Spaces:
Runtime error
Runtime error
| import gradio as gr | |
| from time import sleep | |
| import json | |
| from pymongo import MongoClient | |
| from bson import ObjectId | |
| from openai import OpenAI | |
| openai_client = OpenAI() | |
| import os | |
| ## Get the restaurants based on the search and location | |
| def get_restaurants(search, location, meters): | |
| try: | |
| uri = os.environ.get('MONGODB_ATLAS_URI') | |
| client = MongoClient(uri) | |
| db_name = 'whatscooking' | |
| collection_name = 'restaurants' | |
| restaurants_collection = client[db_name][collection_name] | |
| trips_collection = client[db_name]['smart_trips'] | |
| except: | |
| print("Error Connecting to the MongoDB Atlas Cluster") | |
| # Pre aggregate restaurants collection based on chosen location and radius, the output is stored into | |
| # trips_collection | |
| try: | |
| newTrip, pre_agg = pre_aggregate_meters(restaurants_collection, location, meters) | |
| ## Get openai embeddings | |
| response = openai_client.embeddings.create( | |
| input=search, | |
| model="text-embedding-3-small", | |
| dimensions=256 | |
| ) | |
| ## prepare the similarity search on current trip | |
| vectorQuery = { | |
| "$vectorSearch": { | |
| "index" : "vector_index", | |
| "queryVector": response.data[0].embedding, | |
| "path" : "embedding", | |
| "numCandidates": 10, | |
| "limit": 3, | |
| "filter": {"searchTrip": newTrip} | |
| }} | |
| ## Run the retrieved documents through a RAG system. | |
| restaurant_docs = list(trips_collection.aggregate([vectorQuery, | |
| {"$project": {"_id" : 0, "embedding": 0}}])) | |
| chat_response = openai_client.chat.completions.create( | |
| model="gpt-3.5-turbo", | |
| messages=[ | |
| {"role": "system", "content": "You are a helpful restaurant assistant. You will get a context if the context is not relevat to the user query please address that and not provide by default the restaurants as is."}, | |
| { "role": "user", "content": f"Find me the 2 best restaurant and why based on {search} and {restaurant_docs}. explain trades offs and why I should go to each one. You can mention the third option as a possible alternative."} | |
| ] | |
| ) | |
| ## Removed the temporary documents | |
| trips_collection.delete_many({"searchTrip": newTrip}) | |
| if len(restaurant_docs) == 0: | |
| return "No restaurants found", '<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\':\'\'}&maxDataAge=3600&theme=light&autoRefresh=true"></iframe>', str(pre_agg), str(vectorQuery) | |
| ## Build the map filter | |
| first_restaurant = restaurant_docs[0]['restaurant_id'] | |
| second_restaurant = restaurant_docs[1]['restaurant_id'] | |
| third_restaurant = restaurant_docs[2]['restaurant_id'] | |
| 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\':{$in:[' + restaurant_string + ']}}&maxDataAge=3600&theme=light&autoRefresh=true"></iframe>' | |
| client.close() | |
| return chat_response.choices[0].message.content, iframe,str(pre_agg), str(vectorQuery) | |
| except Exception as e: | |
| print(e) | |
| return "Your query caused an error, please retry with allowed input only ...", '<iframe style="background: #FFFFFF;border: none;border-radius: 2px;box-shadow: 0 2px 10px 0 rgba(70, 76, 79, .2);" width="640" height="480" src="https://charts.mongodb.com/charts-paveldev-wiumf/embed/charts?id=65c24b0c-2215-4e6f-829c-f484dfd8a90c&filter={\'restaurant_id\':\'\'}&maxDataAge=3600&theme=light&autoRefresh=true"></iframe>', str(pre_agg), str(vectorQuery) | |
| def pre_aggregate_meters(restaurants_collection, location, meters): | |
| ## Do the geo location preaggregate and assign the search trip id. | |
| tripId = ObjectId() | |
| pre_aggregate_pipeline = [{ | |
| "$geoNear": { | |
| "near": location, | |
| "distanceField": "distance", | |
| "maxDistance": meters, | |
| "spherical": True, | |
| }, | |
| }, | |
| { | |
| "$addFields": { | |
| "searchTrip" : tripId, | |
| "date" : tripId.generation_time | |
| } | |
| }, | |
| { | |
| "$merge": { | |
| "into": "smart_trips" | |
| } | |
| } ] | |
| result = restaurants_collection.aggregate(pre_aggregate_pipeline); | |
| sleep(3) | |
| return tripId, pre_aggregate_pipeline | |
| with gr.Blocks() as demo: | |
| gr.Markdown( | |
| """ | |
| # MongoDB's Vector Restaurant planner | |
| Start typing below to see the results. You can search a specific cuisine for you and choose 3 predefined locations. | |
| The radius specify the distance from the start search location. This space uses the dataset called [whatscooking.restaurants](https://huggingface.co/datasets/AIatMongoDB/whatscooking.restaurants) | |
| """) | |
| # Create the interface | |
| gr.Interface( | |
| get_restaurants, | |
| [gr.Textbox(placeholder="What type of dinner are you looking for?"), | |
| gr.Radio(choices=[ | |
| ("Timesquare Manhattan", { | |
| "type": "Point", | |
| "coordinates": [-73.98527039999999, 40.7589099] | |
| }), | |
| ("Westside Manhattan", { | |
| "type": "Point", | |
| "coordinates": [-74.013686, 40.701975] | |
| }), | |
| ("Downtown Manhattan", { | |
| "type": "Point", | |
| "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.Code(label="Pre-aggregate pipeline",language="json" ), | |
| gr.Code(label="Vector Query", language="json")] | |
| ) | |
| if __name__ == "__main__": | |
| demo.launch() | |