Spaces:

cryogenic22
/

InsightO

Sleeping

App Files Files Community

cryogenic22 commited on Dec 24, 2024

Commit

b2607f4

verified ·

1 Parent(s): f0a6739

Update app.py

Browse files

Files changed (1) hide show

app.py +117 -22

app.py CHANGED Viewed

@@ -1,34 +1,133 @@
 from fastapi import FastAPI, UploadFile, File
-from fastapi.middleware.cors import CORSMiddleware
-from fastapi.staticfiles import StaticFiles
-from fastapi.responses import FileResponse
 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,
-    allow_origins=["*"],
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-@app.get("/")
-async def read_root():
-    return FileResponse('static/index.html')
 @app.post("/api/process-file")
 async def process_file(file: UploadFile = File(...)):
     content = await file.read()
     with open(f"temp_{file.filename}", "wb") as f:
         f.write(content)
@@ -40,7 +139,6 @@ async def process_file(file: UploadFile = File(...)):
         text_reps.append(text_rep)
     embeddings = model.encode(text_reps)
     metadata = {
         'columns': list(df.columns),
         'row_count': len(df),
@@ -49,7 +147,6 @@ async def process_file(file: UploadFile = File(...)):
     }
     os.remove(f"temp_{file.filename}")
     return {
         'embeddings': embeddings.tolist(),
         'metadata': metadata,
@@ -61,6 +158,4 @@ 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}
-app.mount("/static", StaticFiles(directory="static"), name="static")

 from fastapi import FastAPI, UploadFile, File
+from fastapi.responses import HTMLResponse
 import pandas as pd
 from sentence_transformers import SentenceTransformer
 import numpy as np
+from typing import List
 import os
 app = FastAPI()
 model = SentenceTransformer('all-MiniLM-L6-v2')
+@app.get("/", response_class=HTMLResponse)
+async def root():
+    return """
+    <!DOCTYPE html>
+    <html lang="en">
+    <head>
+        <meta charset="UTF-8">
+        <meta name="viewport" content="width=device-width, initial-scale=1.0">
+        <title>Analytics Dashboard</title>
+        <script src="https://cdn.tailwindcss.com"></script>
+        <script src="https://unpkg.com/react@18/umd/react.development.js" crossorigin></script>
+        <script src="https://unpkg.com/react-dom@18/umd/react-dom.development.js" crossorigin></script>
+        <script src="https://unpkg.com/babel-standalone@6/babel.min.js"></script>
+        <script src="https://unpkg.com/recharts@2.1.9/umd/Recharts.js"></script>
+        <script type="text/babel">
+            const { useState } = React;
+            const { BarChart, Bar, XAxis, YAxis, Tooltip, ResponsiveContainer } = Recharts;
+            function App() {
+                const [data, setData] = useState(null);
+                const [query, setQuery] = useState('');
+                const [insights, setInsights] = useState([]);
+                const handleFileUpload = async (event) => {
+                    const file = event.target.files[0];
+                    const formData = new FormData();
+                    formData.append('file', file);
+                    const response = await fetch('/api/process-file', {
+                        method: 'POST',
+                        body: formData,
+                    });
+                    const result = await response.json();
+                    setData(result);
+                };
+                const handleQuery = async () => {
+                    if (!data || !query) return;
+                    const response = await fetch('/api/query', {
+                        method: 'POST',
+                        headers: { 'Content-Type': 'application/json' },
+                        body: JSON.stringify({
+                            query,
+                            embeddings: data.embeddings
+                        }),
+                    });
+                    const result = await response.json();
+                    const newInsights = result.similar_indices.map(idx => data.raw_data[idx]);
+                    setInsights(newInsights);
+                };
+                return (
+                    <div className="p-6 max-w-6xl mx-auto">
+                        <h1 className="text-2xl font-bold mb-6">Data Analytics Dashboard</h1>
+                        <div className="mb-6">
+                            <label className="block mb-2 text-sm font-medium">Upload Data File</label>
+                            <input
+                                type="file"
+                                onChange={handleFileUpload}
+                                accept=".csv,.xlsx,.xls"
+                                className="block w-full text-sm text-gray-500 file:mr-4 file:py-2 file:px-4 file:rounded-md file:border-0 file:text-sm file:font-semibold file:bg-blue-50 file:text-blue-700 hover:file:bg-blue-100"
+                            />
+                        </div>
+                        {data && (
+                            <div className="space-y-6">
+                                <div>
+                                    <input
+                                        type="text"
+                                        value={query}
+                                        onChange={(e) => setQuery(e.target.value)}
+                                        placeholder="Ask a question about your data..."
+                                        className="w-full p-2 border rounded"
+                                    />
+                                    <button
+                                        onClick={handleQuery}
+                                        className="mt-2 px-4 py-2 bg-blue-600 text-white rounded hover:bg-blue-700"
+                                    >
+                                        Search
+                                    </button>
+                                </div>
+                                {insights.length > 0 && (
+                                    <div className="mt-6">
+                                        <h3 className="text-lg font-semibold mb-4">Related Insights</h3>
+                                        <div className="h-64">
+                                            <ResponsiveContainer width="100%" height="100%">
+                                                <BarChart data={insights}>
+                                                    {Object.keys(insights[0] || {}).map((key) => (
+                                                        <Bar key={key} dataKey={key} fill="#8884d8" />
+                                                    ))}
+                                                    <XAxis />
+                                                    <YAxis />
+                                                    <Tooltip />
+                                                </BarChart>
+                                            </ResponsiveContainer>
+                                        </div>
+                                    </div>
+                                )}
+                            </div>
+                        )}
+                    </div>
+                );
+            }
+            ReactDOM.render(<App />, document.getElementById('root'));
+        </script>
+    </head>
+    <body>
+        <div id="root"></div>
+    </body>
+    </html>
+    """
 @app.post("/api/process-file")
 async def process_file(file: UploadFile = File(...)):
     content = await file.read()
     with open(f"temp_{file.filename}", "wb") as f:
         f.write(content)
         text_reps.append(text_rep)
     embeddings = model.encode(text_reps)
     metadata = {
         'columns': list(df.columns),
         'row_count': len(df),
     }
     os.remove(f"temp_{file.filename}")
     return {
         'embeddings': embeddings.tolist(),
         'metadata': metadata,
     query_embedding = model.encode([query])[0]
     similarities = np.dot(embeddings, query_embedding)
     indices = np.argsort(similarities)[-k:][::-1].tolist()
+    return {"similar_indices": indices}