Struct PineconeStore 

pub struct PineconeStore { /* private fields */ }

Pinecone vector store client

Implementations

impl PineconeStore

pub fn new(api_key: impl Into<String>, host: impl Into<String>) -> Self

Create a Pinecone client.

host format: https://{index-name}.svc.{environment}.pinecone.io

pub fn build_upsert_body(docs: &[Document], vectors: &[Vec<f32>]) -> Value

Build upsert request body (pure function, convenient for testing).

pub fn build_query_body(query_vec: &[f32], top_k: usize) -> Value

Build query request body (pure function, convenient for testing).

pub async fn upsert( &self, docs: &[Document], embeddings: &dyn Embeddings, ) -> Result<(), VectorStoreError>

Upsert documents (auto-embed).

pub async fn query( &self, query_vec: Vec<f32>, top_k: usize, ) -> Result<Vec<Document>, VectorStoreError>

Query similar documents.

pub async fn describe_index_stats( &self, ) -> Result<PineconeIndexStats, VectorStoreError>

读取索引统计(真实 count 的唯一可靠来源)。

Pinecone REST 提供 describe_index_stats,返回 totalVectorCount。

pub async fn delete(&self, ids: &[String]) -> Result<(), VectorStoreError>

Delete by IDs.

Trait Implementations

impl VectorStore for PineconeStore

fn add_documents<'life0, 'async_trait>( &'life0 self, documents: Vec<Document>, embeddings: Vec<Vec<f32>>, ) -> Pin<Box<dyn Future<Output = Result<Vec<String>, VectorStoreError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Adds documents.

fn similarity_search<'life0, 'life1, 'async_trait>( &'life0 self, query_embedding: &'life1 [f32], k: usize, ) -> Pin<Box<dyn Future<Output = Result<Vec<SearchResult>, VectorStoreError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Searches similar documents.

fn get_document<'life0, 'life1, 'async_trait>( &'life0 self, _id: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<Option<Document>, VectorStoreError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Gets document by ID.

fn get_embedding<'life0, 'life1, 'async_trait>( &'life0 self, _id: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<Option<Vec<f32>>, VectorStoreError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Gets document embedding by ID.

fn delete_document<'life0, 'life1, 'async_trait>( &'life0 self, id: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<(), VectorStoreError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Deletes document.

fn count<'life0, 'async_trait>( &'life0 self, ) -> Pin<Box<dyn Future<Output = usize> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Returns document count.

fn clear<'life0, 'async_trait>( &'life0 self, ) -> Pin<Box<dyn Future<Output = Result<(), VectorStoreError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Clears store.

fn embed_query(&self) -> Option<&dyn Embeddings>

返回该向量存储自带的文本嵌入器(若有)。

fn similarity_search_text<'life0, 'life1, 'async_trait>( &'life0 self, query: &'life1 str, k: usize, ) -> Pin<Box<dyn Future<Output = Result<Vec<SearchResult>, VectorStoreError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

文本相似度检索:用 embed_query 返回的嵌入器把 query 向量化后再检索。

fn similarity_search_with_min_score<'life0, 'life1, 'async_trait>( &'life0 self, query_embedding: &'life1 [f32], k: usize, min_score: Option<f32>, ) -> Pin<Box<dyn Future<Output = Result<Vec<SearchResult>, VectorStoreError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

带最低分数阈值的相似度检索。