ydy0615
eb6e8bbfff
- Configure Vite dev server to proxy /v1 requests to backend - Change backend port from 8000 to 8001 - Simplify API URLs to relative paths instead of absolute localhost URLs - Increase debounce delay from 500ms to 1000ms for better stability - Update README documentation to reflect all changes
113 lines
3.7 KiB
Python
113 lines
3.7 KiB
Python
from fastapi import FastAPI
|
|
from fastapi.middleware.cors import CORSMiddleware
|
|
from fastapi.responses import StreamingResponse, JSONResponse
|
|
from pydantic import BaseModel
|
|
import json
|
|
import base64
|
|
import uuid
|
|
import logging
|
|
|
|
from prompt import build_prompt, prepare_prompt_context
|
|
from llm import call_ollama, call_vlm_ocr
|
|
|
|
logging.basicConfig(
|
|
level=logging.INFO,
|
|
format="%(asctime)s %(levelname)s %(name)s - %(message)s",
|
|
)
|
|
logger = logging.getLogger("api")
|
|
|
|
app = FastAPI()
|
|
|
|
app.add_middleware(
|
|
CORSMiddleware,
|
|
allow_origins=["*"],
|
|
allow_credentials=True,
|
|
allow_methods=["*"],
|
|
allow_headers=["*"],
|
|
)
|
|
|
|
class CompletionRequest(BaseModel):
|
|
prefix: str
|
|
suffix: str
|
|
languageId: str = 'markdown'
|
|
|
|
class OCRRequest(BaseModel):
|
|
image: str
|
|
filename: str = "image.jpg"
|
|
language: str = 'auto'
|
|
|
|
|
|
def _preview(text: str, limit: int = 80) -> str:
|
|
value = (text or "").replace("\n", "\\n")
|
|
if len(value) <= limit:
|
|
return value
|
|
return value[:limit] + "..."
|
|
|
|
@app.post("/v1/completions")
|
|
async def create_completion(request: CompletionRequest):
|
|
request_id = str(uuid.uuid4())[:8]
|
|
try:
|
|
logger.info(
|
|
"[%s] /v1/completions prefix_chars=%d suffix_chars=%d lang=%s prefix_tail='%s' suffix_head='%s'",
|
|
request_id,
|
|
len(request.prefix or ""),
|
|
len(request.suffix or ""),
|
|
request.languageId,
|
|
_preview((request.prefix or "")[-120:]),
|
|
_preview((request.suffix or "")[:120]),
|
|
)
|
|
llm_prefix, llm_suffix = prepare_prompt_context(request.prefix or "", request.suffix or "")
|
|
logger.info("[%s] llm_input_prefix=%r", request_id, llm_prefix)
|
|
logger.info("[%s] llm_input_suffix=%r", request_id, llm_suffix)
|
|
prompt = build_prompt(request.prefix, request.suffix, request.languageId)
|
|
result = await call_ollama(prompt, tag=f"{request_id}-primary", temperature=0.7)
|
|
|
|
content = result["content"] or ""
|
|
if not content.strip():
|
|
logger.warning("[%s] primary returned empty content, returning empty result", request_id)
|
|
logger.info(
|
|
"[%s] completion resolved source=primary content_chars=%d content_preview='%s'",
|
|
request_id,
|
|
len(content),
|
|
_preview(content, 120),
|
|
)
|
|
|
|
async def generate():
|
|
yield f"data: {json.dumps({'content': content})}\n\n"
|
|
yield f"data: {json.dumps({'done': True})}\n\n"
|
|
|
|
return StreamingResponse(generate(), media_type="text/event-stream")
|
|
|
|
except Exception as e:
|
|
logger.exception("[%s] /v1/completions failed: %s", request_id, e)
|
|
return JSONResponse(content={"error": str(e)}, status_code=500)
|
|
|
|
@app.post("/v1/ocr")
|
|
async def ocr_image(request: OCRRequest):
|
|
request_id = str(uuid.uuid4())[:8]
|
|
try:
|
|
logger.info(
|
|
"[%s] /v1/ocr filename=%s language=%s image_base64_chars=%d",
|
|
request_id,
|
|
request.filename,
|
|
request.language,
|
|
len(request.image or ""),
|
|
)
|
|
image_bytes = base64.b64decode(request.image)
|
|
logger.info("[%s] /v1/ocr decoded image_bytes=%d", request_id, len(image_bytes))
|
|
result = await call_vlm_ocr(image_bytes, request.language)
|
|
logger.info(
|
|
"[%s] /v1/ocr success text_chars=%d text_preview='%s'",
|
|
request_id,
|
|
len(result or ""),
|
|
_preview(result or "", 120),
|
|
)
|
|
return {"text": result, "filename": request.filename}
|
|
except Exception as e:
|
|
logger.exception("[%s] /v1/ocr failed: %s", request_id, e)
|
|
return JSONResponse(content={"error": str(e)}, status_code=500)
|
|
|
|
if __name__ == "__main__":
|
|
import uvicorn
|
|
uvicorn.run(app, host="0.0.0.0", port=8001)
|