init

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
 from time import sleep
+import json
 from pymongo import MongoClient
 from bson import ObjectId
 from openai import OpenAI
@@ -17,7 +18,7 @@ trips_collection = client[db_name]['smart_trips']
 
 def get_restaurants(search, location, meters):
 
-    newTrip = pre_aggregate_meters(location, meters)
+    newTrip, pre_agg = pre_aggregate_meters(location, meters)
 
     response = openai_client.embeddings.create(
             input=search,
@@ -25,7 +26,7 @@ def get_restaurants(search, location, meters):
             dimensions=256
         )
 
-    restaurant_docs = list(trips_collection.aggregate([{
+    vectorQuery = {
         "$vectorSearch": {
             "index" : "vector_index",
             "queryVector": response.data[0].embedding,
@@ -33,7 +34,8 @@ def get_restaurants(search, location, meters):
             "numCandidates": 10,
             "limit": 3,
             "filter": {"searchTrip": newTrip}
-        }},
+        }}
+    restaurant_docs = list(trips_collection.aggregate([vectorQuery,
         {"$project": {"_id" : 0, "embedding": 0}}]))
 
     
@@ -57,15 +59,13 @@ def get_restaurants(search, location, meters):
         restaurant_string = f"\'{first_restaurant}\', \'{second_restaurant}\', \'{third_restaurant}\'"
     iframe = '<iframe style="background: #FFFFFF;border: none;border-radius: 2px;box-shadow: 0 2px 10px 0 rgba(70, 76, 79, .2);" width="640" height="480" src="https://charts.mongodb.com/charts-paveldev-wiumf/embed/charts?id=65c24b0c-2215-4e6f-829c-f484dfd8a90c&filter={\'restaurant_id\':{$in:['  + restaurant_string  + ']}}&maxDataAge=3600&theme=light&autoRefresh=true"></iframe>'
 
-    return chat_response.choices[0].message.content, iframe
+    return chat_response.choices[0].message.content, iframe,str(pre_agg), str(vectorQuery)
     
 
 def pre_aggregate_meters(location, meters):
 
     tripId = ObjectId()
-
-    result = restaurants_collection.aggregate([
-        {
+    pre_aggregate_pipeline =  [{
             "$geoNear": {
             "near": location,
             "distanceField": "distance",
@@ -83,14 +83,14 @@ def pre_aggregate_meters(location, meters):
             "$merge": {
                 "into": "smart_trips"
             }
-        }   
-    ]);
+        } ]
+
+    result = restaurants_collection.aggregate(pre_aggregate_pipeline);
 
-    print(result)
     print(trips_collection.count_documents({"searchTrip": tripId}));
     sleep(10)
 
-    return tripId
+    return tripId, pre_aggregate_pipeline
 
 
 with gr.Blocks() as demo:
@@ -115,15 +115,17 @@ with gr.Blocks() as demo:
         }), ("home",{
             "type": "Point",
             "coordinates": [
-            40.701975, -74.013686
+            -74.013686, 40.701975
             ]
         }), ("park", {
             "type": "Point",
-            "coordinates": [40.720777, -74.000468
+            "coordinates": [ -74.000468,40.720777
             ]
         })], label="Location", info="What location you need?"),
         gr.Slider(minimum=500, maximum=10000, randomize=False, step=5, label="Radius in meters")],
-       [gr.Textbox(label="MongoDB Vector Recommendations", placeholder="Results will be displayed here"), "html"],
+       [gr.Textbox(label="MongoDB Vector Recommendations", placeholder="Results will be displayed here"), "html",
+        gr.Code(label="Pre-aggregate pipeline",language="json" ),
+        gr.Code(label="Vector Query", language="json")],
         
     )
     #radio.change(location_searched, loc, out)