ydy0615/llm-in-text
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
65d4a57d3340b672c23ed90ae9a4b9de35dfdf13
llm-in-text/backend/__pycache__/prompt.cpython-313.pyc

26 lines
1.5 KiB
Plaintext
Raw Normal View History

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
<EFBFBD>
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
-ƍi<C68D><00><00>.<00>SSKrSSKJr S\S\S\4Sjrg)<07>N)<01>Tuple<6C>prefix<69>suffix<69>returnc<00><00>SnU(aUSnX-nUSSnURS5nU(aURS5O/nSRXB*S5nSRUSS5nSUSUS 3nUR5$)
uo
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
改进后的提示词构建函数。
使用更明确的指令来引导模型生成高质量的续写内容。
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
<EFBFBD>r<00>N<>
<EFBFBD>u<>You are an expert writing assistant. Continue the text naturally.
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
CONTEXT:
⟨CURSOR⟩ marks where to continue.
- Before ⟨CURSOR⟩: existing text
- After ⟨CURSOR⟩: following context (if any)
RULES:
- Match existing style, tone, and terminology
- Maintain logical flow
- Write only the continuation, nothing else
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
- IMPORTANT: Start continuation directly from ⟨CURSOR⟩ position
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
TEXT:
u ⟨CURSOR⟩z
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
CONTINUATION:)<03>split<69>join<69>strip) rr<00>MAX_CONTEXT_LINES<45>
first_char<EFBFBD> prefix_lines<65> suffix_lines<65> recent_prefix<69> recent_suffix<69>prompts <20>./Users/allenyuan/llm-in-text/backend/prompt.py<70> build_promptrs<><00><00>
<1B><15><0E><1B>A<EFBFBD>Y<EFBFBD>
<EFBFBD><17>$<24><06><17><01><02><1A><06><19><<3C><<3C><04>%<25>L<EFBFBD>)/<2F>6<EFBFBD><<3C><<3C><04>%<25>R<EFBFBD>L<EFBFBD><18>I<EFBFBD>I<EFBFBD>l<EFBFBD>+=<3D>+><3E>?<3F>@<40>M<EFBFBD><18>I<EFBFBD>I<EFBFBD>l<EFBFBD>2<EFBFBD>A<EFBFBD>.<2E>/<2F>M<EFBFBD><01><0F><0F>|<7C>M<EFBFBD>?<3F>+<0E><11>F<EFBFBD>$ <12><<3C><<3C>><3E><19>)<05>os<6F>typingr<00>strr<00>rr<00><module>rs%<00><01> <09><18>%<1A><13>%<1A>c<EFBFBD>%<1A>c<EFBFBD>%r
Reference in New Issue Copy Permalink