GH-3187: Replace Spring environment variables with custom alternatives
Fixes: #3187 This commit addresses the issue with Spring environment variables that directly mirror Spring AI application properties, which can confuse users into thinking they should always set environment variables that match Spring property names. Instead, we've replaced all instances of SPRING_* prefixed environment variables in the documentation with custom-named alternatives that are referenced using Spring Expression Language (SpEL) or retrieved programmatically. Each documentation section now shows multiple configuration approaches: - Direct property setting in application.properties/yml - Using custom environment variables with SpEL - Accessing environment variables programmatically This gives users more flexibility while making it clear that using SPRING_* prefixed environment variables is not required or recommended. Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
This commit is contained in:
Soby Chacko
committed by
Ilayaperumal Gopinathan
Ilayaperumal Gopinathan
parent
c2a694900c
commit
b2d5ff0693
@@ -10,14 +10,42 @@ Spring AI provides dedicated xref:api/chat/bedrock-converse.adoc[Amazon Bedrock
|
||||
|
||||
== Prerequisites
|
||||
|
||||
You will need to create an API key on Anthropic portal.
|
||||
Create an account at https://console.anthropic.com/dashboard[Anthropic API dashboard] and generate the api key on the https://console.anthropic.com/settings/keys[Get API Keys] page.
|
||||
The Spring AI project defines a configuration property named `spring.ai.anthropic.api-key` that you should set to the value of the `API Key` obtained from anthropic.com.
|
||||
Exporting an environment variable is one way to set that configuration property:
|
||||
You will need to create an API key on the Anthropic portal.
|
||||
|
||||
[source,shell]
|
||||
Create an account at https://console.anthropic.com/dashboard[Anthropic API dashboard] and generate the API key on the https://console.anthropic.com/settings/keys[Get API Keys] page.
|
||||
|
||||
The Spring AI project defines a configuration property named `spring.ai.anthropic.api-key` that you should set to the value of the `API Key` obtained from anthropic.com.
|
||||
|
||||
You can set this configuration property in your `application.properties` file:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_ANTHROPIC_API_KEY=<INSERT KEY HERE>
|
||||
spring.ai.anthropic.api-key=<your-anthropic-api-key>
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference a custom environment variable:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
anthropic:
|
||||
api-key: ${ANTHROPIC_API_KEY}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export ANTHROPIC_API_KEY=<your-anthropic-api-key>
|
||||
----
|
||||
|
||||
You can also set this configuration programmatically in your application code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
// Retrieve API key from a secure source or environment variable
|
||||
String apiKey = System.getenv("ANTHROPIC_API_KEY");
|
||||
----
|
||||
|
||||
=== Add Repositories and BOM
|
||||
|
||||
@@ -14,15 +14,35 @@ To access models using an API key, obtain your Azure OpenAI `endpoint` and `api-
|
||||
|
||||
Spring AI defines two configuration properties:
|
||||
|
||||
1. `spring.ai.azure.openai.api-key`: Set this to the value the `API Key` obtained from Azure.
|
||||
1. `spring.ai.azure.openai.api-key`: Set this to the value of the `API Key` obtained from Azure.
|
||||
2. `spring.ai.azure.openai.endpoint`: Set this to the endpoint URL obtained when provisioning your model in Azure.
|
||||
|
||||
You can set these configuration properties by exporting environment variables:
|
||||
You can set these configuration properties in your `application.properties` or `application.yml` file:
|
||||
|
||||
[source,shell]
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_AZURE_OPENAI_API_KEY=<INSERT AZURE KEY HERE>
|
||||
export SPRING_AI_AZURE_OPENAI_ENDPOINT=<INSERT ENDPOINT URL HERE>
|
||||
spring.ai.azure.openai.api-key=<your-azure-api-key>
|
||||
spring.ai.azure.openai.endpoint=<your-azure-endpoint-url>
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference custom environment variables:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
azure:
|
||||
openai:
|
||||
api-key: ${AZURE_OPENAI_API_KEY}
|
||||
endpoint: ${AZURE_OPENAI_ENDPOINT}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export AZURE_OPENAI_API_KEY=<your-azure-openai-api-key>
|
||||
export AZURE_OPENAI_ENDPOINT=<your-azure-openai-endpoint-url>
|
||||
----
|
||||
|
||||
=== OpenAI Key
|
||||
@@ -31,9 +51,34 @@ To authenticate with the OpenAI service (not Azure), provide an OpenAI API key.
|
||||
|
||||
When using this approach, set the `spring.ai.azure.openai.chat.options.deployment-name` property to the name of the https://platform.openai.com/docs/models[OpenAI model] you wish to use.
|
||||
|
||||
[source,shell]
|
||||
In your application configuration:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_AZURE_OPENAI_OPENAI_API_KEY=<INSERT OPENAI KEY HERE>
|
||||
spring.ai.azure.openai.openai-api-key=<your-azure-openai-key>
|
||||
spring.ai.azure.openai.chat.options.deployment-name=<openai-model-name>
|
||||
----
|
||||
|
||||
Using environment variables with SpEL:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
azure:
|
||||
openai:
|
||||
openai-api-key: ${AZURE_OPENAI_API_KEY}
|
||||
chat:
|
||||
options:
|
||||
deployment-name: ${AZURE_OPENAI_MODEL_NAME}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export AZURE_OPENAI_API_KEY=<your-openai-key>
|
||||
export AZURE_OPENAI_MODEL_NAME=<openai-model-name>
|
||||
----
|
||||
|
||||
=== Microsoft Entra ID
|
||||
|
||||
@@ -5,13 +5,41 @@ Spring AI supports the various AI language models from DeepSeek. You can interac
|
||||
== Prerequisites
|
||||
|
||||
You will need to create an API key with DeepSeek to access DeepSeek language models.
|
||||
Create an account at https://platform.deepseek.com/sign_up[DeepSeek registration page] and generate a token on the https://platform.deepseek.com/api_keys[API Keys page].
|
||||
The Spring AI project defines a configuration property named `spring.ai.deepseek.api-key` that you should set to the value of the `API Key` obtained from the https://platform.deepseek.com/api_keys[API Keys page].
|
||||
Exporting an environment variable is one way to set this configuration property:
|
||||
|
||||
[source,shell]
|
||||
Create an account at https://platform.deepseek.com/sign_up[DeepSeek registration page] and generate a token on the https://platform.deepseek.com/api_keys[API Keys page].
|
||||
|
||||
The Spring AI project defines a configuration property named `spring.ai.deepseek.api-key` that you should set to the value of the `API Key` obtained from the API Keys page.
