向量存储库#
向量存储库包含已摄取文档分块的嵌入向量(有时也包含文档分块本身)。
简单向量存储库#
默认情况下,LlamaIndex 使用一个简单的内存向量存储库,非常适合快速实验。通过调用 vector_store.persist()(以及对应的 SimpleVectorStore.from_persist_path(...))方法,这些向量存储可以持久化到磁盘(或从磁盘加载)。
向量存储选项与功能支持#
LlamaIndex 支持超过 20 种不同的向量存储方案。我们正在积极增加更多集成并提升各方案的功能覆盖率。
| 向量存储 | 类型 | 元数据过滤 | 混合搜索 | 删除 | 存储文档 | 异步 |
|---|---|---|---|---|---|---|
| 阿里云 OpenSearch | 云端 | ✓ | ✓ | ✓ | ✓ | |
| Apache Cassandra® | 自托管/云端 | ✓ | ✓ | ✓ | ||
| Astra DB | 云端 | ✓ | ✓ | ✓ | ||
| Azure AI 搜索 | 云端 | ✓ | ✓ | ✓ | ✓ | |
| Azure CosmosDB Mongo vCore | 云端 | ✓ | ✓ | |||
| Azure CosmosDB NoSql | 云端 | ✓ | ✓ | |||
| 百度向量数据库 | 云端 | ✓ | ✓ | ✓ | ||
| ChatGPT 检索插件 | 聚合器 | ✓ | ✓ | |||
| Chroma | 自托管 | ✓ | ✓ | ✓ | ||
| Couchbase | 自托管/云端 | ✓ | ✓ | ✓ | ✓ | |
| DashVector | 云端 | ✓ | ✓ | ✓ | ✓ | |
| Databricks | 云端 | ✓ | ✓ | ✓ | ||
| Deeplake | 自托管/云端 | ✓ | ✓ | ✓ | ||
| DocArray | 聚合器 | ✓ | ✓ | ✓ | ||
| DuckDB | 内存/自托管 | ✓ | ✓ | ✓ | ||
| DynamoDB | 云端 | ✓ | ||||
| Elasticsearch | 自托管/云端 | ✓ | ✓ | ✓ | ✓ | ✓ |
| FAISS | 内存 | |||||
| Google AlloyDB | 云端 | ✓ | ✓ | ✓ | ✓ | |
| Google Cloud SQL Postgres | 云端 | ✓ | ✓ | ✓ | ✓ | |
| Hnswlib | 内存 | |||||
| txtai | 内存 | |||||
| Jaguar | 自托管/云端 | ✓ | ✓ | ✓ | ✓ | |
| LanceDB | 云端 | ✓ | ✓ | ✓ | ||
| Lantern | 自托管/云端 | ✓ | ✓ | ✓ | ✓ | ✓ |
| Metal | 云端 | ✓ | ✓ | ✓ | ||
| MongoDB Atlas | 自托管/云端 | ✓ | ✓ | ✓ | ✓ | |
| MyScale | 云端 | ✓ | ✓ | ✓ | ✓ | |
| Milvus / Zilliz | 自托管/云端 | ✓ | ✓ | ✓ | ✓ | |
| Neo4jVector | 自托管/云端 | ✓ | ✓ | ✓ | ||
| OpenSearch | 自托管/云端 | ✓ | ✓ | ✓ | ✓ | ✓ |
| Pinecone | 云端 | ✓ | ✓ | ✓ | ✓ | |
| Postgres | 自托管/云端 | ✓ | ✓ | ✓ | ✓ | ✓ |
| pgvecto.rs | 自托管/云端 | ✓ | ✓ | ✓ | ✓ | |
| Qdrant | 自托管/云端 | ✓ | ✓ | ✓ | ✓ | ✓ |
| Redis | 自托管/云端 | ✓ | ✓ | ✓ | ||
| Simple | 内存 | ✓ | ✓ | |||
| SingleStore | 自托管/云端 | ✓ | ✓ | ✓ | ||
| Supabase | 自托管/云端 | ✓ | ✓ | ✓ | ||
| Tablestore | 云端 | ✓ | ✓ | ✓ | ✓ | |
| Tair | 云端 | ✓ | ✓ | ✓ | ||
| TiDB | 云端 | ✓ | ✓ | ✓ | ||
| 腾讯向量数据库 | 云端 | ✓ | ✓ | ✓ | ✓ | |
| Timescale | ✓ | ✓ | ✓ | ✓ | ||
| Typesense | 自托管/云端 | ✓ | ✓ | ✓ | ||
| Upstash | 云端 | ✓ | ||||
| Vearch | 自托管 | ✓ | ✓ | ✓ | ||
| Vespa | 自托管/云端 | ✓ | ✓ | ✓ | ✓ | |
| Vertex AI 向量搜索 | 云端 | ✓ | ✓ | ✓ | ||
| Weaviate | 自托管/云端 | ✓ | ✓ | ✓ | ✓ | |
| WordLift | 云端 | ✓ | ✓ | ✓ | ✓ | ✓ |
更多详情请参阅向量存储集成。
示例 Notebook#
- 阿里云 OpenSearch
- Astra DB
- 异步索引创建
- Azure AI 搜索
- Azure Cosmos DB Mongo vCore
- Azure Cosmos DB NoSql
- 百度向量数据库
- Cassandra
- ChromaDB
- Couchbase
- 达摩院向量引擎
- Databricks
- DeepLake
- DocArray HNSW
- DocArray 内存索引
- DuckDB
- Epsilla
- Google AlloyDB for PostgreSQL
- Google Cloud SQL for PostgreSQL
- Jaguar
- LanceDB
- Lantern
- Metal
- Milvus
- Milvus 异步 API
- Milvus 全文检索
- Milvus 混合检索
- MyScale
- ElasticSearch
- FAISS
- Hnswlib
- MongoDB Atlas
- Neo4j
- OpenSearch
- Pinecone
- Pinecone 混合检索
- PGvectoRS
- PostgreSQL
- Redis
- Qdrant
- Qdrant 混合检索
- Rockset
- 简单索引
- Supabase
- 表格存储
- Tair
- TiDB
- 腾讯云向量数据库
- Timescale
- Upstash
- Vearch
- Vespa
- Vertex AI 向量搜索
- Weaviate
- Weaviate 混合检索
- WordLift
- Zep