Spring/spring-ai
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Updated several vector db docs to fix errors and to expand on instructions, making it easier to follow and complete successfully: Azure AI Search, Neo4j, and Postgres/PGvector

Browse Source
This commit is contained in:
Mark Heckler
2024-02-07 18:16:56 -06:00
committed by Christian Tzolov
parent dc86957a07
commit 214858bec5
3 changed files with 74 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
spring-ai-docs/src/main/antora/modules/ROOT/pages/api/vectordbs/azure.adoc
View File

@@ -43,47 +43,47 @@ Add these dependencies to your project:
* OpenAI Embedding:
[source,xml]
----
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-openai-spring-boot-starter</artifactId>
<version>0.8.0-SNAPSHOT</version>
</dependency>
----
[source,xml]
----
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-openai-spring-boot-starter</artifactId>
<version>0.8.0-SNAPSHOT</version>
</dependency>
----
* Or Azure AI Embedding:
[source,xml]
----
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-azure-openai-spring-boot-starter</artifactId>
<version>0.8.0-SNAPSHOT</version>
</dependency>
----
[source,xml]
----
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-azure-openai-spring-boot-starter</artifactId>
<version>0.8.0-SNAPSHOT</version>
</dependency>
----
* Or Local Sentence Transformers Embedding:
[source,xml]
----
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-transformers-spring-boot-starter</artifactId>
<version>0.8.0-SNAPSHOT</version>
</dependency>
----
[source,xml]
----
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-transformers-spring-boot-starter</artifactId>
<version>0.8.0-SNAPSHOT</version>
</dependency>
----
2. Azure (AI Search) Vector Store
[source,xml]
----
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-azure-vector-store</artifactId>
<version>0.8.0-SNAPSHOT</version>
</dependency>
----
[source,xml]
----
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-azure-vector-store</artifactId>
<version>0.8.0-SNAPSHOT</version>
</dependency>
----
== Sample Code

39
spring-ai-docs/src/main/antora/modules/ROOT/pages/api/vectordbs/neo4j.adoc
View File

@@ -15,14 +15,14 @@ link:https://neo4j.com/docs/cypher-manual/current/indexes-for-vector-search/[Neo
1. OpenAI Account: Create an account at link:https://platform.openai.com/signup[OpenAI Signup] and generate the token at link:https://platform.openai.com/account/api-keys[API Keys].
2. A running Neo4j (5.13+) instance
a. link:https://hub.docker.com/_/neo4j[Docker] image _neo4j:5.13_
a. link:https://hub.docker.com/_/neo4j[Docker] image _neo4j:5.15_
b. link:https://neo4j.com/download/[Neo4j Desktop]
c. link:https://neo4j.com/cloud/aura-free/[Neo4j Aura]
d. link:https://neo4j.com/deployment-center/[Neo4j Server] instance
== Configuration
To connect to Neo4j and use the `Neo4jVectorStore`, you need to provide (e.g. via `application.properties`) configurations for your instance.
To connect to Neo4j and use the `Neo4jVectorStore`, you need to provide (e.g. via `application.properties`, environment variables, etc.) configurations for your instance.
Additionally, you'll need to provide your OpenAI API Key. Set it as an environment variable like so:
@@ -77,5 +77,38 @@ Add these dependencies to your project:
To configure `Neo4jVectorStore` in your application, you can use the following setup:
Add to `application.properties` (using your Neo4j credentials):
Add to your environment (using your own Neo4j credentials and the appropriate access protocol+endpoint) the following properties either by updating and executing the following commands or creating a shell script to be run from your command prompt (Linux/Mac/WSL2):
[source,bash]
----
export SPRING_NEO4J_URI=<uri_for_your_neo4j_instance>
export SPRING_NEO4J_AUTHENTICATION_USERNAME=<your_username>
export SPRING_NEO4J_AUTHENTICATION_PASSWORD=<your_password>
----
NOTE: If you choose to create a shell script for ease in future work, be sure to run it prior to starting your application by "sourcing" the file, i.e. `source <your_script_name>.sh`.
You'll need a `VectorStore` to store the embeddings. You can use the `Neo4jVectorStore` for this purpose, but first, you must create two beans the `Neo4jVectorStore` constructor requires. Here are examples of all of the beans you'll need:
[source,java]
----
@Bean
public Driver driver() {
return GraphDatabase.driver(System.getenv("SPRING_NEO4J_URI"),
AuthTokens.basic(System.getenv("SPRING_NEO4J_AUTHENTICATION_USERNAME"),
System.getenv("SPRING_NEO4J_AUTHENTICATION_PASSWORD")));
}
@Bean
public EmbeddingClient embeddingClient() {
return new OpenAiEmbeddingClient(new OpenAiApi(System.getenv("SPRING_AI_OPENAI_API_KEY")));
}
@Bean
public VectorStore vectorStore(Driver driver, EmbeddingClient embeddingClient) {
return new Neo4jVectorStore(driver, embeddingClient,
Neo4jVectorStore.Neo4jVectorStoreConfig.defaultConfig());
}
----
The `Neo4jVectorStore` is now ready to be used in your application. You can use it to store embeddings and perform similarity searches.

12
spring-ai-docs/src/main/antora/modules/ROOT/pages/api/vectordbs/pgvector.adoc
View File

@@ -18,18 +18,18 @@ On startup, the `PgVectorStore` will attempt to install the required database ex
[sql]
----
CREATE EXTENSION IF NOT EXISTS vector
CREATE EXTENSION IF NOT EXISTS hstore
CREATE EXTENSION IF NOT EXISTS "uuid-ossp"
CREATE EXTENSION IF NOT EXISTS vector;
CREATE EXTENSION IF NOT EXISTS hstore;
CREATE EXTENSION IF NOT EXISTS "uuid-ossp";
CREATE TABLE IF NOT EXISTS vector_store (
id uuid DEFAULT uuid_generate_v4() PRIMARY KEY,
content text,
metadata json,
embedding vector(1536)
)
);
CREATE INDEX ON vector_store USING HNSW (embedding vector_cosine_ops)
CREATE INDEX ON vector_store USING HNSW (embedding vector_cosine_ops);
----
== Configuration
@@ -111,7 +111,7 @@ Add to `application.yml` (using your DB credentials):
----
spring:
datasource:
url: jdbc:postgresql://localhost:5432/vector_store
url: jdbc:postgresql://localhost:5432/postgres
username: postgres
password: postgres
----