Create app.py

app.py

@@ -1,12 +1,17 @@
-# app.py
-from fastapi import FastAPI, UploadFile
+from fastapi import FastAPI, UploadFile, File
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.staticfiles import StaticFiles
-import os
+import pandas as pd
+from sentence_transformers import SentenceTransformer
+import numpy as np
+from typing import List, Dict
+import json
 from anthropic import Anthropic
+import os
 
 app = FastAPI()
 anthropic = Anthropic(api_key=os.environ["ANTHROPIC_API_KEY"])
+model = SentenceTransformer('all-MiniLM-L6-v2')
 
 app.add_middleware(
     CORSMiddleware,
@@ -15,4 +20,47 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
+@app.post("/api/process-file")
+async def process_file(file: UploadFile = File(...)):
+    content = await file.read()
+    
+    # Save temporarily
+    with open(f"temp_{file.filename}", "wb") as f:
+        f.write(content)
+    
+    # Read file
+    df = pd.read_excel(f"temp_{file.filename}") if file.filename.endswith('.xlsx') else pd.read_csv(f"temp_{file.filename}")
+    
+    # Create text representations
+    text_reps = []
+    for _, row in df.iterrows():
+        text_rep = " ".join([f"{col}: {val}" for col, val in row.items()])
+        text_reps.append(text_rep)
+    
+    # Generate embeddings
+    embeddings = model.encode(text_reps)
+    
+    metadata = {
+        'columns': list(df.columns),
+        'row_count': len(df),
+        'numerical_cols': list(df.select_dtypes(include=[np.number]).columns),
+        'categorical_cols': list(df.select_dtypes(include=['object']).columns)
+    }
+    
+    os.remove(f"temp_{file.filename}")
+    
+    return {
+        'embeddings': embeddings.tolist(),
+        'metadata': metadata,
+        'raw_data': df.to_dict('records')
+    }
+
+@app.post("/api/query")
+async def query_data(query: str, embeddings: List[List[float]], k: int = 5):
+    query_embedding = model.encode([query])[0]
+    similarities = np.dot(embeddings, query_embedding)
+    indices = np.argsort(similarities)[-k:][::-1].tolist()
+    return {"similar_indices": indices}
+
+# Mount static files at root
 app.mount("/", StaticFiles(directory="static", html=True), name="static")