AI vendors and your data

Vendors146Answers427

146 vendors · 427 answers

Create an index changed Pinecone, Oct 26, 2026

Pinecone · Oct 26, 2026 · 16 added, 14 removed · seen by the weekly check

The pageAll Pinecone terms
  1. Added: 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:
  2. Added: 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 .
  3. Added: 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.
  4. Added: 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.
  5. Removed: A Pinecone index can hold any combination of the following:
  6. Removed: Documents are the unit of data in an index with a document schema - JSON records whose ranking fields are indexed according to a schema you declare at index creation. An index with a document schema can mix dense_vector , sparse_vector , and FTS-enabled string ranking fields in the same record, alongside any number of metadata fields (auto-indexed at upsert time). Use documents for full-text search (BM25 ranking on string fields with full_text_search enabled), and to combine multiple scoring methods on the same data via score_by .
  7. Removed: Dense vectors are numerical representations of the meaning and relationships of text, images, or other data. Indexes of dense vectors are used for semantic search , or together with sparse vectors for hybrid search .
  8. Removed: Sparse vectors are high-dimensional vectors with mostly zero values, produced by a sparse embedding model such as pinecone-sparse-english-v0 . Indexes of sparse vectors are used for sparse-vector search , or together with dense vectors for hybrid search .
  9. Added: An index with a document schema stores typed JSON documents. The schema declares how each ranking field is indexed: as a string field with full_text_search enabled for BM25 ranking, a dense_vector for ANN similarity, or a sparse_vector . A single index can mix all three ranking field types, and at query time you pick the ranking signal with score_by . Any other fields you upsert are stored as metadata, auto-indexed for filtering at upsert time.
  10. 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 Records API.
  11. Removed: For index naming rules, available cloud regions, similarity metrics, and hosted embedding models, see Index configuration .
  12. Removed: An index with a document schema stores typed JSON documents. The schema declares how each ranking field is indexed: as a string field with full_text_search enabled for BM25 ranking, a dense_vector for ANN similarity, or a sparse_vector . A single index can mix all three ranking field types; at query time, pick the ranking signal with score_by . Metadata fields (anything else you upsert) aren't declared in the schema - they're auto-indexed for filtering at upsert time.
  13. Removed: Full-text search isn't integrated embedding. A string field with full_text_search is indexed for BM25 ranking and Lucene queries. It doesn't call an embedding model. Integrated embedding remains available for vector indexes.
  14. Added: 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.
  15. Added: You can include additional fields (for example, category or year ) at upsert time. All metadata fields are automatically indexed for filtering - they don't need to be declared in the schema. The schema is for ranking fields only. string_list , float , and boolean fields are always metadata, and a string field is metadata unless it sets full_text_search , embed , or sparse_embed . Declaring a metadata-only field in the schema is rejected at index creation. To index only the metadata fields you filter on, see Configure metadata indexing .
  16. Added: On a document index, declare embed or sparse_embed on a string field. Pinecone then embeds its text on write and the query text at search time, so you upsert and search with plain text instead of vectors. See Integrated embedding for the schema, examples, and limits. For the full schema reference (all field types, language and analyzer options, dedicated read capacity, and Python SDK examples), see Full-text search .
  17. Added: 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.
  18. Added: 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 .)
  19. Removed: A single index with a document schema can hold FTS-enabled string and dense_vector ranking fields together (the same schema can also include a sparse_vector field). A single search request ranks by one scoring type - multi-field BM25 is supported (multiple text clauses on different fields, or one query_string clause spanning fields), and any scoring method can be combined with metadata filters, including text-match filters ( $match_phrase , $match_all , $match_any ) on FTS-enabled string fields.
  20. Removed: You can include additional fields (for example, category or year ) at upsert time. All metadata fields are automatically indexed for filtering - they don't need to be declared in the schema. The schema is for ranking fields only; declaring a metadata-only field ( string without full_text_search , string_list , float , or boolean ) is rejected at index creation. To index only the metadata fields you filter on, see Configure metadata indexing . For the full schema reference (all field types, language and analyzer options, dedicated read capacity, and Python SDK examples), see Full-text search .
  21. Removed: Schema migration is not 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.
  22. Added: Legacy integrated indexes (created with create_index_for_model and served by the legacy Records API) don't support updating or importing with text.
  23. Added: 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:
  24. Removed: Indexes with integrated embedding don't support updating or importing with text.
  25. Removed: 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:
  26. Added: Other parameters are optional. See Create an index with integrated embedding for details.
  27. Removed: Other parameters are optional. See the API reference for details.
  28. Added: Other parameters are optional. See Create an index for details.
  29. Added: 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:
  30. Removed: 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:
2 paragraphs left out as page noise
  • Added (spacing or invisible characters only): You can restore an index from a backup, regardless of whether it stores dense or sparse vectors. For more details, see Restore an index .
  • Removed (spacing or invisible characters only): 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
4d90fa4e0d63 to 819f07994f3b
Dated by
the weekly check that first read the new text