Files
aiagent/backend/app/services
renjianbo 1f7c136544 feat: #33 多模态Agent — 图片识别/视觉理解/语音转文字/文字转语音
后端新增 4 个内置工具: image_ocr (Tesseract OCR)、image_vision (GPT-4o 多模态视觉)、
speech_to_text (Whisper API)、text_to_speech (TTS API)。
前端 AgentChatPreview 增加录音上传和语音朗读交互。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-05-06 22:02:19 +08:00
..
2026-01-19 00:09:36 +08:00
2026-01-19 00:09:36 +08:00
2026-01-19 00:09:36 +08:00
2026-01-19 00:09:36 +08:00
2026-01-19 00:09:36 +08:00
2026-01-19 00:09:36 +08:00
2026-01-19 00:09:36 +08:00
2026-01-19 00:09:36 +08:00
2026-01-19 00:09:36 +08:00
2026-01-19 00:09:36 +08:00