update

Dockerfile

@@ -10,7 +10,7 @@ ENV TRANSFORMERS_CACHE=/app/.cache
 # 修改目录的所有者和权限
 RUN mkdir -p /app
 RUN chown -R appuser:appuser /app
-RUN chmod -R 755 /app
+RUN chmod -R 777 /app
 
 RUN mkdir -p /app/.cache
 

Dockerfile copy

@@ -0,0 +1,40 @@
+# 使用官方 Python 基础镜像
+FROM python:3.9-slim
+
+# 创建 appuser 用户和组
+RUN groupadd -r appuser && useradd -r -g appuser appuser
+
+# 设置环境变量
+ENV TRANSFORMERS_CACHE=/app/.cache
+
+# 修改目录的所有者和权限
+RUN mkdir -p /app
+RUN chown -R appuser:appuser /app
+RUN chmod -R 755 /app
+
+RUN mkdir -p /app/.cache
+
+# 设置工作目录
+WORKDIR /app
+
+# 将 /app 目录的所有权赋予 appuser
+
+
+# 复制依赖文件到容器中
+COPY requirements.txt .
+
+# 安装依赖
+RUN pip install --no-cache-dir -r requirements.txt
+
+# 复制项目代码到容器中
+COPY . .
+
+# 设置 /app/.cache 及其子目录的权限
+RUN chown -R appuser:appuser /app/.cache
+RUN chmod -R 777 /app/.cache
+
+# 切换到 appuser 用户
+USER appuser
+
+# 指定容器启动时运行的命令
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app copy.py

@@ -0,0 +1,68 @@
+from fastapi import FastAPI, HTTPException, Depends, Header
+from pydantic import BaseModel, Field
+from sentence_transformers import SentenceTransformer
+import logging, os
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# 定义依赖项来校验 Authorization
+async def check_authorization(authorization: str = Header(..., alias="Authorization")):
+    # 去掉 Bearer 和后面的空格
+    if not authorization.startswith("Bearer "):
+        raise HTTPException(status_code=401, detail="Invalid Authorization header format")
+    
+    token = authorization[len("Bearer "):]
+    if token != os.environ.get("AUTHORIZATION"):
+        raise HTTPException(status_code=401, detail="Unauthorized access")
+    return token
+
+app = FastAPI()
+
+try:
+    # Load the BGE Reranker model
+    model = SentenceTransformer("BAAI/bge-reranker-large")
+    logger.info("Reranker model loaded successfully.")
+except Exception as e:
+    logger.error(f"Failed to load model: {e}")
+    raise HTTPException(status_code=500, detail="Model loading failed. Check logs for details.")
+
+class RerankerRequest(BaseModel):
+    query: str = Field(..., min_length=1, max_length=1000, description="The query text.")
+    documents: list[str] = Field(..., min_items=2, description="A list of documents to rerank.")
+    truncate: bool = Field(False, description="Whether to truncate the documents.")
+
+@app.post("/rerank")
+# async def rerank(request: RerankerRequest, authorization: str = Depends(check_authorization)):
+async def rerank(request: RerankerRequest):
+    query = request.query
+    documents = request.documents
+
+    try:
+        if not query or not documents:
+            raise HTTPException(status_code=400, detail="Query and documents must be provided.")
+
+        from sentence_transformers import util
+
+        # Calculate embeddings for the query and documents
+        query_embedding = model.encode(query, convert_to_tensor=True)
+        document_embeddings = model.encode(documents, convert_to_tensor=True)
+
+        # Calculate cosine similarity between the query and each document
+        scores = util.cos_sim(query_embedding, document_embeddings)[0].tolist()
+
+        # Create a list of dictionaries containing the document and its score
+        results = [{"document": doc, "score": score} for doc, score in zip(documents, scores)]
+
+        # Sort the results by score in descending order
+        ranked_results = sorted(results, key=lambda x: x["score"], reverse=True)
+
+        return {
+            "object": "list",
+            "data": ranked_results,
+            "model": "BAAI/bge-reranker-large"
+        }
+    except Exception as e:
+        logger.error(f"Error processing reranking: {e}")
+        raise HTTPException(status_code=500, detail="Internal Server Error. Check logs for details.")