👐 Perform vector search queries

Now let's run some vector search queries against the books collection.

Fill in any <CODE_BLOCK_N> placeholders and run the cells under the Step 6: Perform vector search queries section in the notebook to run vector search queries against your data.

The answers for code blocks in this section are as follows:

CODE_BLOCK_9

Answer

get_embedding(user_query, mode)

CODE_BLOCK_10

Answer

[
    {
        "$vectorSearch": {
            "index": ATLAS_VECTOR_SEARCH_INDEX_NAME,
            "queryVector": query_embedding,
            "path": "embedding",
            "numCandidates": 50,
            "filter": filter,
            "limit": 5,
        }
    },
    {"$project": {"_id": 0, "title": 1, "cover": 1, "year":1, "pages":1, "score": {"$meta": "vectorSearchScore"}}},
]

CODE_BLOCK_11

Answer

collection.aggregate(pipeline)