ydy0615/llm-in-text
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
9ff51ac2f30ec1d9a4bcef7ffc00a33a927a2b94
llm-in-text/README.md

95 lines
2.2 KiB
Markdown
Raw Normal View History

feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
# LLM in Text - 智能写作助手
Initial commit
2026-01-11 14:11:14 +00:00
feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
基于 Vue3 和 FastAPI 的智能 Markdown 编辑器，集成大语言模型（LLM）实时补全建议功能。
feat(project): scaffold Vue 3 + Vite markdown editor Add initial project structure including: - .gitignore and VSCode settings - Vite configuration and package.json with Vue 3 dependencies - Basic HTML entry point and README update - Core source files: App.vue, main.js, style.css - Markdown editor component with plugin system and related types - Sample HelloWorld component, router, and Pinia store - Assets and SVG icons This commit establishes the foundation for the Vue 3 application.
2026-01-12 12:23:44 +08:00
refactor(editor): migrate to ProseMirror Mark-based ghost text system - Replace overlay-based GhostTextOverlay.vue with ProseMirror Mark system - Add AI toggle button with enable/disable functionality - Implement new copilotPlugin.ts using copilotGhostMark for inline suggestions - Fix cursor position offset in prompt.py by moving first suffix char to prefix - Improve API error handling with abort signal support and debug logging - Update model configuration from gpt-oss:120b to gpt-oss:20b - Add button tooltips and improve editor styling - Remove deprecated inlineSuggestionPlugin.ts - Update README with new architecture diagram and feature documentation
2026-02-13 09:24:50 +08:00
## 功能特性
feat: switch from OpenAI API to native Ollama Python client This commit refactors the LLM integration to use Ollama's native Python client instead of OpenAI-compatible API, while fixing critical template syntax errors and improving project structure. Key changes: - Replace openai package with ollama package in backend requirements - Rewrite llm.py to use ollama.AsyncClient for direct Ollama API calls - Update main.py to use non-streaming Ollama responses with thinking extraction - Fix template syntax error in MilkdownEditor.vue (GhostTextOverlay component tags) - Fix string截取错误 by using slice() instead of substring() - Add src/utils/api.js and src/utils/config.js for shared configuration - Add CORS middleware to FastAPI backend - Update prompt.py with clearer instructions for continuation generation - Add comprehensive README.md documentation BREAKING CHANGE: Environment variables OLLAMA_BASE_URL changed to OLLAMA_HOST (remove /v1/ suffix)
2026-02-07 08:53:37 +08:00
refactor(editor): migrate to ProseMirror Mark-based ghost text system - Replace overlay-based GhostTextOverlay.vue with ProseMirror Mark system - Add AI toggle button with enable/disable functionality - Implement new copilotPlugin.ts using copilotGhostMark for inline suggestions - Fix cursor position offset in prompt.py by moving first suffix char to prefix - Improve API error handling with abort signal support and debug logging - Update model configuration from gpt-oss:120b to gpt-oss:20b - Add button tooltips and improve editor styling - Remove deprecated inlineSuggestionPlugin.ts - Update README with new architecture diagram and feature documentation
2026-02-13 09:24:50 +08:00
### Markdown 编辑器
feat: switch from OpenAI API to native Ollama Python client This commit refactors the LLM integration to use Ollama's native Python client instead of OpenAI-compatible API, while fixing critical template syntax errors and improving project structure. Key changes: - Replace openai package with ollama package in backend requirements - Rewrite llm.py to use ollama.AsyncClient for direct Ollama API calls - Update main.py to use non-streaming Ollama responses with thinking extraction - Fix template syntax error in MilkdownEditor.vue (GhostTextOverlay component tags) - Fix string截取错误 by using slice() instead of substring() - Add src/utils/api.js and src/utils/config.js for shared configuration - Add CORS middleware to FastAPI backend - Update prompt.py with clearer instructions for continuation generation - Add comprehensive README.md documentation BREAKING CHANGE: Environment variables OLLAMA_BASE_URL changed to OLLAMA_HOST (remove /v1/ suffix)
2026-02-07 08:53:37 +08:00
- 基于 Milkdown Crepe 的所见即所得编辑体验
feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
- 支持 Markdown 语法和 LaTeX 公式
- 支持 Mermaid 图表渲染
refactor(editor): migrate to ProseMirror Mark-based ghost text system - Replace overlay-based GhostTextOverlay.vue with ProseMirror Mark system - Add AI toggle button with enable/disable functionality - Implement new copilotPlugin.ts using copilotGhostMark for inline suggestions - Fix cursor position offset in prompt.py by moving first suffix char to prefix - Improve API error handling with abort signal support and debug logging - Update model configuration from gpt-oss:120b to gpt-oss:20b - Add button tooltips and improve editor styling - Remove deprecated inlineSuggestionPlugin.ts - Update README with new architecture diagram and feature documentation
2026-02-13 09:24:50 +08:00