|
||||
|
||||
You can set this configuration property in your `application.properties` file:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_DEEPSEEK_API_KEY=<INSERT KEY HERE>
|
||||
spring.ai.deepseek.api-key=<your-deepseek-api-key>
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference a custom environment variable:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
deepseek:
|
||||
api-key: ${DEEPSEEK_API_KEY}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export DEEPSEEK_API_KEY=<your-deepseek-api-key>
|
||||
----
|
||||
|
||||
You can also set this configuration programmatically in your application code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
// Retrieve API key from a secure source or environment variable
|
||||
String apiKey = System.getenv("DEEPSEEK_API_KEY");
|
||||
----
|
||||
|
||||
=== Add Repositories and BOM
|
||||
|
||||
@@ -18,21 +18,55 @@ for examples of using Groq with Spring AI.
|
||||
|
||||
== Prerequisites
|
||||
|
||||
* Create an API Key.
|
||||
Please visit https://console.groq.com/keys[here] to create an API Key.
|
||||
* **Create an API Key**:
|
||||
Visit https://console.groq.com/keys[here] to create an API Key.
|
||||
The Spring AI project defines a configuration property named `spring.ai.openai.api-key` that you should set to the value of the `API Key` obtained from groq.com.
|
||||
* Set the Groq URL.
|
||||
|
||||
* **Set the Groq URL**:
|
||||
You have to set the `spring.ai.openai.base-url` property to `https://api.groq.com/openai`.
|
||||
* Select a https://console.groq.com/docs/models[Groq Model].
|
||||
Use the `spring.ai.openai.chat.options.model=<model name>` property to set the Model.
|
||||
|
||||
Exporting an environment variable is one way to set that configuration property:
|
||||
* **Select a Groq Model**:
|
||||
Use the `spring.ai.openai.chat.model=<model name>` property to select from the available https://console.groq.com/docs/models[Groq Models].
|
||||
|
||||
[source,shell]
|
||||
You can set these configuration properties in your `application.properties` file:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_OPENAI_API_KEY=<INSERT GROQ API KEY HERE>
|
||||
export SPRING_AI_OPENAI_BASE_URL=https://api.groq.com/openai
|
||||
export SPRING_AI_OPENAI_CHAT_MODEL=llama3-70b-8192
|
||||
spring.ai.openai.api-key=<your-groq-api-key>
|
||||
spring.ai.openai.base-url=https://api.groq.com/openai
|
||||
spring.ai.openai.chat.model=llama3-70b-8192
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference custom environment variables:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
openai:
|
||||
api-key: ${GROQ_API_KEY}
|
||||
base-url: ${GROQ_BASE_URL}
|
||||
chat:
|
||||
model: ${GROQ_MODEL}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export GROQ_API_KEY=<your-groq-api-key>
|
||||
export GROQ_BASE_URL=https://api.groq.com/openai
|
||||
export GROQ_MODEL=llama3-70b-8192
|
||||
----
|
||||
|
||||
You can also set these configurations programmatically in your application code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
// Retrieve configuration from secure sources or environment variables
|
||||
String apiKey = System.getenv("GROQ_API_KEY");
|
||||
String baseUrl = System.getenv("GROQ_BASE_URL");
|
||||
String model = System.getenv("GROQ_MODEL");
|
||||
----
|
||||
|
||||
=== Add Repositories and BOM
|
||||
|
||||
@@ -10,15 +10,49 @@ TIP: For a complete and up-to-date list of supported models and architectures, s
|
||||
|
||||
You will need to create an Inference Endpoint on Hugging Face and create an API token to access the endpoint.
|
||||
Further details can be found link:https://huggingface.co/docs/inference-endpoints/index[here].
|
||||
The Spring AI project defines a configuration property named `spring.ai.huggingface.chat.api-key` that you should set to the value of the API token obtained from Hugging Face.
|
||||
There is also a configuration property named `spring.ai.huggingface.chat.url` that you should set to the inference endpoint URL obtained when provisioning your model in Hugging Face.
|
||||
You can find this on the Inference Endpoint's UI link:https://ui.endpoints.huggingface.co/[here].
|
||||
Exporting environment variables is one way to set these configuration properties:
|
||||
|
||||
[source,shell]
|
||||
The Spring AI project defines two configuration properties:
|
||||
|
||||
1. `spring.ai.huggingface.chat.api-key`: Set this to the value of the API token obtained from Hugging Face.
|
||||
2. `spring.ai.huggingface.chat.url`: Set this to the inference endpoint URL obtained when provisioning your model in Hugging Face.
|
||||
|
||||
You can find your inference endpoint URL on the Inference Endpoint's UI link:https://ui.endpoints.huggingface.co/[here].
|
||||
|
||||
You can set these configuration properties in your `application.properties` file:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_HUGGINGFACE_CHAT_API_KEY=<INSERT KEY HERE>
|
||||
export SPRING_AI_HUGGINGFACE_CHAT_URL=<INSERT INFERENCE ENDPOINT URL HERE>
|
||||
spring.ai.huggingface.chat.api-key=<your-huggingface-api-key>
|
||||
spring.ai.huggingface.chat.url=<your-inference-endpoint-url>
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference custom environment variables:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
huggingface:
|
||||
chat:
|
||||
api-key: ${HUGGINGFACE_API_KEY}
|
||||
url: ${HUGGINGFACE_ENDPOINT_URL}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export HUGGINGFACE_API_KEY=<your-huggingface-api-key>
|
||||
export HUGGINGFACE_ENDPOINT_URL=<your-inference-endpoint-url>
|
||||
----
|
||||
|
||||
You can also set these configurations programmatically in your application code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
// Retrieve API key and endpoint URL from secure sources or environment variables
|
||||
String apiKey = System.getenv("HUGGINGFACE_API_KEY");
|
||||
String endpointUrl = System.getenv("HUGGINGFACE_ENDPOINT_URL");
|
||||
----
|
||||
|
||||
=== Add Repositories and BOM
|
||||
|
||||
@@ -7,12 +7,39 @@ Spring AI supports the various AI language models from MiniMax. You can interact
|
||||
You will need to create an API with MiniMax to access MiniMax language models.
|
||||
|
||||
Create an account at https://www.minimaxi.com/login[MiniMax registration page] and generate the token on the https://www.minimaxi.com/user-center/basic-information/interface-key[API Keys page].
|
||||
The Spring AI project defines a configuration property named `spring.ai.minimax.api-key` that you should set to the value of the `API Key` obtained from https://www.minimaxi.com/user-center/basic-information/interface-key[API Keys page].
