AI 增加 Chroma 向量库
This commit is contained in:
@@ -43,7 +43,7 @@
|
|||||||
特别适合处理复杂的企业知识库。
|
特别适合处理复杂的企业知识库。
|
||||||
|
|
||||||
此外该模块,支持云上大模型和本地部署的大模型,如:DeepSeek、通义千问,理论上支持所有 OpenAPI 标准接口的 AI 提供商。
|
此外该模块,支持云上大模型和本地部署的大模型,如:DeepSeek、通义千问,理论上支持所有 OpenAPI 标准接口的 AI 提供商。
|
||||||
并能无缝集成多种嵌入式 AI 模型的向量数据库,如 PGVector、Elasticsearch、Milvus 等,实现高效的数据存储、检索及分析。
|
并能无缝集成多种嵌入式 AI 模型的向量数据库,如 Chroma、PGVector、Elasticsearch、Milvus 等,实现高效的数据存储、检索及分析。
|
||||||
无论是大规模数据集还是高度专业化的领域知识,JeeSite CMS + RAG + AI 都能提供定制化解决方案,满足企业多样化的业务需求和技术要求。
|
无论是大规模数据集还是高度专业化的领域知识,JeeSite CMS + RAG + AI 都能提供定制化解决方案,满足企业多样化的业务需求和技术要求。
|
||||||
企业可以轻松管理和访问复杂的信息资源,促进内部知识共享和创新,从而在竞争激烈的市场环境中保持领先地位。
|
企业可以轻松管理和访问复杂的信息资源,促进内部知识共享和创新,从而在竞争激烈的市场环境中保持领先地位。
|
||||||
|
|
||||||
@@ -65,6 +65,7 @@
|
|||||||
|
|
||||||
支持的向量库列表:<https://docs.spring.io/spring-ai/reference/1.0/api/vectordbs.html>
|
支持的向量库列表:<https://docs.spring.io/spring-ai/reference/1.0/api/vectordbs.html>
|
||||||
|
|
||||||
|
* Chroma
|
||||||
* PGVector
|
* PGVector
|
||||||
* Elasticsearch
|
* Elasticsearch
|
||||||
* Milvus
|
* Milvus
|
||||||
|
|||||||
@@ -49,11 +49,17 @@
|
|||||||
<artifactId>spring-ai-ollama-spring-boot-starter</artifactId>
|
<artifactId>spring-ai-ollama-spring-boot-starter</artifactId>
|
||||||
</dependency>
|
</dependency>
|
||||||
|
|
||||||
<!-- PG 向量数据库 -->
|
<!-- Chroma 向量数据库 -->
|
||||||
|
<dependency>
|
||||||
|
<groupId>org.springframework.ai</groupId>
|
||||||
|
<artifactId>spring-ai-chroma-store-spring-boot-starter</artifactId>
|
||||||
|
</dependency>
|
||||||
|
|
||||||
|
<!-- PG 向量数据库
|
||||||
<dependency>
|
<dependency>
|
||||||
<groupId>org.springframework.ai</groupId>
|
<groupId>org.springframework.ai</groupId>
|
||||||
<artifactId>spring-ai-pgvector-store-spring-boot-starter</artifactId>
|
<artifactId>spring-ai-pgvector-store-spring-boot-starter</artifactId>
|
||||||
</dependency>
|
</dependency> -->
|
||||||
|
|
||||||
<!-- ES 向量数据库
|
<!-- ES 向量数据库
|
||||||
<dependency>
|
<dependency>
|
||||||
|
|||||||
@@ -54,37 +54,45 @@ spring:
|
|||||||
# 向量数据库配置
|
# 向量数据库配置
|
||||||
vectorstore:
|
vectorstore:
|
||||||
|
|
||||||
# Postgresql 向量数据库(PG 连接配置,见下文,需要手动建表)
|
# Chroma 向量数据库
|
||||||
pgvector:
|
chroma:
|
||||||
initialize-schema: false
|
client:
|
||||||
id-type: TEXT
|
host: http://localhost
|
||||||
index-type: HNSW
|
port: 8000
|
||||||
distance-type: COSINE_DISTANCE
|
initialize-schema: true
|
||||||
#table-name: vector_store_384
|
collection-name: vector_store
|
||||||
#dimensions: 384
|
|
||||||
#table-name: vector_store_786
|
# # Postgresql 向量数据库(PG 连接配置,见下文,需要手动建表)
|
||||||
#dimensions: 768
|
# pgvector:
|
||||||
table-name: vector_store_1024
|
# id-type: TEXT
|
||||||
dimensions: 1024
|
# index-type: HNSW
|
||||||