- 导入/导出 Markdown 文件
feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
- 导出 DOCX 和 PDF 格式
feat: switch from OpenAI API to native Ollama Python client This commit refactors the LLM integration to use Ollama's native Python client instead of OpenAI-compatible API, while fixing critical template syntax errors and improving project structure. Key changes: - Replace openai package with ollama package in backend requirements - Rewrite llm.py to use ollama.AsyncClient for direct Ollama API calls - Update main.py to use non-streaming Ollama responses with thinking extraction - Fix template syntax error in MilkdownEditor.vue (GhostTextOverlay component tags) - Fix string截取错误 by using slice() instead of substring() - Add src/utils/api.js and src/utils/config.js for shared configuration - Add CORS middleware to FastAPI backend - Update prompt.py with clearer instructions for continuation generation - Add comprehensive README.md documentation BREAKING CHANGE: Environment variables OLLAMA_BASE_URL changed to OLLAMA_HOST (remove /v1/ suffix)
2026-02-07 08:53:37 +08:00
refactor(editor): migrate to ProseMirror Mark-based ghost text system - Replace overlay-based GhostTextOverlay.vue with ProseMirror Mark system - Add AI toggle button with enable/disable functionality - Implement new copilotPlugin.ts using copilotGhostMark for inline suggestions - Fix cursor position offset in prompt.py by moving first suffix char to prefix - Improve API error handling with abort signal support and debug logging - Update model configuration from gpt-oss:120b to gpt-oss:20b - Add button tooltips and improve editor styling - Remove deprecated inlineSuggestionPlugin.ts - Update README with new architecture diagram and feature documentation
2026-02-13 09:24:50 +08:00
### AI 智能补全
- 实时生成文本补全建议（灰色显示）
- 流式响应，低延迟体验
feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
- 多种交互方式：Tab接受、Esc拒绝、点击接受
refactor(editor): migrate to ProseMirror Mark-based ghost text system - Replace overlay-based GhostTextOverlay.vue with ProseMirror Mark system - Add AI toggle button with enable/disable functionality - Implement new copilotPlugin.ts using copilotGhostMark for inline suggestions - Fix cursor position offset in prompt.py by moving first suffix char to prefix - Improve API error handling with abort signal support and debug logging - Update model configuration from gpt-oss:120b to gpt-oss:20b - Add button tooltips and improve editor styling - Remove deprecated inlineSuggestionPlugin.ts - Update README with new architecture diagram and feature documentation
2026-02-13 09:24:50 +08:00
feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
### 文档处理
- OCR 图片识别：上传图片自动识别文字
- 文档转换：PDF、DOCX、PPTX、TXT 转 Markdown
- 文档块嵌入：可折叠的文档预览块
- 智能大小限制：32KB自动禁用AI
refactor(editor): migrate to ProseMirror Mark-based ghost text system - Replace overlay-based GhostTextOverlay.vue with ProseMirror Mark system - Add AI toggle button with enable/disable functionality - Implement new copilotPlugin.ts using copilotGhostMark for inline suggestions - Fix cursor position offset in prompt.py by moving first suffix char to prefix - Improve API error handling with abort signal support and debug logging - Update model configuration from gpt-oss:120b to gpt-oss:20b - Add button tooltips and improve editor styling - Remove deprecated inlineSuggestionPlugin.ts - Update README with new architecture diagram and feature documentation
2026-02-13 09:24:50 +08:00
feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
### 设置面板
- 外观主题：亮色/暗色/跟随系统
- 背景模式：默认/暖色/阅读灯/自定义图片
- 模型智能：低/中/高思考级别
- 隐私控制：隐私模式防止发送IP
- 多语言界面：中英日韩德法
refactor(editor): migrate to ProseMirror Mark-based ghost text system - Replace overlay-based GhostTextOverlay.vue with ProseMirror Mark system - Add AI toggle button with enable/disable functionality - Implement new copilotPlugin.ts using copilotGhostMark for inline suggestions - Fix cursor position offset in prompt.py by moving first suffix char to prefix - Improve API error handling with abort signal support and debug logging - Update model configuration from gpt-oss:120b to gpt-oss:20b - Add button tooltips and improve editor styling - Remove deprecated inlineSuggestionPlugin.ts - Update README with new architecture diagram and feature documentation
2026-02-13 09:24:50 +08:00
feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
### 语音功能
- TTS文字转语音（macOS）
- STT语音转文字
feat: switch from OpenAI API to native Ollama Python client This commit refactors the LLM integration to use Ollama's native Python client instead of OpenAI-compatible API, while fixing critical template syntax errors and improving project structure. Key changes: - Replace openai package with ollama package in backend requirements - Rewrite llm.py to use ollama.AsyncClient for direct Ollama API calls - Update main.py to use non-streaming Ollama responses with thinking extraction - Fix template syntax error in MilkdownEditor.vue (GhostTextOverlay component tags) - Fix string截取错误 by using slice() instead of substring() - Add src/utils/api.js and src/utils/config.js for shared configuration - Add CORS middleware to FastAPI backend - Update prompt.py with clearer instructions for continuation generation - Add comprehensive README.md documentation BREAKING CHANGE: Environment variables OLLAMA_BASE_URL changed to OLLAMA_HOST (remove /v1/ suffix)