|
||||
Exporting an environment variable is one way to set that configuration property:
|
||||
|
||||
[source,shell]
|
||||
The Spring AI project defines a configuration property named `spring.ai.minimax.api-key` that you should set to the value of the `API Key` obtained from the API Keys page.
|
||||
|
||||
You can set this configuration property in your `application.properties` file:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_MINIMAX_API_KEY=<INSERT KEY HERE>
|
||||
spring.ai.minimax.api-key=<your-minimax-api-key>
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference an environment variable:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
minimax:
|
||||
api-key: ${MINIMAX_API_KEY}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export MINIMAX_API_KEY=<your-minimax-api-key>
|
||||
----
|
||||
|
||||
You can also set this configuration programmatically in your application code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
// Retrieve API key from a secure source or environment variable
|
||||
String apiKey = System.getenv("MINIMAX_API_KEY");
|
||||
----
|
||||
|
||||
=== Add Repositories and BOM
|
||||
@@ -298,4 +325,4 @@ Flux<ChatResponse> streamResponse = chatModel.stream(new Prompt(this.messages, t
|
||||
==== MiniMaxApi Samples
|
||||
* The link:https://github.com/spring-projects/spring-ai/blob/main/models/spring-ai-minimax/src/test/java/org/springframework/ai/minimax/api/MiniMaxApiIT.java[MiniMaxApiIT.java] test provides some general examples how to use the lightweight library.
|
||||
|
||||
* The link:https://github.com/spring-projects/spring-ai/blob/main/models/spring-ai-minimax/src/test/java/org/springframework/ai/minimax/api/MiniMaxApiToolFunctionCallIT.java[MiniMaxApiToolFunctionCallIT.java] test shows how to use the low-level API to call tool functions.>
|
||||
* The link:https://github.com/spring-projects/spring-ai/blob/main/models/spring-ai-minimax/src/test/java/org/springframework/ai/minimax/api/MiniMaxApiToolFunctionCallIT.java[MiniMaxApiToolFunctionCallIT.java] test shows how to use the low-level API to call tool functions.>
|
||||
|
||||
@@ -8,13 +8,41 @@ Check the xref:_openai_api_compatibility[OpenAI API compatibility] section to le
|
||||
== Prerequisites
|
||||
|
||||
You will need to create an API with Mistral AI to access Mistral AI language models.
|
||||
Create an account at https://auth.mistral.ai/ui/registration[Mistral AI registration page] and generate the token on the https://console.mistral.ai/api-keys/[API Keys page].
|
||||
The Spring AI project defines a configuration property named `spring.ai.mistralai.api-key` that you should set to the value of the `API Key` obtained from console.mistral.ai.
|
||||
Exporting an environment variable is one way to set that configuration property:
|
||||
|
||||
[source,shell]
|
||||
Create an account at https://auth.mistral.ai/ui/registration[Mistral AI registration page] and generate the token on the https://console.mistral.ai/api-keys/[API Keys page].
|
||||
|
||||
The Spring AI project defines a configuration property named `spring.ai.mistralai.api-key` that you should set to the value of the `API Key` obtained from console.mistral.ai.
|
||||
|
||||
You can set this configuration property in your `application.properties` file:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_MISTRALAI_API_KEY=<INSERT KEY HERE>
|
||||
spring.ai.mistralai.api-key=<your-mistralai-api-key>
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference a custom environment variable:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
mistralai:
|
||||
api-key: ${MISTRALAI_API_KEY}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export MISTRALAI_API_KEY=<your-mistralai-api-key>
|
||||
----
|
||||
|
||||
You can also set this configuration programmatically in your application code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
// Retrieve API key from a secure source or environment variable
|
||||
String apiKey = System.getenv("MISTRALAI_API_KEY");
|
||||
----
|
||||
|
||||
=== Add Repositories and BOM
|
||||
|
||||
@@ -5,13 +5,41 @@ Spring AI supports the various AI language models from OpenAI, the company behin
|
||||
== Prerequisites
|
||||
|
||||
You will need to create an API with OpenAI to access ChatGPT models.
|
||||
Create an account at https://platform.openai.com/signup[OpenAI signup page] and generate the token on the https://platform.openai.com/account/api-keys[API Keys page].
|
||||
The Spring AI project defines a configuration property named `spring.ai.openai.api-key` that you should set to the value of the `API Key` obtained from openai.com.
|
||||
Exporting an environment variable is one way to set that configuration property:
|
||||
|
||||
[source,shell]
|
||||
Create an account at https://platform.openai.com/signup[OpenAI signup page] and generate the token on the https://platform.openai.com/account/api-keys[API Keys page].
|
||||
|
||||
The Spring AI project defines a configuration property named `spring.ai.openai.api-key` that you should set to the value of the `API Key` obtained from openai.com.
|
||||
|
||||
You can set this configuration property in your `application.properties` file:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_OPENAI_API_KEY=<INSERT KEY HERE>
|
||||
spring.ai.openai.api-key=<your-openai-api-key>
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference a custom environment variable:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
openai:
|
||||
api-key: ${OPENAI_API_KEY}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export OPENAI_API_KEY=<your-openai-api-key>
|
||||
----
|
||||
|
||||
You can also set this configuration programmatically in your application code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
// Retrieve API key from a secure source or environment variable
|
||||
String apiKey = System.getenv("OPENAI_API_KEY");
|
||||
----
|
||||
|
||||
=== Add Repositories and BOM
|
||||
|
||||
@@ -17,24 +17,63 @@ Check the https://github.com/spring-projects/spring-ai/blob/main/models/spring-a
|
||||
== Prerequisites
|
||||
|
||||
* **Create an API Key**:
|
||||
Visit https://docs.perplexity.ai/guides/getting-started[here] to create an API Key. Configure it using the `spring.ai.openai.api-key` property in your Spring AI project.
|
||||
Visit https://docs.perplexity.ai/guides/getting-started[here] to create an API Key.
|
||||
Configure it using the `spring.ai.openai.api-key` property in your Spring AI project.
|
||||
|
||||
* **Set the Perplexity Base URL**:
|
||||
Set the `spring.ai.openai.base-url` property to `https://api.perplexity.ai`.
|
||||
|
||||
* **Select a Perplexity Model**:
|
||||
Use the `spring.ai.openai.chat.model=<model name>` property to specify the model. Refer to https://docs.perplexity.ai/guides/model-cards[Supported Models] for available options.
|
||||
Use the `spring.ai.openai.chat.model=<model name>` property to specify the model.