batching-strategy: TOKEN_COUNT
|
# distance-type: COSINE_DISTANCE
|
||||||
max-document-batch-size: 10000
|
# initialize-schema: false
|
||||||
|
# #table-name: vector_store_384
|
||||||
|
# #dimensions: 384
|
||||||
|
# #table-name: vector_store_786
|
||||||
|
# #dimensions: 768
|
||||||
|
# table-name: vector_store_1024
|
||||||
|
# dimensions: 1024
|
||||||
|
# batching-strategy: TOKEN_COUNT
|
||||||
|
# max-document-batch-size: 10000
|
||||||
|
|
||||||
# # ES 向量数据库(ES 连接配置,见下文)
|
# # ES 向量数据库(ES 连接配置,见下文)
|
||||||
# elasticsearch:
|
# elasticsearch:
|
||||||
# initialize-schema: true
|
|
||||||
# index-name: vector-index
|
# index-name: vector-index
|
||||||
|
# initialize-schema: true
|
||||||
# dimensions: 1024
|
# dimensions: 1024
|
||||||
# similarity: cosine
|
# similarity: cosine
|
||||||
# batching-strategy: TOKEN_COUNT
|
# batching-strategy: TOKEN_COUNT
|
||||||
|
|
||||||
# # Milvus 向量数据库(字符串长度不超过65535)
|
# # Milvus 向量数据库(字符串长度不超过65535)
|
||||||
# milvus:
|
# milvus:
|
||||||
# initialize-schema: true
|
|
||||||
# client:
|
# client:
|
||||||
# host: "localhost"
|
# host: "localhost"
|
||||||
# port: 19530
|
# port: 19530
|
||||||
# username: "root"
|
# username: "root"
|
||||||
# password: "milvus"
|
# password: "milvus"
|
||||||
|
# initialize-schema: true
|
||||||
# database-name: "default2"
|
# database-name: "default2"
|
||||||
# collection-name: "vector_store2"
|
# collection-name: "vector_store2"
|
||||||
# embedding-dimension: 384
|
# embedding-dimension: 384
|
||||||
@@ -93,24 +101,24 @@ spring:
|
|||||||
|
|
||||||
# ========= Postgresql 向量数据库数据源 =========
|
# ========= Postgresql 向量数据库数据源 =========
|
||||||
|
|
||||||
jdbc:
|
#jdbc:
|
||||||
ds_pgvector:
|
# ds_pgvector:
|
||||||
type: postgresql
|
# type: postgresql
|
||||||
driver: org.postgresql.Driver
|
# driver: org.postgresql.Driver
|
||||||
url: jdbc:postgresql://127.0.0.1:5433/jeesite-ai
|
# url: jdbc:postgresql://127.0.0.1:5433/jeesite-ai
|
||||||
username: postgres
|
# username: postgres
|
||||||
password: postgres
|
# password: postgres
|
||||||
testSql: SELECT 1
|
# testSql: SELECT 1
|
||||||
|
|
||||||
# ========= ES 向量数据库连接配置 =========
|
# ========= ES 向量数据库连接配置 =========
|
||||||
|
|
||||||
spring.elasticsearch:
|
#spring.elasticsearch:
|
||||||
enabled: true
|
# enabled: true
|
||||||
socket-timeout: 120s
|
# socket-timeout: 120s
|
||||||
connection-timeout: 120s
|
# connection-timeout: 120s
|
||||||
uris: http://127.0.0.1:9200
|
# uris: http://127.0.0.1:9200
|
||||||
username: elastic
|
# username: elastic
|
||||||
password: elastic
|
# password: elastic
|
||||||
|
|
||||||
# 对话消息存缓存,可自定义存数据库
|
# 对话消息存缓存,可自定义存数据库
|
||||||
j2cache:
|
j2cache:
|
||||||
|
|||||||
Reference in New Issue
Block a user