app.py

from fastapi import FastAPI
from pydantic import BaseModel
from sentence_transformers import SentenceTransformer
import numpy as np
import json

# Load your JSON data
with open("data.json") as f:
    data = json.load(f)

# Initialize model
model = SentenceTransformer('all-MiniLM-L6-v2')

# Precompute embeddings for all file names
file_names = [item["file_name"] for item in data]
file_embeddings = model.encode(file_names)

app = FastAPI()

class Query(BaseModel):
    text: str

@app.post("/search")
async def search(query: Query):
    # Encode query
    query_embedding = model.encode([query.text])
    
    # Compute cosine similarity
    similarities = np.dot(file_embeddings, query_embedding.T).flatten()
    
    # Find best match
    best_match_idx = np.argmax(similarities)
    
    return {
        "best_match": data[best_match_idx]["file_name"],
        "similarity_score": float(similarities[best_match_idx])
    }