|
||||
Refer to https://docs.perplexity.ai/guides/model-cards[Supported Models] for available options.
|
||||
|
||||
* **Set the chat completions path**:
|
||||
Set the `spring.ai.openai.chat.completions-path` to `/chat/completions` . Refer to https://docs.perplexity.ai/api-reference/chat-completions[chat completions api] for more details.
|
||||
Set the `spring.ai.openai.chat.completions-path` to `/chat/completions`.
|
||||
Refer to https://docs.perplexity.ai/api-reference/chat-completions[chat completions api] for more details.
|
||||
|
||||
Example environment variables configuration:
|
||||
You can set these configuration properties in your `application.properties` file:
|
||||
|
||||
[source,shell]
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_OPENAI_API_KEY=<INSERT PERPLEXITY API KEY HERE>
|
||||
export SPRING_AI_OPENAI_BASE_URL=https://api.perplexity.ai
|
||||
export SPRING_AI_OPENAI_CHAT_MODEL=llama-3.1-sonar-small-128k-online
|
||||
spring.ai.openai.api-key=<your-perplexity-api-key>
|
||||
spring.ai.openai.base-url=https://api.perplexity.ai
|
||||
spring.ai.openai.chat.model=llama-3.1-sonar-small-128k-online
|
||||
spring.ai.openai.chat.completions-path=/chat/completions
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference custom environment variables:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
openai:
|
||||
api-key: ${PERPLEXITY_API_KEY}
|
||||
base-url: ${PERPLEXITY_BASE_URL}
|
||||
chat:
|
||||
model: ${PERPLEXITY_MODEL}
|
||||
completions-path: ${PERPLEXITY_COMPLETIONS_PATH}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export PERPLEXITY_API_KEY=<your-perplexity-api-key>
|
||||
export PERPLEXITY_BASE_URL=https://api.perplexity.ai
|
||||
export PERPLEXITY_MODEL=llama-3.1-sonar-small-128k-online
|
||||
export PERPLEXITY_COMPLETIONS_PATH=/chat/completions
|
||||
----
|
||||
|
||||
You can also set these configurations programmatically in your application code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
// Retrieve configuration from secure sources or environment variables
|
||||
String apiKey = System.getenv("PERPLEXITY_API_KEY");
|
||||
String baseUrl = System.getenv("PERPLEXITY_BASE_URL");
|
||||
String model = System.getenv("PERPLEXITY_MODEL");
|
||||
String completionsPath = System.getenv("PERPLEXITY_COMPLETIONS_PATH");
|
||||
----
|
||||
|
||||
=== Add Repositories and BOM
|
||||
|
||||
@@ -7,12 +7,39 @@ Spring AI supports the various AI language models from ZhiPu AI. You can interac
|
||||
You will need to create an API with ZhiPuAI to access ZhiPu AI language models.
|
||||
|
||||
Create an account at https://open.bigmodel.cn/login[ZhiPu AI registration page] and generate the token on the https://open.bigmodel.cn/usercenter/apikeys[API Keys page].
|
||||
The Spring AI project defines a configuration property named `spring.ai.zhipuai.api-key` that you should set to the value of the `API Key` obtained from https://open.bigmodel.cn/usercenter/apikeys[API Keys page].
|
||||
Exporting an environment variable is one way to set that configuration property:
|
||||
|
||||
[source,shell]
|
||||
The Spring AI project defines a configuration property named `spring.ai.zhipuai.api-key` that you should set to the value of the `API Key` obtained from the API Keys page.
|
||||
|
||||
You can set this configuration property in your `application.properties` file:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_ZHIPU_AI_API_KEY=<INSERT KEY HERE>
|
||||
spring.ai.zhipuai.api-key=<your-zhipuai-api-key>
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference a custom environment variable:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
zhipuai:
|
||||
api-key: ${ZHIPUAI_API_KEY}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export ZHIPUAI_API_KEY=<your-zhipuai-api-key>
|
||||
----
|
||||
|
||||
You can also set this configuration programmatically in your application code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
// Retrieve API key from a secure source or environment variable
|
||||
String apiKey = System.getenv("ZHIPUAI_API_KEY");
|
||||
----
|
||||
|
||||
=== Add Repositories and BOM
|
||||
@@ -265,4 +292,4 @@ Flux<ChatCompletionChunk> streamResponse = this.zhiPuAiApi.chatCompletionStream(
|
||||
Follow the https://github.com/spring-projects/spring-ai/blob/main/models/spring-ai-zhipuai/src/main/java/org/springframework/ai/zhipuai/api/ZhiPuAiApi.java[ZhiPuAiApi.java]'s JavaDoc for further information.
|
||||
|
||||
==== ZhiPuAiApi Samples
|
||||
* The link:https://github.com/spring-projects/spring-ai/blob/main/models/spring-ai-zhipuai/src/test/java/org/springframework/ai/zhipuai/api/ZhiPuAiApiIT.java[ZhiPuAiApiIT.java] test provides some general examples how to use the lightweight library.
|
||||
* The link:https://github.com/spring-projects/spring-ai/blob/main/models/spring-ai-zhipuai/src/test/java/org/springframework/ai/zhipuai/api/ZhiPuAiApiIT.java[ZhiPuAiApiIT.java] test provides some general examples how to use the lightweight library.
|
||||
|
||||
@@ -20,30 +20,73 @@ Obtain your Azure OpenAI `endpoint` and `api-key` from the Azure OpenAI Service
|
||||
|
||||
Spring AI defines two configuration properties:
|
||||
|
||||
|
||||
1. `spring.ai.azure.openai.api-key`: Set this to the value of the `API Key` obtained from Azure.
|
||||
2. `spring.ai.azure.openai.endpoint`: Set this to the endpoint URL obtained when provisioning your model in Azure.
|
||||
|
||||
You can set these configuration properties by exporting environment variables:
|
||||
You can set these configuration properties in your `application.properties` or `application.yml` file:
|
||||
|
||||
[source,shell]
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_AZURE_OPENAI_API_KEY=<INSERT AZURE KEY HERE>
|
||||
export SPRING_AI_AZURE_OPENAI_ENDPOINT=<INSERT ENDPOINT URL HERE>
|
||||
spring.ai.azure.openai.api-key=<your-azure-api-key>
|
||||
spring.ai.azure.openai.endpoint=<your-azure-endpoint-url>
|
||||
----
|
||||
|
||||
If you prefer to use environment variables for sensitive information like API keys, you can use Spring Expression Language (SpEL) in your configuration:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
azure:
|
||||
openai:
|
||||
api-key: ${AZURE_OPENAI_API_KEY}
|
||||
endpoint: ${AZURE_OPENAI_ENDPOINT}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export AZURE_OPENAI_API_KEY=<your-azure-openai-api-key>
|
||||
export AZURE_OPENAI_ENDPOINT=<your-azure-endpoint-url>
|
||||
----
|
||||
|
||||
=== OpenAI Key
|
||||
|
||||
To authenticate with the OpenAI service (not Azure), provide an OpenAI API key. This will automatically set the endpoint to https://api.openai.com/v1.