2026-02-07 08:53:37 +08:00
feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
## 技术架构
feat: switch from OpenAI API to native Ollama Python client This commit refactors the LLM integration to use Ollama's native Python client instead of OpenAI-compatible API, while fixing critical template syntax errors and improving project structure. Key changes: - Replace openai package with ollama package in backend requirements - Rewrite llm.py to use ollama.AsyncClient for direct Ollama API calls - Update main.py to use non-streaming Ollama responses with thinking extraction - Fix template syntax error in MilkdownEditor.vue (GhostTextOverlay component tags) - Fix string截取错误 by using slice() instead of substring() - Add src/utils/api.js and src/utils/config.js for shared configuration - Add CORS middleware to FastAPI backend - Update prompt.py with clearer instructions for continuation generation - Add comprehensive README.md documentation BREAKING CHANGE: Environment variables OLLAMA_BASE_URL changed to OLLAMA_HOST (remove /v1/ suffix)
2026-02-07 08:53:37 +08:00
feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
前端: Vue3 + Vite + Milkdown + ProseMirror
后端: FastAPI + Python + Ollama
feat: switch from OpenAI API to native Ollama Python client This commit refactors the LLM integration to use Ollama's native Python client instead of OpenAI-compatible API, while fixing critical template syntax errors and improving project structure. Key changes: - Replace openai package with ollama package in backend requirements - Rewrite llm.py to use ollama.AsyncClient for direct Ollama API calls - Update main.py to use non-streaming Ollama responses with thinking extraction - Fix template syntax error in MilkdownEditor.vue (GhostTextOverlay component tags) - Fix string截取错误 by using slice() instead of substring() - Add src/utils/api.js and src/utils/config.js for shared configuration - Add CORS middleware to FastAPI backend - Update prompt.py with clearer instructions for continuation generation - Add comprehensive README.md documentation BREAKING CHANGE: Environment variables OLLAMA_BASE_URL changed to OLLAMA_HOST (remove /v1/ suffix)
2026-02-07 08:53:37 +08:00
## 快速开始
feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
环境: Node.js 18+、Python 3.8+、Ollama
feat: switch from OpenAI API to native Ollama Python client This commit refactors the LLM integration to use Ollama's native Python client instead of OpenAI-compatible API, while fixing critical template syntax errors and improving project structure. Key changes: - Replace openai package with ollama package in backend requirements - Rewrite llm.py to use ollama.AsyncClient for direct Ollama API calls - Update main.py to use non-streaming Ollama responses with thinking extraction - Fix template syntax error in MilkdownEditor.vue (GhostTextOverlay component tags) - Fix string截取错误 by using slice() instead of substring() - Add src/utils/api.js and src/utils/config.js for shared configuration - Add CORS middleware to FastAPI backend - Update prompt.py with clearer instructions for continuation generation - Add comprehensive README.md documentation BREAKING CHANGE: Environment variables OLLAMA_BASE_URL changed to OLLAMA_HOST (remove /v1/ suffix)
2026-02-07 08:53:37 +08:00
feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
安装:
- 前端: npm install
- 后端: pip install -r backend/requirements.txt
feat: switch from OpenAI API to native Ollama Python client This commit refactors the LLM integration to use Ollama's native Python client instead of OpenAI-compatible API, while fixing critical template syntax errors and improving project structure. Key changes: - Replace openai package with ollama package in backend requirements - Rewrite llm.py to use ollama.AsyncClient for direct Ollama API calls - Update main.py to use non-streaming Ollama responses with thinking extraction - Fix template syntax error in MilkdownEditor.vue (GhostTextOverlay component tags) - Fix string截取错误 by using slice() instead of substring() - Add src/utils/api.js and src/utils/config.js for shared configuration - Add CORS middleware to FastAPI backend - Update prompt.py with clearer instructions for continuation generation - Add comprehensive README.md documentation BREAKING CHANGE: Environment variables OLLAMA_BASE_URL changed to OLLAMA_HOST (remove /v1/ suffix)
2026-02-07 08:53:37 +08:00
feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
启动:
- 后端: python backend/main.py (端口8001)
- 前端: npm run dev (端口5173)
