo192.png"/><link rel="manifest" href="./manifest.json"/><title>Xinference</title><script defer="defer" src="./static/js/main.ef2a203a.js"></script><link href="./static/css/main.4bafd904.css" rel="stylesheet"></head><body><noscript>You need to enable JavaScript to run this app.</noscript><div id="root"></div></body></html>