commit

Dockerfile

@@ -0,0 +1,25 @@
+# Use a slim Python 3.11 base image
+FROM python:3.13-slim
+
+# Avoid writing .pyc files and enable unbuffered stdout/stderr
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+# Set the working directory
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
+
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+
+COPY . .
+
+
+EXPOSE 7860
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,69 @@
+import os
+from uuid import uuid4
+from fastapi import FastAPI
+from fastapi.responses import FileResponse
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.staticfiles import StaticFiles
+from pydantic import BaseModel, Field
+from sentence_transformers import SentenceTransformer
+import weaviate
+from weaviate.classes.init import Auth
+
+WEAVIATE_URL = os.getenv("WEAVIATE_URL", "https://hrdhwtqlrkqmc8sfizwvpq.c0.asia-southeast1.gcp.weaviate.cloud")
+WEAVIATE_API_KEY = os.getenv("WEAVIATE_API_KEY", "pMDX7ysJPkSTUMdV3gEwxhGmyB7wB301fLaJ")
+CLASS_NAME = "PdfChunk"
+
+app = FastAPI()
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+app.mount("/static", StaticFiles(directory="static"), name="static")
+
+model = SentenceTransformer("all-MiniLM-L6-v2")
+
+client = weaviate.connect_to_weaviate_cloud(
+    cluster_url=WEAVIATE_URL,
+    auth_credentials=Auth.api_key(WEAVIATE_API_KEY),
+)
+
+class QueryRequest(BaseModel):
+    text: str = Field(..., min_length=1)
+    top_k: int = Field(default=7, ge=1, le=100)
+
+@app.get("/")
+def root():
+    return {"message": "PDF RAG API is running. Use POST / to query."}
+
+@app.get("/openapi.yaml")
+def serve_openapi_yaml():
+    return FileResponse("static/openapi.yaml", media_type="text/yaml")
+
+@app.post("/")
+def query_weaviate(q: QueryRequest):
+    try:
+        query_vector = model.encode(q.text).tolist()
+        collection = client.collections.get(CLASS_NAME)
+
+        results = collection.query.near_vector(
+            near_vector=query_vector,
+            limit=q.top_k,
+        )
+
+        return {
+            "query": q.text,
+            "results": [
+                {
+                    "text": obj.properties.get("text", ""),
+                    "source": obj.properties.get("source", ""),
+                }
+                for obj in results.objects
+            ]
+        }
+
+    except Exception as e:
+        return {"error": str(e)}

requirements.txt

@@ -0,0 +1,5 @@
+fastapi
+uvicorn
+pydantic
+sentence-transformers
+weaviate-client