feat: switch from OpenAI API to native Ollama Python client This commit refactors the LLM integration to use Ollama's native Python client instead of OpenAI-compatible API, while fixing critical template syntax errors and improving project structure. Key changes: - Replace openai package with ollama package in backend requirements - Rewrite llm.py to use ollama.AsyncClient for direct Ollama API calls - Update main.py to use non-streaming Ollama responses with thinking extraction - Fix template syntax error in MilkdownEditor.vue (GhostTextOverlay component tags) - Fix string截取错误 by using slice() instead of substring() - Add src/utils/api.js and src/utils/config.js for shared configuration - Add CORS middleware to FastAPI backend - Update prompt.py with clearer instructions for continuation generation - Add comprehensive README.md documentation BREAKING CHANGE: Environment variables OLLAMA_BASE_URL changed to OLLAMA_HOST (remove /v1/ suffix)
2026-02-07 08:53:37 +08:00
feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
## API接口
feat: switch from OpenAI API to native Ollama Python client This commit refactors the LLM integration to use Ollama's native Python client instead of OpenAI-compatible API, while fixing critical template syntax errors and improving project structure. Key changes: - Replace openai package with ollama package in backend requirements - Rewrite llm.py to use ollama.AsyncClient for direct Ollama API calls - Update main.py to use non-streaming Ollama responses with thinking extraction - Fix template syntax error in MilkdownEditor.vue (GhostTextOverlay component tags) - Fix string截取错误 by using slice() instead of substring() - Add src/utils/api.js and src/utils/config.js for shared configuration - Add CORS middleware to FastAPI backend - Update prompt.py with clearer instructions for continuation generation - Add comprehensive README.md documentation BREAKING CHANGE: Environment variables OLLAMA_BASE_URL changed to OLLAMA_HOST (remove /v1/ suffix)
2026-02-07 08:53:37 +08:00
feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
- POST /v1/completions 流式补全建议
- POST /v1/ocr 图片文字识别
- POST /v1/convert 文档转换
- POST /v1/completions/cancel 取消请求
feat: switch from OpenAI API to native Ollama Python client This commit refactors the LLM integration to use Ollama's native Python client instead of OpenAI-compatible API, while fixing critical template syntax errors and improving project structure. Key changes: - Replace openai package with ollama package in backend requirements - Rewrite llm.py to use ollama.AsyncClient for direct Ollama API calls - Update main.py to use non-streaming Ollama responses with thinking extraction - Fix template syntax error in MilkdownEditor.vue (GhostTextOverlay component tags) - Fix string截取错误 by using slice() instead of substring() - Add src/utils/api.js and src/utils/config.js for shared configuration - Add CORS middleware to FastAPI backend - Update prompt.py with clearer instructions for continuation generation - Add comprehensive README.md documentation BREAKING CHANGE: Environment variables OLLAMA_BASE_URL changed to OLLAMA_HOST (remove /v1/ suffix)
2026-02-07 08:53:37 +08:00
refactor(editor): migrate to ProseMirror Mark-based ghost text system - Replace overlay-based GhostTextOverlay.vue with ProseMirror Mark system - Add AI toggle button with enable/disable functionality - Implement new copilotPlugin.ts using copilotGhostMark for inline suggestions - Fix cursor position offset in prompt.py by moving first suffix char to prefix - Improve API error handling with abort signal support and debug logging - Update model configuration from gpt-oss:120b to gpt-oss:20b - Add button tooltips and improve editor styling - Remove deprecated inlineSuggestionPlugin.ts - Update README with new architecture diagram and feature documentation
2026-02-13 09:24:50 +08:00
## 核心实现
feat: switch from OpenAI API to native Ollama Python client This commit refactors the LLM integration to use Ollama's native Python client instead of OpenAI-compatible API, while fixing critical template syntax errors and improving project structure. Key changes: - Replace openai package with ollama package in backend requirements - Rewrite llm.py to use ollama.AsyncClient for direct Ollama API calls - Update main.py to use non-streaming Ollama responses with thinking extraction - Fix template syntax error in MilkdownEditor.vue (GhostTextOverlay component tags) - Fix string截取错误 by using slice() instead of substring() - Add src/utils/api.js and src/utils/config.js for shared configuration - Add CORS middleware to FastAPI backend - Update prompt.py with clearer instructions for continuation generation - Add comprehensive README.md documentation BREAKING CHANGE: Environment variables OLLAMA_BASE_URL changed to OLLAMA_HOST (remove /v1/ suffix)
2026-02-07 08:53:37 +08:00
feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
### 后端
- main.py: FastAPI服务器、SSE流式响应
- llm.py: 异步Ollama调用、超时控制
- prompt.py: 7条Prompt规则
- tts_asr.py: macOS 语音处理
feat(editor): add image insertion with OCR support and size limit handling Add image button with dropdown menu for uploading local images or inserting from URL. Integrate VLM-based OCR to extract text context from images and include in AI suggestions. Implement document size limits to disable AI when exceeding threshold. Refactor copilot plugin with per-view runtime state and OCR context injection. Add OCR cache utility for managing image metadata. Add code splitting configuration for optimized bundle size.
