Simple example showing how to search against sentences and retrieve a related page that it belongs to as context

parent_document_retriever.py

import os
import pymongo
import time

import openai

embeddings = openai.Embedding.create(
  input="What is a transformer?",
  model="text-embedding-ada-002"
)

embeddings = embeddings.data[0].embedding

client = pymongo.MongoClient("") # mongodb cluster URI

db = client['vector-test']
coll = db['nested_test']
times = []
vector_agg_with_lookup = [
        {
        "$vectorSearch": {
        "index": "vector_index",
        "path": "vector",
        "queryVector": embeddings,
        "limit": 10,
        "numCandidates": 50,
        "filter": {"$eq": {"$doc_level": "sentence"}},
    },
},
{
    "$project": {"text": 1, "page": 1, "doc_level": 1},
},
{
    "$lookup": {
        "from": "nested_test",
        "localField": "page",
        "foreignField": "page",
        "as": "parent_context",
        "pipeline": [{"$match": {"doc_level": "page"}}, {"$unwind": "$parent_context"}],
    }
}]

x = coll.aggregate(vector_agg_with_lookup)
parent_context = doc["parent_context"]["text"]