feat: LLM 应用网页开发及内联建议功能实现

backend/llm.py

@@ -6,44 +6,22 @@ from datetime import datetime
 import ollama
 from dotenv import load_dotenv
 
+from prompts import get_vlm_ocr_prompt
+
 load_dotenv()
 
 OLLAMA_MODEL = os.getenv('OLLAMA_MODEL', 'gpt-oss:20b')
 OLLAMA_HOST = os.getenv('OLLAMA_HOST', 'http://localhost:11434')
 VLM_MODEL = os.getenv('VLM_MODEL', 'qwen3-vl:30b')
 
-# Timeouts in seconds
-COMPLETION_TIMEOUT = 30
-OCR_TIMEOUT = 60
-CONVERT_TIMEOUT = 30
+# Timeouts in seconds (10 minutes for large model loading)
+COMPLETION_TIMEOUT = 600
+OCR_TIMEOUT = 120
+CONVERT_TIMEOUT = 60
 
 client = ollama.AsyncClient(host=OLLAMA_HOST)
 logger = logging.getLogger("llm")
 
-VLM_OCR_CONTEXT_PROMPT = """You are an OCR and visual-context extractor for markdown writing assistance.
-
-Your output will be embedded inside an HTML comment as hidden context for a text-completion model.
-
-Requirements:
-- Keep output compact: maximum 120 words.
-- Use plain text only (no markdown code fences).
-- Never output <!-- or -->.
-- Do not invent unreadable text; mark uncertain characters with ?.
-- Preserve original script for recognized text (do not forcibly translate).
-
-Return exactly this format:
-
-TEXT:
-<exact transcription of visible text; use " | " for line breaks; write "(none)" if no readable text>
-
-KEY_DETAILS:
-- <3-5 short factual bullets about relevant objects/layout>
-
-LANGUAGE:
-<dominant language(s) in visible text, e.g. English / Chinese / Mixed>
-
-SUMMARY:
-<one short sentence, <= 20 words>"""
 
 def _extract_message(response) -> tuple[str, str]:
     content = ""
@@ -166,7 +144,7 @@ async def call_vlm_ocr(image_bytes: bytes, language: str = 'auto') -> str:
                 model=VLM_MODEL,
                 messages=[{
                     'role': 'user',
-                    'content': VLM_OCR_CONTEXT_PROMPT,
+                    'content': get_vlm_ocr_prompt(),
                     'images': [image_bytes]
                 }],
                 stream=False,