2026-02-14 18:28:37 +08:00
feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
### 前端
- copilotPlugin.ts: ProseMirror Mark系统
- 关键函数: scheduleFetch、insertGhostText
- Pinia Store状态管理
feat(editor): add image insertion with OCR support and size limit handling Add image button with dropdown menu for uploading local images or inserting from URL. Integrate VLM-based OCR to extract text context from images and include in AI suggestions. Implement document size limits to disable AI when exceeding threshold. Refactor copilot plugin with per-view runtime state and OCR context injection. Add OCR cache utility for managing image metadata. Add code splitting configuration for optimized bundle size.
2026-02-14 18:28:37 +08:00
## 设计亮点
feat: switch from OpenAI API to native Ollama Python client This commit refactors the LLM integration to use Ollama's native Python client instead of OpenAI-compatible API, while fixing critical template syntax errors and improving project structure. Key changes: - Replace openai package with ollama package in backend requirements - Rewrite llm.py to use ollama.AsyncClient for direct Ollama API calls - Update main.py to use non-streaming Ollama responses with thinking extraction - Fix template syntax error in MilkdownEditor.vue (GhostTextOverlay component tags) - Fix string截取错误 by using slice() instead of substring() - Add src/utils/api.js and src/utils/config.js for shared configuration - Add CORS middleware to FastAPI backend - Update prompt.py with clearer instructions for continuation generation - Add comprehensive README.md documentation BREAKING CHANGE: Environment variables OLLAMA_BASE_URL changed to OLLAMA_HOST (remove /v1/ suffix)
2026-02-07 08:53:37 +08:00
feat(plugin): add document export, doc‑block, and TTS/ASR support Adds a DocBlock component that renders embedded documents, new export buttons for DOCX and PDF, and updates the file‑upload picker to accept *.txt, *.docx, *.pptx, and *.pdf. Introduces a DOCX→PDF conversion bridge in the backend and new /tts and /asr endpoints that expose TTS and speech‑recognition functionality. The README is rewritten to describe the new features and clean up legacy documentation. All changes are backward‑compatible and do not introduce breaking API changes.
2026-04-04 23:56:18 +08:00
1. 前后端分离
2. 低延迟优化：防抖+SSE+AbortController
3. ProseMirror Mark系统
4. 多种交互方式
5. 智能大小限制
6. 隐私保护
7. 多语言支持
8. 主题定制
9. 文档处理
10. 语音功能
## 开发指南
代码风格: Python(4空格,snake_case) JS/TS(2空格,camelCase)
测试: pytest
构建: npm run build
feat: switch from OpenAI API to native Ollama Python client This commit refactors the LLM integration to use Ollama's native Python client instead of OpenAI-compatible API, while fixing critical template syntax errors and improving project structure. Key changes: - Replace openai package with ollama package in backend requirements - Rewrite llm.py to use ollama.AsyncClient for direct Ollama API calls - Update main.py to use non-streaming Ollama responses with thinking extraction - Fix template syntax error in MilkdownEditor.vue (GhostTextOverlay component tags) - Fix string截取错误 by using slice() instead of substring() - Add src/utils/api.js and src/utils/config.js for shared configuration - Add CORS middleware to FastAPI backend - Update prompt.py with clearer instructions for continuation generation - Add comprehensive README.md documentation BREAKING CHANGE: Environment variables OLLAMA_BASE_URL changed to OLLAMA_HOST (remove /v1/ suffix)
2026-02-07 08:53:37 +08:00
## 许可证
MIT License
Reference in New Issue Copy Permalink