for integration with react

app.py

@@ -1,23 +1,39 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
 import os
-import gradio as gr
 import google.generativeai as genai
 import faiss
 import numpy as np
 from sentence_transformers import SentenceTransformer
 from pymongo import MongoClient
+import uvicorn
+from fastapi.middleware.cors import CORSMiddleware
+
+app = FastAPI()
+
+# CORS Middleware to allow frontend to access API
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # Allow all origins (React App)
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
 
 # ✅ Configure Gemini API
 genai.configure(api_key=os.getenv("GEMINI_API_KEY"))
 
-# ✅ Load Sentence Transformer Model
-model = SentenceTransformer('all-MiniLM-L6-v2')
+# ✅ Sentence Transformer
+model = SentenceTransformer("all-MiniLM-L6-v2")
 
-# ✅ Connect to MongoDB
+# ✅ MongoDB
 MONGO_URI = os.getenv("MONGO_URI")
 client = MongoClient(MONGO_URI)
 db = client["AiWork"]
 
-# ✅ Fetch latest data dynamically
+class QueryRequest(BaseModel):
+    email: str
+    query: str
+
 def fetch_latest_data():
     return {
         "users": list(db.users.find()),
@@ -29,6 +45,8 @@ def fetch_latest_data():
     }
 
 def generate_sentences(db):
+    # Your existing logic here...
+
     users, teams, projects, modules, documents, schedules = (
         db["users"], db["teams"], db["projects"], db["modules"], db["documents"], db["schedules"]
     )
@@ -99,8 +117,8 @@ def generate_sentences(db):
     
     return user_sentences
 
-# ✅ Update FAISS Index dynamically
 def update_faiss_index(user_sentences):
+    # Your existing FAISS logic here...
     faiss_indices = {}  
     for email, categories in user_sentences.items():
         sentences = sum(categories.values(), [])  
@@ -118,8 +136,8 @@ def update_faiss_index(user_sentences):
 
     return faiss_indices
 
-# ✅ Query FAISS Index
 def get_relevant_sentences(email, query, faiss_indices):
+    # Your FAISS query logic here...
     if email not in faiss_indices:
         return ["User not found or no data available."]
     
@@ -138,31 +156,28 @@ def get_relevant_sentences(email, query, faiss_indices):
 
     return filtered_sentences if filtered_sentences else ["No relevant information found."]
 
-# ✅ Generate response using Gemini API
+
 def generate_response(email, query):
     filtered_sentences = get_relevant_sentences(email, query, faiss_indices)
-    
-    if filtered_sentences == ["No relevant information found."]:
-        return "No relevant information found."
-    
-    prompt = f"Based on query '{query}', generate a short answer using:\n\n" + "\n".join(filtered_sentences)
+    prompt = f"Query: {query}\n\n" + "\n".join(filtered_sentences)
     model = genai.GenerativeModel("gemini-1.5-flash")
     response = model.generate_content(prompt)
-    
     return response.text
 
-# ✅ Real-time data update function
-def real_time_update():
-    latest_data = fetch_latest_data()  
-    user_sentences = generate_sentences(latest_data)  
-    return update_faiss_index(user_sentences)
+@app.post("/chat")
+async def chat(request: QueryRequest):
+    try:
+        response = generate_response(request.email, request.query)
+        return {"response": response}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
 
-# ✅ Run initial update
-faiss_indices = real_time_update()
+@app.get("/")
+def home():
+    return {"message": "AI Workspace Backend Running"}
 
-# ✅ Gradio Web UI
-def chat(email, query):
-    return generate_response(email, query)
+# Initial Update
+faiss_indices = update_faiss_index(generate_sentences(fetch_latest_data()))
 
-iface = gr.Interface(fn=chat, inputs=["text", "text"], outputs="text", title="AI Workspace Assistant")
-iface.launch()
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=7860)