This test task aims to evaluate your grasp of fundamental machine learning and development concepts. Your task involves working with an image dataset to develop a system capable of searching for similar images based on textual queries.
Please choose whatever image dataset you prefer, for example:
| collection::collection_manager::holders::segment_holder::SegmentHolder::appendable_segments::{{closure}} () at lib/collection/src/collection_manager/holders/segment_holder.rs:238 | |
| collection::collection_manager::holders::segment_holder::SegmentHolder::appendable_segments (self=0x7fcb18c430b8) at lib/collection/src/collection_manager/holders/segment_holder.rs:236 | |
| collection::collection_manager::holders::segment_holder::SegmentHolder::segment_flush_ordering (self=0x7fcb18c430b8) at lib/collection/src/collection_manager/holders/segment_holder.rs:460 | |
| collection::collection_manager::holders::segment_holder::SegmentHolder::flush_all (self=0x7fcb18c430b8, sync=false) at lib/collection/src/collection_manager/holders/segment_holder.rs:477 | |
| collection::update_handler::UpdateHandler::flush_segments (segments=...) at lib/collection/src/update_handler.rs:552 | |
| collection::update_handler::UpdateHandler::flush_worker::{{closure}} () at lib/collection/src/update_handler.rs:518 | |
| collection::collection_manager::holders::segment_ |
| { | |
| "result": [ | |
| { | |
| "payload": { | |
| "location": "html > body > div:nth-of-type(1) > section:nth-of-type(2) > div > div > div > article > h3:nth-of-type(4)", | |
| "sections": [ | |
| "documentation", | |
| "documentation/quick_start" | |
| ], | |
| "tag": "h3", |
| import asyncio | |
| import time | |
| from multiprocessing import Pool | |
| import httpx | |
| import numpy as np | |
| from grpclib.client import Channel | |
| from qdrant_client import QdrantClient | |
| from qdrant_client.grpc import PointsStub, WithPayloadSelector | |
| from qdrant_client.http.models import Distance, OptimizersConfigDiff, \ |
| # File: service.py | |
| from fastapi import FastAPI | |
| # That is the file where NeuralSearcher is stored | |
| from neural_searcher import NeuralSearcher | |
| app = FastAPI() | |
| # Create an instance of the neural searcher |
| from qdrant_client.http.models import Filter | |
| ... | |
| city_of_interest = "Berlin" | |
| # Define a filter for cities | |
| city_filter = Filter(**{ | |
| "must": [{ | |
| "key": "city", # We store city information in a field of the same name |
| # File: neural_searcher.py | |
| from qdrant_client import QdrantClient | |
| from sentence_transformers import SentenceTransformer | |
| class NeuralSearcher: | |
| def __init__(self, collection_name): | |
| self.collection_name = collection_name |
| import numpy as np | |
| import json | |
| fd = open('./startups.json') | |
| # payload is now an iterator over startup data | |
| payload = map(json.loads, fd) | |
| # Here we load all vectors into memory, numpy array works as iterable for itself. | |
| # Other option would be to use Mmap, if we don't want to load all data into RAM |