|
||||
To authenticate with the OpenAI service (not Azure), provide an OpenAI API key.
|
||||
This will automatically set the endpoint to https://api.openai.com/v1.
|
||||
|
||||
When using this approach, set the `spring.ai.azure.openai.chat.options.deployment-name` property to the name of the https://platform.openai.com/docs/models[OpenAI model] you wish to use.
|
||||
|
||||
[source,shell]
|
||||
In your application configuration:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_AZURE_OPENAI_OPENAI_API_KEY=<INSERT OPENAI KEY HERE>
|
||||
spring.ai.azure.openai.openai-api-key=<your-azure-openai-key>
|
||||
spring.ai.azure.openai.chat.options.deployment-name=<openai-model-name>
|
||||
----
|
||||
|
||||
Using environment variables with SpEL:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
azure:
|
||||
openai:
|
||||
openai-api-key: ${AZURE_OPENAI_API_KEY}
|
||||
chat:
|
||||
options:
|
||||
deployment-name: ${OPENAI_MODEL_NAME}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export AZURE_OPENAI_API_KEY=<your-openai-key>
|
||||
export OPENAI_MODEL_NAME=<openai-model-name>
|
||||
----
|
||||
=== Microsoft Entra ID
|
||||
|
||||
For keyless authentication using Microsoft Entra ID (formerly Azure Active Directory), set _only_ the `spring.ai.azure.openai.endpoint` configuration property and _not_ the api-key property mentioned above.
|
||||
|
||||
@@ -47,13 +47,36 @@ TIP: Refer to the xref:getting-started.adoc#dependency-management[Dependency Man
|
||||
|
||||
=== Enable Cohere Embedding Support
|
||||
|
||||
By default the Cohere model is disabled.
|
||||
To enable it set the `spring.ai.model.embedding` property to `bedrock-cohere`.
|
||||
Exporting environment variable is one way to set this configuration property:
|
||||
By default, the Cohere embedding model is disabled.
|
||||
To enable it, set the `spring.ai.model.embedding` property to `bedrock-cohere` in your application configuration:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
spring.ai.model.embedding=bedrock-cohere
|
||||
----
|
||||
|
||||
Alternatively, you can use Spring Expression Language (SpEL) to reference an environment variable:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
model:
|
||||
embedding: ${AI_MODEL_EMBEDDING}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export AI_MODEL_EMBEDDING=bedrock-cohere
|
||||
----
|
||||
|
||||
You can also set this property using Java system properties when starting your application:
|
||||
|
||||
[source,shell]
|
||||
----
|
||||
export SPRING_AI_MODEL_EMBEDDING=bedrock-cohere
|
||||
java -Dspring.ai.model.embedding=bedrock-cohere -jar your-application.jar
|
||||
----
|
||||
|
||||
=== Embedding Properties
|
||||
|
||||
@@ -54,13 +54,36 @@ TIP: Refer to the xref:getting-started.adoc#dependency-management[Dependency Man
|
||||
|
||||
=== Enable Titan Embedding Support
|
||||
|
||||
By default the Titan embedding model is disabled.
|
||||
To enable it set the `spring.ai.model.embedding` property to `bedrock-titan`.
|
||||
Exporting environment variable is one way to set this configuration property:
|
||||
By default, the Titan embedding model is disabled.
|
||||
To enable it, set the `spring.ai.model.embedding` property to `bedrock-titan` in your application configuration:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
spring.ai.model.embedding=bedrock-titan
|
||||
----
|
||||
|
||||
Alternatively, you can use Spring Expression Language (SpEL) to reference an environment variable:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
model:
|
||||
embedding: ${AI_MODEL_EMBEDDING}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export AI_MODEL_EMBEDDING=bedrock-titan
|
||||
----
|
||||
|
||||
You can also set this property using Java system properties when starting your application:
|
||||
|
||||
[source,shell]
|
||||
----
|
||||
export SPRING_AI_MODEL_EMBEDDING=bedrock-titan
|
||||
java -Dspring.ai.model.embedding=bedrock-titan -jar your-application.jar
|
||||
----
|
||||
|
||||
=== Embedding Properties
|
||||
@@ -236,4 +259,4 @@ TitanEmbeddingRequest request = TitanEmbeddingRequest.builder()
|
||||
.build();
|
||||
|
||||
TitanEmbeddingResponse response = this.titanEmbedApi.embedding(this.request);
|
||||
----
|
||||
----
|
||||
|
||||
@@ -7,12 +7,39 @@ Spring AI supports the various AI language models from MiniMax. You can interact
|
||||
You will need to create an API with MiniMax to access MiniMax language models.
|
||||
|
||||
Create an account at https://www.minimaxi.com/login[MiniMax registration page] and generate the token on the https://www.minimaxi.com/user-center/basic-information/interface-key[API Keys page].
|
||||
The Spring AI project defines a configuration property named `spring.ai.minimax.api-key` that you should set to the value of the `API Key` obtained from https://www.minimaxi.com/user-center/basic-information/interface-key[API Keys page].
|
||||
Exporting an environment variable is one way to set that configuration property:
|
||||
|
||||
[source,shell]
|
||||
The Spring AI project defines a configuration property named `spring.ai.minimax.api-key` that you should set to the value of the `API Key` obtained from the API Keys page.
|
||||
|
||||
You can set this configuration property in your `application.properties` file:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_MINIMAX_API_KEY=<INSERT KEY HERE>
|
||||
spring.ai.minimax.api-key=<your-minimax-api-key>
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference an environment variable:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
minimax:
|
||||
api-key: ${MINIMAX_API_KEY}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export MINIMAX_API_KEY=<your-minimax-api-key>
|
||||
----
|
||||
|
||||
You can also set this configuration programmatically in your application code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
// Retrieve API key from a secure source or environment variable
|
||||
String apiKey = System.getenv("MINIMAX_API_KEY");
|
||||
----
|
||||
|
||||
=== Add Repositories and BOM
|
||||
|
||||
@@ -8,12 +8,39 @@ Embeddings are vectorial representations of text that capture the semantic meani
|
||||
You will need to create an API with MistralAI to access MistralAI embeddings models.
