Update app.py

app.py

@@ -1,60 +1,7 @@
-from fastapi import FastAPI, Query, HTTPException
-from transformers import CLIPModel, CLIPProcessor
-import torch
-import os
+from fastapi import FastAPI
 
-app = FastAPI(title="CLIP-based Document Retrieval API")
+app = FastAPI()
 
-# Load model and processor (requires Pillow)
-try:
-    model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
-    processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
-    model.eval()
-except ImportError as e:
-    raise RuntimeError(
-        "Missing dependencies. Make sure to install 'pillow'.\nInstall using:\n\npip install pillow"
-    )
-except Exception as e:
-    raise RuntimeError(f"Failed to load model or processor: {str(e)}")
-
-# Load and encode sentences
-document_path = "test.txt"
-if not os.path.exists(document_path):
-    raise FileNotFoundError(f"❌ Document not found: {document_path}")
-
-with open(document_path, "r", encoding="utf-8") as f:
-    sentences = [line.strip() for line in f if line.strip()]
-
-with torch.no_grad():
-    sentence_inputs = processor(text=sentences, return_tensors="pt", padding=True, truncation=True)
-    sentence_embeddings = model.get_text_features(**sentence_inputs)
-
-@app.get("/", tags=["Welcome"])
-async def root():
-    return {"message": "✅ CLIP-based Document Retrieval API is Running"}
-
-@app.get("/search", tags=["Search"])
-async def search(
-    query: str = Query(..., description="Search text query"),
-    top_k: int = Query(5, gt=0, le=20, description="Number of top results to return (max 20)")
-):
-    if not query.strip():
-        raise HTTPException(status_code=400, detail="Query must not be empty")
-
-    with torch.no_grad():
-        query_inputs = processor(text=[query], return_tensors="pt", padding=True, truncation=True)
-        query_embedding = model.get_text_features(**query_inputs)
-
-        # Cosine similarity
-        similarities = torch.nn.functional.cosine_similarity(query_embedding, sentence_embeddings)[0]
-        top_indices = torch.topk(similarities, k=top_k).indices
-
-        results = [{
-            "sentence": sentences[i],
-            "score": round(similarities[i].item(), 4)
-        } for i in top_indices]
-
-    return {
-        "query": query,
-        "results": results
-    }
+@app.get("/")
+def greet_json():
+    return {"welcome": "Created!"}