|
|
|
"After executing the above, the documents in \"movies\" collection will contain an additional field of \"embedding\", as defined by the `EMBEDDDING_FIELD_NAME` variable, apart from already existing fields like title, plot, genres, cast, directors, etc."
|
|
|
|
"After executing the above, the documents in \"movies\" collection will contain an additional field of \"embedding\", as defined by the `EMBEDDING_FIELD_NAME` variable, apart from already existing fields like title, plot, genres, cast, directors, etc."
|
|
|
|
"Note: We are restricting this to just 500 documents in the interest of time. If you want to do this over the entire dataset of 23,000+ documents in our sample_mflix database, it will take a little while. Alternatively, you can use the [sample_mflix.embedded_movies collection](https://www.mongodb.com/docs/atlas/sample-data/sample-mflix/#sample_mflix.embedded_movies) which includes a pre-populated `plot_embedding` field that contains embeddings created using OpenAI's `text-embedding-3-small` embedding model that you can use with the Atlas Search vector search feature.\n",
|
|
|
|
"Note: We are restricting this to just 500 documents in the interest of time. If you want to do this over the entire dataset of 23,000+ documents in our sample_mflix database, it will take a little while. Alternatively, you can use the [sample_mflix.embedded_movies collection](https://www.mongodb.com/docs/atlas/sample-data/sample-mflix/#sample_mflix.embedded_movies) which includes a pre-populated `plot_embedding` field that contains embeddings created using OpenAI's `text-embedding-ada-002` embedding model that you can use with the Atlas Search vector search feature.\n",
|