|
||||
|
||||
Create an account at https://auth.mistral.ai/ui/registration[MistralAI registration page] and generate the token on the https://console.mistral.ai/api-keys/[API Keys page].
|
||||
The Spring AI project defines a configuration property named `spring.ai.mistralai.api-key` that you should set to the value of the `API Key` obtained from console.mistral.ai.
|
||||
Exporting an environment variable is one way to set that configuration property:
|
||||
|
||||
[source,shell]
|
||||
The Spring AI project defines a configuration property named `spring.ai.mistralai.api-key` that you should set to the value of the `API Key` obtained from console.mistral.ai.
|
||||
|
||||
You can set this configuration property in your `application.properties` file:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_MISTRALAI_API_KEY=<INSERT KEY HERE>
|
||||
spring.ai.mistralai.api-key=<your-mistralai-api-key>
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference an environment variable:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
mistralai:
|
||||
api-key: ${MISTRALAI_API_KEY}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export MISTRALAI_API_KEY=<your-mistralai-api-key>
|
||||
----
|
||||
|
||||
You can also set this configuration programmatically in your application code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
// Retrieve API key from a secure source or environment variable
|
||||
String apiKey = System.getenv("MISTRALAI_API_KEY");
|
||||
----
|
||||
|
||||
=== Add Repositories and BOM
|
||||
|
||||
@@ -9,12 +9,39 @@ An embedding is a vector (list) of floating point numbers. The distance between
|
||||
You will need to create an API with OpenAI to access OpenAI embeddings models.
|
||||
|
||||
Create an account at https://platform.openai.com/signup[OpenAI signup page] and generate the token on the https://platform.openai.com/account/api-keys[API Keys page].
|
||||
The Spring AI project defines a configuration property named `spring.ai.openai.api-key` that you should set to the value of the `API Key` obtained from openai.com.
|
||||
Exporting an environment variable is one way to set that configuration property:
|
||||
|
||||
[source,shell]
|
||||
The Spring AI project defines a configuration property named `spring.ai.openai.api-key` that you should set to the value of the `API Key` obtained from openai.com.
|
||||
|
||||
You can set this configuration property in your `application.properties` file:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_OPENAI_API_KEY=<INSERT KEY HERE>
|
||||
spring.ai.openai.api-key=<your-openai-api-key>
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference an environment variable:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
openai:
|
||||
api-key: ${OPENAI_API_KEY}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export OPENAI_API_KEY=<your-openai-api-key>
|
||||
----
|
||||
|
||||
You can also set this configuration programmatically in your application code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
// Retrieve API key from a secure source or environment variable
|
||||
String apiKey = System.getenv("OPENAI_API_KEY");
|
||||
----
|
||||
|
||||
=== Add Repositories and BOM
|
||||
|
||||
@@ -9,12 +9,39 @@ An embedding is a vector (list) of floating point numbers. The distance between
|
||||
You will need to create an API with ZhiPuAI to access ZhiPu AI language models.
|
||||
|
||||
Create an account at https://open.bigmodel.cn/login[ZhiPu AI registration page] and generate the token on the https://open.bigmodel.cn/usercenter/apikeys[API Keys page].
|
||||
The Spring AI project defines a configuration property named `spring.ai.zhipu.api-key` that you should set to the value of the `API Key` obtained from https://open.bigmodel.cn/usercenter/apikeys[API Keys page].
|
||||
Exporting an environment variable is one way to set that configuration property:
|
||||
|
||||
[source,shell]
|
||||
The Spring AI project defines a configuration property named `spring.ai.zhipu.api-key` that you should set to the value of the `API Key` obtained from the API Keys page.
|
||||
|
||||
You can set this configuration property in your `application.properties` file:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_ZHIPU_AI_API_KEY=<INSERT KEY HERE>
|
||||
spring.ai.zhipu.api-key=<your-zhipu-api-key>
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference an environment variable:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
zhipu:
|
||||
api-key: ${ZHIPU_API_KEY}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export ZHIPU_API_KEY=<your-zhipu-api-key>
|
||||
----
|
||||
|
||||
You can also set this configuration programmatically in your application code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
// Retrieve API key from a secure source or environment variable
|
||||
String apiKey = System.getenv("ZHIPU_API_KEY");
|
||||
----
|
||||
|
||||
=== Add Repositories and BOM
|
||||
|
||||
@@ -6,14 +6,47 @@ Spring AI supports DALL-E, the Image generation model from Azure OpenAI.
|
||||
== Prerequisites
|
||||
|
||||
Obtain your Azure OpenAI `endpoint` and `api-key` from the Azure OpenAI Service section on the link:https://portal.azure.com[Azure Portal].
|
||||
Spring AI defines a configuration property named `spring.ai.azure.openai.api-key` that you should set to the value of the `API Key` obtained from Azure.
|
||||
There is also a configuration property named `spring.ai.azure.openai.endpoint` that you should set to the endpoint URL obtained when provisioning your model in Azure.
|
||||
Exporting environment variables is one way to set these configuration properties:
|
||||
|
||||
[source,shell]
|
||||
Spring AI defines two configuration properties:
|
||||
|
||||
1. `spring.ai.azure.openai.api-key`: Set this to the value of the `API Key` obtained from Azure.
|
||||
2. `spring.ai.azure.openai.endpoint`: Set this to the endpoint URL obtained when provisioning your model in Azure.
|
||||
|
||||
You can set these configuration properties in your `application.properties` file:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_AZURE_OPENAI_API_KEY=<INSERT KEY HERE>
|
||||
export SPRING_AI_AZURE_OPENAI_ENDPOINT=<INSERT ENDPOINT URL HERE>
|
||||
spring.ai.azure.openai.api-key=<your-azure-openai-api-key>
|
||||
spring.ai.azure.openai.endpoint=<your-azure-openai-endpoint>
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference custom environment variables:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
azure:
|
||||
openai:
|
||||
api-key: ${AZURE_OPENAI_API_KEY}
|
||||
endpoint: ${AZURE_OPENAI_ENDPOINT}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export AZURE_OPENAI_API_KEY=<your-azure-openai-api-key>
|
||||
export AZURE_OPENAI_ENDPOINT=<your-azure-openai-endpoint>
|
||||
----
|
||||
|
||||
You can also set these configurations programmatically in your application code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
// Retrieve API key and endpoint from secure sources or environment variables
|
||||
String apiKey = System.getenv("AZURE_OPENAI_API_KEY");
|
||||
String endpoint = System.getenv("AZURE_OPENAI_ENDPOINT");
|
||||
----
|
||||
|
||||
=== Deployment Name
|
||||
|
||||
@@ -6,13 +6,41 @@ Spring AI supports DALL-E, the Image generation model from OpenAI.
