👐 Generate embeddings

To perform vector search on the data, we need to embed it (i.e. generate embedding vectors) before ingesting it into MongoDB.

Fill in any <CODE_BLOCK_N> placeholders and run the cells under the Step 4: Generate embeddings section in the notebook to embed the chunked articles.

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

CODE_BLOCK_3

Answer

embedding_model.encode(text)

CODE_BLOCK_4

Answer

doc["embedding"] = get_embedding(doc["body"])

caution

If the embedding generation is taking too long (> 5 min), kill/interrupt the cell and move on to the next step with the documents that have been embedded up until that point.