ydy0615/llm-in-text
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
32 Commits 2 Branches 0 Tags
d2b64ad5d61c594032f052e60e4f9308622ea78d
Commit Graph

5 Commits

Author SHA1 Message Date
ydy0615
d2b64ad5d6 feat: add IP geolocation tracking and include location in prompts 
- Add GeoLite2-City.mmdb database for IP lookup
- Create geoip.py module for IP location services
- Extract client IP from requests and log location info
- Pass location context to LLM prompts for enhanced responses
 2026-02-18 08:59:28 +08:00
ydy0615
1e58c18bbc feat: add image hash-based OCR caching with 100MB size limit 
- Implement SHA-256 image hashing to cache OCR results and avoid re-processing identical images
- Add 100MB file size limit for image uploads with user-friendly error messages
- Clear ghost suggestions when uploading new images to prevent interference
- Optimize size limit calculation in copilot plugin to include OCR context
- Remove debug logging from production code
- Add image processing optimization plan document

BREAKING CHANGE: Image upload size limit is now enforced at 100MB (previously unlimited)
 2026-02-15 22:17:37 +08:00
“ydy0615”
65d4a57d33 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
“ydy0615”
16e76e1e90 refactor(editor): migrate to Milkdown with LaTeX support and clean up legacy code 
- Removed old contenteditable-based MarkdownEditor component
- Integrated Milkdown Crepe with LaTeX (KaTeX) rendering support
- Simplified inline suggestion plugin using ProseMirror decorations
- Removed debug logging and unused components (HelloWorld, plan files)
- Increased debounce from 150ms to 500ms for better performance
- Fixed SSE JSON serialization in backend main.py
 2026-02-12 18:52:16 +08:00
ydy0615
2abf276d10 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 09:10:26 +08:00