|
||||
== Prerequisites
|
||||
|
||||
You will need to create an API key with OpenAI to access ChatGPT models.
|
||||
Create an account at https://platform.openai.com/signup[OpenAI signup page] and generate the token on the https://platform.openai.com/account/api-keys[API Keys page].
|
||||
The Spring AI project defines a configuration property named `spring.ai.openai.api-key` that you should set to the value of the `API Key` obtained from openai.com.
|
||||
Exporting an environment variable is one way to set that configuration property:
|
||||
|
||||
[source,shell]
|
||||
Create an account at https://platform.openai.com/signup[OpenAI signup page] and generate the token on the https://platform.openai.com/account/api-keys[API Keys page].
|
||||
|
||||
The Spring AI project defines a configuration property named `spring.ai.openai.api-key` that you should set to the value of the `API Key` obtained from openai.com.
|
||||
|
||||
You can set this configuration property in your `application.properties` file:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_OPENAI_API_KEY=<INSERT KEY HERE>
|
||||
spring.ai.openai.api-key=<your-openai-api-key>
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference a custom environment variable:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
openai:
|
||||
api-key: ${OPENAI_API_KEY}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export OPENAI_API_KEY=<your-openai-api-key>
|
||||
----
|
||||
|
||||
You can also set this configuration programmatically in your application code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
// Retrieve API key from a secure source or environment variable
|
||||
String apiKey = System.getenv("OPENAI_API_KEY");
|
||||
----
|
||||
|
||||
== Auto-configuration
|
||||
|
||||
@@ -4,14 +4,40 @@ Spring AI supports Stability AI's https://platform.stability.ai/docs/api-referen
|
||||
|
||||
== Prerequisites
|
||||
|
||||
You will need to create an API key with Stability AI to access their AI models, follow their https://platform.stability.ai/docs/getting-started/authentication[Getting Started documentation].
|
||||
You will need to create an API key with Stability AI to access their AI models. Follow their https://platform.stability.ai/docs/getting-started/authentication[Getting Started documentation] to obtain your API key.
|
||||
|
||||
The Spring AI project defines a configuration property named `spring.ai.stabilityai.api-key` that you should set to the value of the `API Key` obtained from Stability AI.
|
||||
Exporting an environment variable is one way to set that configuration property.
|
||||
|
||||
[source,shell]
|
||||
You can set this configuration property in your `application.properties` file:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_STABILITYAI_API_KEY=<INSERT KEY HERE>
|
||||
spring.ai.stabilityai.api-key=<your-stabilityai-api-key>
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference a custom environment variable:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
stabilityai:
|
||||
api-key: ${STABILITYAI_API_KEY}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export STABILITYAI_API_KEY=<your-stabilityai-api-key>
|
||||
----
|
||||
|
||||
You can also set this configuration programmatically in your application code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
// Retrieve API key from a secure source or environment variable
|
||||
String apiKey = System.getenv("STABILITYAI_API_KEY");
|
||||
----
|
||||
|
||||
== Auto-configuration
|
||||
|
||||
@@ -8,13 +8,41 @@ Spring AI supports CogView, the Image generation model from ZhiPuAI.
|
||||
You will need to create an API with ZhiPuAI to access ZhiPu AI language models.
|
||||
|
||||
Create an account at https://open.bigmodel.cn/login[ZhiPu AI registration page] and generate the token on the https://open.bigmodel.cn/usercenter/apikeys[API Keys page].
|
||||
The Spring AI project defines a configuration property named `spring.ai.zhipuai.api-key` that you should set to the value of the `API Key` obtained from https://open.bigmodel.cn/usercenter/apikeys[API Keys page].
|
||||
Exporting an environment variable is one way to set that configuration property:
|
||||
|
||||
[source,shell]
|
||||
The Spring AI project defines a configuration property named `spring.ai.zhipuai.api-key` that you should set to the value of the `API Key` obtained from the API Keys page.
|
||||
|
||||
You can set this configuration property in your `application.properties` file:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
export SPRING_AI_ZHIPU_AI_API_KEY=<INSERT KEY HERE>
|
||||
spring.ai.zhipuai.api-key=<your-zhipuai-api-key>
|
||||
----
|
||||
|
||||
For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference a custom environment variable:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
zhipuai:
|
||||
api-key: ${ZHIPUAI_API_KEY}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
# In your environment or .env file
|
||||
export ZHIPUAI_API_KEY=<your-zhipuai-api-key>
|
||||
----
|
||||
|
||||
You can also set this configuration programmatically in your application code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
// Retrieve API key from a secure source or environment variable
|
||||
String apiKey = System.getenv("ZHIPUAI_API_KEY");
|
||||
----
|
||||
|
||||
=== Add Repositories and BOM
|
||||
|
||||
Spring AI artifacts are published in Maven Central and Spring Snapshot repositories.
|
||||
|
||||
@@ -62,7 +62,7 @@ Here is an example of the needed bean:
|
||||
@Bean
|
||||
public EmbeddingModel embeddingModel() {
|
||||
// Can be any other EmbeddingModel implementation.
|
||||
return new OpenAiEmbeddingModel(new OpenAiApi(System.getenv("SPRING_AI_OPENAI_API_KEY")));
|
||||
return new OpenAiEmbeddingModel(OpenAiApi.builder().apiKey(System.getenv("OPENAI_API_KEY")).build());
|
||||
}
|
||||
----
|
||||
|
||||
|
||||
@@ -81,9 +81,9 @@ List<Document> results = vectorStore.similaritySearch(SearchRequest.query("Sprin
|
||||
=== Configuration Properties
|
||||
|
||||
To connect to Couchbase and use the `CouchbaseSearchVectorStore`, you need to provide access details for your instance.
