AI vendors and your data

Vendors146Answers427

146 vendors · 427 answers

Create an index changed Pinecone, Oct 19, 2026

Pinecone · Oct 19, 2026 · 2 added, 26 removed · seen by the weekly check

The pageAll Pinecone terms
  1. Added: For index naming rules, available cloud regions, similarity metrics, and hosted embedding models, see Index configuration .
  2. Added: A new index of any type can't accept data until its status.ready field is true . The Python SDK waits for this by default, and the Node.js SDK waits when you pass waitUntilReady: true . If you call the API directly, describe the index repeatedly until status.ready is true , then upsert.
  3. Removed: To index only the metadata fields you filter on, rather than all of them, see Configure metadata indexing .
  4. Removed: When creating an index, you must choose the cloud and region where you want the index to be hosted. The following table lists the available public clouds and regions and the plans that support them:
  5. Removed: The cloud and region can't be changed after a serverless index is created.
  6. Removed: On the Starter plan, you can create serverless indexes in the us-east-1 region of AWS only. To create indexes in other regions, upgrade to the Builder, Standard, or Enterprise plan .
  7. Removed: When creating an index that stores dense vectors, you can choose from the following similarity metrics. For the most accurate results, choose the similarity metric used to train the embedding model for your vectors. For more information, see Vector Similarity Explained .
  8. Removed: Indexes that store sparse vectors must use the dotproduct metric.
  9. Removed: Querying indexes with this metric returns a similarity score equal to the squared Euclidean distance between the result and query vectors. This metric calculates the square of the distance between two data points in a plane. It's one of the most commonly used distance metrics. For an example, see our IT threat detection example . When you use metric='euclidean' , the most similar results are those with the lowest similarity score .
  10. Removed: This is often used to find similarities between different documents. The advantage is that the scores are normalized to [-1,1] range. For an example, see our generative question answering example .
  11. Removed: This is used to multiply two vectors. You can use it to tell us how similar the two vectors are. The more positive the answer is, the closer the two vectors are in terms of their directions. For an example, see our semantic search example .
  12. Removed: Dense vectors and sparse vectors are the basic units of data in Pinecone and what Pinecone was specially designed to store and work with. Dense vectors represents the semantics of data such as text, images, and audio recordings, while sparse vectors represent documents or queries in a way that captures keyword information. To transform data into vector format, you use an embedding model. Pinecone hosts several embedding models so it's easy to manage your vector storage and search process on a single platform. You can use a hosted model to embed your data as an integrated part of upserting and querying, or you can use a hosted model to embed your data as a standalone operation. The following embedding models are hosted by Pinecone.
  13. Removed: To understand how cost is calculated for embedding, see Embedding cost . To get model details via the API, see List models and Describe a model .
  14. Removed: multilingual-e5-large is an efficient dense embedding model trained on a mixture of multilingual datasets. It works well on messy data and short queries expected to return medium-length passages of text (1-2 paragraphs). Details
  15. Removed: For rate limits, see Embedding tokens per minute and Embedding tokens per month . Parameters The multilingual-e5-large model supports the following parameters:
  16. Removed: The type of input data. Accepted values: query or passage .
  17. Removed: How to handle inputs longer than those supported by the model. Accepted values: END or NONE .
  18. Removed: END truncates the input sequence at the input token limit. NONE returns an error when the input exceeds the input token limit.
  19. Removed: llama-text-embed-v2 is a high-performance dense embedding model optimized for text retrieval and ranking tasks. It's trained on a diverse range of text corpora and provides strong performance on longer passages and structured documents. Details
  20. Removed: Dimension: 1024 (default), 2048, 768, 512, 384
  21. Removed: For rate limits, see Embedding tokens per minute and Embedding tokens per month . Parameters The llama-text-embed-v2 model supports the following parameters:
  22. Removed: Dimension of the vector to return.
  23. Removed: pinecone-sparse-english-v0 is a sparse embedding model for converting text to sparse vectors for sparse-vector search or hybrid search. Built on the innovations of the DeepImpact architecture , the model directly estimates the lexical importance of tokens by using their context, unlike traditional retrieval models like BM25, which rely solely on term frequency. Details
  24. Removed: Max sequence length: 512 or 2048
  25. Removed: For rate limits, see Embedding tokens per minute and Embedding tokens per month . Parameters The pinecone-sparse-english-v0 model supports the following parameters:
  26. Removed: Maximum number of tokens to embed. Accepted values: 512 or 2048 .
  27. Removed: END truncates the input sequence at the the max_tokens_per_sequence limit. NONE returns an error when the input exceeds the max_tokens_per_sequence limit.
  28. Removed: Whether to return the string tokens.
About this change
Page
docs.pinecone.io/guides/index-data/create-an-index
Kind
Documentation
Text hash
1fa586d95732 to 4d90fa4e0d63
Dated by
the weekly check that first read the new text