mirror of
https://github.com/open-webui/open-webui.git
synced 2026-09-23 00:41:56 +00:00
Fixes #24544 Previously, the loaded indicator only worked for Ollama models (which have 'expires_at' from /api/ps). llama.cpp models served through the Ollama endpoint don't have 'expires_at' and weren't detected as loaded. Changes: - Query /slots endpoint for models without expires_at - Match slot model IDs to determine loaded status - Cache server capabilities to avoid 404 spam on standard Ollama servers - Use asyncio.gather for concurrent /slots requests - Handle null/empty expires_at values correctly - Fix URL construction with trailing slash handling The fix queries /slots concurrently and caches which backends support it, preventing network spam while adding llama.cpp loaded detection. |
||
|---|---|---|
| .. | ||
| access_control | ||
| images | ||
| mcp | ||
| telemetry | ||
| actions.py | ||
| anthropic.py | ||
| asgi_middleware.py | ||
| audit.py | ||
| auth.py | ||
| automations.py | ||
| calendar.py | ||
| channels.py | ||
| chat.py | ||
| code_interpreter.py | ||
| embeddings.py | ||
| files.py | ||
| filter.py | ||
| groups.py | ||
| headers.py | ||
| logger.py | ||
| middleware.py | ||
| misc.py | ||
| models.py | ||
| oauth.py | ||
| payload.py | ||
| pdf_generator.py | ||
| plugin.py | ||
| rate_limit.py | ||
| redis.py | ||
| response.py | ||
| sanitize.py | ||
| security_headers.py | ||
| session_pool.py | ||
| task.py | ||
| tools.py | ||
| validate.py | ||
| webhook.py | ||