|
||||
A simple configuration can either be provided via Spring Boot's `application.properties`,
|
||||
Configuration can be provided via Spring Boot's `application.properties`:
|
||||
|
||||
[application,properties]
|
||||
[source,properties]
|
||||
----
|
||||
spring.ai.openai.api-key=<key>
|
||||
spring.couchbase.connection-string=<conn_string>
|
||||
@@ -91,19 +91,44 @@ spring.couchbase.username=<username>
|
||||
spring.couchbase.password=<password>
|
||||
----
|
||||
|
||||
environment variables,
|
||||
If you prefer to use environment variables for sensitive information like passwords or API keys, you have multiple options:
|
||||
|
||||
==== Option 1: Using Spring Expression Language (SpEL)
|
||||
|
||||
You can use custom environment variable names and reference them in your application configuration using SpEL:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
openai:
|
||||
api-key: ${OPENAI_API_KEY}
|
||||
couchbase:
|
||||
connection-string: ${COUCHBASE_CONN_STRING}
|
||||
username: ${COUCHBASE_USER}
|
||||
password: ${COUCHBASE_PASSWORD}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
export SPRING_COUCHBASE_CONNECTION_STRINGS=<couchbase connection string like couchbase://localhost>
|
||||
export SPRING_COUCHBASE_USERNAME=<couchbase username>
|
||||
export SPRING_COUCHBASE_PASSWORD=<couchbase password>
|
||||
# API key if needed, e.g. OpenAI
|
||||
export SPRING_AI_OPENAI_API_KEY=<api-key>
|
||||
# In your environment or .env file
|
||||
export OPENAI_API_KEY=<api-key>
|
||||
export COUCHBASE_CONN_STRING=<couchbase connection string like couchbase://localhost>
|
||||
export COUCHBASE_USER=<couchbase username>
|
||||
export COUCHBASE_PASSWORD=<couchbase password>
|
||||
----
|
||||
|
||||
or can be a mix of those.
|
||||
For example, if you want to store your password as an environment variable but keep the rest in the plain `application.yml` file.
|
||||
==== Option 2: Accessing Environment Variables Programmatically
|
||||
|
||||
Alternatively, you can access environment variables in your Java code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
String apiKey = System.getenv("OPENAI_API_KEY");
|
||||
----
|
||||
|
||||
This approach gives you flexibility in naming your environment variables while keeping sensitive information out of your application configuration files.
|
||||
|
||||
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`.
|
||||
|
||||
|
||||
@@ -64,7 +64,7 @@ Here is an example of the needed bean:
|
||||
@Bean
|
||||
public EmbeddingModel embeddingModel() {
|
||||
// Can be any other EmbeddingModel implementation.
|
||||
return new OpenAiEmbeddingModel(new OpenAiApi(System.getenv("SPRING_AI_OPENAI_API_KEY")));
|
||||
return new OpenAiEmbeddingModel(new OpenAiApi(System.getenv("OPENAI_API_KEY")));
|
||||
}
|
||||
----
|
||||
|
||||
|
||||
@@ -44,7 +44,7 @@ TIP: Refer to the xref:getting-started.adoc#dependency-management[Dependency Man
|
||||
== Configuration
|
||||
|
||||
To connect to Weaviate and use the `WeaviateVectorStore`, you need to provide access details for your instance.
|
||||
A simple configuration can either be provided via Spring Boot's _application.properties_,
|
||||
Configuration can be provided via Spring Boot's _application.properties_:
|
||||
|
||||
[source,properties]
|
||||
----
|
||||
@@ -55,20 +55,46 @@ spring.ai.vectorstore.weaviate.api-key=<your_api_key>
|
||||
spring.ai.openai.api-key=<api-key>
|
||||
----
|
||||
|
||||
environment variables,
|
||||
If you prefer to use environment variables for sensitive information like API keys, you have multiple options:
|
||||
|
||||
=== Option 1: Using Spring Expression Language (SpEL)
|
||||
|
||||
You can use custom environment variable names and reference them in your application configuration:
|
||||
|
||||
[source,yaml]
|
||||
----
|
||||
# In application.yml
|
||||
spring:
|
||||
ai:
|
||||
vectorstore:
|
||||
weaviate:
|
||||
host: ${WEAVIATE_HOST}
|
||||
scheme: ${WEAVIATE_SCHEME}
|
||||
api-key: ${WEAVIATE_API_KEY}
|
||||
openai:
|
||||
api-key: ${OPENAI_API_KEY}
|
||||
----
|
||||
|
||||
[source,bash]
|
||||
----
|
||||
export SPRING_AI_VECTORSTORE_WEAVIATE_HOST=<host_of_your_weaviate_instance>
|
||||
export SPRING_AI_VECTORSTORE_WEAVIATE_SCHEME=<http_or_https>
|
||||
export SPRING_AI_VECTORSTORE_WEAVIATE_API_KEY=<your_api_key>
|
||||
# API key if needed, e.g. OpenAI
|
||||
export SPRING_AI_OPENAI_API_KEY=<api-key>
|
||||
# In your environment or .env file
|
||||
export WEAVIATE_HOST=<host_of_your_weaviate_instance>
|
||||
export WEAVIATE_SCHEME=<http_or_https>
|
||||
export WEAVIATE_API_KEY=<your_api_key>
|
||||
export OPENAI_API_KEY=<api-key>
|
||||
----
|
||||
|
||||
or can be a mix of those.
|
||||
=== Option 2: Accessing Environment Variables Programmatically
|
||||
|
||||
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`.
|
||||
Alternatively, you can access environment variables in your Java code:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
String weaviateApiKey = System.getenv("WEAVIATE_API_KEY");
|
||||
String openAiApiKey = System.getenv("OPENAI_API_KEY");
|
||||
----
|
||||
|
||||
NOTE: If you choose to create a shell script to manage your environment variables, be sure to run it prior to starting your application by "sourcing" the file, i.e. `source <your_script_name>.sh`.
|
||||
|
||||
== Auto-configuration
|
||||
|
||||
@@ -100,14 +126,17 @@ TIP: Refer to the xref:getting-started.adoc#artifact-repositories[Artifact Repos
|
||||
|
||||
Additionally, you will need a configured `EmbeddingModel` bean. Refer to the xref:api/embeddings.adoc#available-implementations[EmbeddingModel] section for more information.
|
||||
|
||||
Here is an example of the needed bean:
|
||||
Here is an example of the required bean:
|
||||
|
||||
[source,java]
|
||||
----
|
||||
@Bean
|
||||
public EmbeddingModel embeddingModel() {
|
||||
// Can be any other Embeddingmodel implementation.
|
||||
return new OpenAiEmbeddingModel(new OpenAiApi(System.getenv("SPRING_AI_OPENAI_API_KEY")));
|
||||
// Retrieve API key from a secure source or environment variable
|
||||
String apiKey = System.getenv("OPENAI_API_KEY");
|
||||
|
||||
// Can be any other EmbeddingModel implementation
|
||||
return new OpenAiEmbeddingModel(OpenAiApi.builder().apiKey(apiKey).build());
|
||||
}
|
||||
----
|
||||
|
||||
|
||||
Reference in New Issue
Block a user