AI vendors and your data

Vendors146Answers427

146 vendors · 427 answers

Create an index changed Pinecone, Nov 9, 2026

Pinecone · Nov 9, 2026 · 5 added, 30 removed · seen by the weekly check

The pageAll Pinecone terms

After this change the quoted clause for residency is no longer on the page. The answer is flagged until a person re-reads it.

  1. Added: A Pinecone index lets you store and search your data. A document index stores JSON documents whose fields you declare in a schema at creation. It can combine dense vector, sparse vector, and full-text ( string ) fields in one document, so a single index serves full-text search , semantic search , and sparse-vector search . To create a legacy vector index, see Create a vector index . To create a legacy integrated index, see Create an integrated index .
  2. Removed: A Pinecone index lets you store and search your data. What an index holds determines the search it supports, so you pick the index type when you create it:
  3. Removed: Documents : JSON records whose fields you declare in a schema at creation. A document index is the default, and it can combine dense vector, sparse vector, and full-text ( string ) fields in one record, so a single index serves full-text search , semantic search , and sparse-vector search .
  4. Removed: Dense vectors : Numerical representations of the meaning of text, images, or other data. A vector index of dense vectors serves semantic search , or hybrid search together with sparse vectors.
  5. Removed: Sparse vectors : High-dimensional vectors with mostly zero values that capture keyword signals, produced by a sparse embedding model such as pinecone-sparse-english-v0 . A vector index of sparse vectors serves sparse-vector search , or hybrid search together with dense vectors.
  6. Added: Full-text search and integrated embedding are different features. A string field with full_text_search is indexed for BM25 keyword ranking and Lucene queries. It doesn't create vectors or call an embedding model. To have Pinecone turn a field's text into vectors, use integrated embedding : declare embed or sparse_embed on a string field in a document index. The legacy create_index_for_model path does this too, creating a legacy integrated index served by the legacy Records API.
  7. Removed: Full-text search and integrated embedding are different features. A string field with full_text_search is indexed for BM25 keyword ranking and Lucene queries. It doesn't create vectors or call an embedding model. To have Pinecone turn a field's text into vectors, use integrated embedding : declare embed or sparse_embed on a string field in a document index. The legacy create_index_for_model path does this too, creating a legacy integrated index served by the Records API.
  8. Added: A single index with a document schema can hold string fields with full_text_search and dense_vector ranking fields together, and the same schema can also include a sparse_vector field. A single search request ranks by one scoring type. Multi-field BM25 is supported: use multiple text clauses on different fields, or one query_string clause spanning fields. Any scoring method can be combined with metadata filters, including text-match filters ( $match_phrase , $match_all , $match_any ) on string fields with full_text_search .
  9. Removed: A single index with a document schema can hold FTS-enabled string and dense_vector ranking fields together, and the same schema can also include a sparse_vector field. A single search request ranks by one scoring type. Multi-field BM25 is supported: use multiple text clauses on different fields, or one query_string clause spanning fields. Any scoring method can be combined with metadata filters, including text-match filters ( $match_phrase , $match_all , $match_any ) on FTS-enabled string fields.
  10. Added: You can't add, remove, or modify a document index's fields after you create it. To change a schema, delete the index and create a new one. To move an existing legacy vector index or legacy integrated index onto a document schema, convert it instead of reloading your data.
  11. Added: You can create an index from a backup. For more details, see Restore an index .
  12. Removed: Schema migration isn't yet supported. Once an index with a document schema is created, you can't add, remove, or modify fields. Plan your schema carefully. If you need to change a schema, delete the index and create a new one.
  13. Removed: A vector index stores dense or sparse vectors and is read and written through the Vectors API. (A document index can also hold dense_vector and sparse_vector fields; see Create a document index .)
  14. Removed: You can create an index that stores dense vectors with integrated vector embedding , or one that stores vectors generated with an external embedding model.
  15. Removed: Legacy integrated indexes (created with create_index_for_model and served by the legacy Records API) don't support updating or importing with text.
  16. Removed: This creates a legacy integrated index served by the Records API. To embed text in a document index instead, see Integrated embedding . If you want to upsert and search with source text and have Pinecone convert it to dense vectors automatically, create an index with integrated embedding as follows:
  17. Removed: Set cloud and region to the cloud and region where the index should be deployed.
  18. Removed: Set embed.model to one of Pinecone's hosted embedding models .
  19. Removed: Set embed.field_map to the name of the field in your source document that contains the data for embedding.
  20. Removed: Other parameters are optional. See Create an index with integrated embedding for details.
  21. Removed: If you use an external embedding model to convert your data to dense vectors, create an index as follows:
  22. Removed: Set the vector_type to dense .
  23. Removed: Specify the dimension and similarity metric of the vectors you'll store in the index. This should match the dimension and metric supported by your embedding model.
  24. Removed: Set spec.cloud and spec.region to the cloud and region where the index should be deployed. For Python, you also need to import the ServerlessSpec class.
  25. Removed: Other parameters are optional. See Create an index for details.
  26. Removed: You can create an index that stores sparse vectors with integrated vector embedding , or one that stores vectors generated with an external embedding model.
  27. Removed: This creates a legacy integrated index served by the Records API. To embed text in a document index instead, see Integrated embedding . If you want to upsert and search with source text and have Pinecone convert it to sparse vectors automatically, create an index with integrated embedding as follows:
  28. Removed: Set embed.model to one of Pinecone's hosted sparse embedding models .
  29. Removed: Set embed.field_map to the name of the field in your source document that contains the text for embedding.
  30. Removed: If needed, embed.read_parameters and embed.write_parameters can be used to override the default model embedding behavior.
  31. Removed: If you use an external embedding model to convert your data to sparse vectors, create an index as follows:
  32. Removed: Set the vector_type to sparse .
  33. Removed: Set the distance metric to dotproduct . Indexes that store sparse vectors don't support other distance metrics .
  34. Removed: Set spec.cloud and spec.region to the cloud and region where the index should be deployed.
  35. Removed: You can restore an index from a backup, regardless of whether it stores dense or sparse vectors. For more details, see Restore an index .
About this change
Page
docs.pinecone.io/guides/index-data/create-an-index
Kind
Documentation
Text hash
819f07994f3b to 0a3fe3faf05f
Dated by
the weekly check that first read the new text