Delete app.py

app.py

@@ -1,44 +0,0 @@
-from fastapi import FastAPI, Query
-from transformers import CLIPModel, CLIPProcessor
-import torch
-
-# Initialize FastAPI
-app = FastAPI()
-
-# Load CLIP model and processor from Hugging Face
-model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
-processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
-
-# Load and process document
-with open("test.txt", "r", encoding="utf-8") as f:
-    sentences = [line.strip() for line in f if line.strip()]
-
-# Encode document sentences
-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("/")
-def welcome():
-    return {"message": "CLIP-based Document Retrieval Service is Running!"}
-
-@app.get("/search")
-def search(text: str = Query(..., description="Enter your query"), top_k: int = 5):
-    with torch.no_grad():
-        query_inputs = processor(text=[text], return_tensors="pt", padding=True, truncation=True)
-        query_embedding = model.get_text_features(**query_inputs)
-
-        # Compute cosine similarity
-        scores = torch.nn.functional.cosine_similarity(query_embedding, sentence_embeddings)[0]
-        top_indices = torch.topk(scores, k=top_k).indices
-
-        results = [{
-            "matched_sentence": sentences[i],
-            "similarity_score": round(scores[i].item(), 3)
-        } for i in top_indices]
-
-    return {
-        "query": text,
-        "top_matches": results
-    }
-