AI Configuration Parameters
All the following parameters must be configured in the openkm.properties file. Once configured, the OpenKM service must be restarted for the changes to take effect.
Some functionalities must be enabled in the user's Profiles for them to be available.
From Administration > AI Prompt, prompts can be defined in combination with Creating your own AI prompt plugin.
OpenKM utilizes Spring AI (specifically version 1.1.2 at the time of this documentation). The parameters shown here represent only a subset of those provided by this library. For comprehensive information, please consult the Spring AI documentation:
- Chat Models: https://docs.spring.io/spring-ai/reference/api/chatmodel.html
- Model Comparison: https://docs.spring.io/spring-ai/reference/api/chat/comparison.html
- OpenAI Chat Parameters: https://docs.spring.io/spring-ai/reference/api/chat/openai-chat.html
Currently supported models include: Anthropic Claude, Azure OpenAI, Google Vertex AI Gemini, Ollama (for running local models), and OpenAI. Additional models from the comparison list can be integrated as needed.
You should only activate one AI model at a time.
An active AI model is required for several OpenKM functionalities, including prompts, AI plugins for document processing, RAG (Retrieval-Augmented Generation), and the MCP client.
AI Provider Configuration
The following parameters define which AI model to use for chat and embedding operations.
| Property | Type | Description |
|---|---|---|
|
spring.ai.model.chat |
String |
Specifies the chat model provider. openai |
|
spring.ai.model.embedding |
String |
Specifies the embedding model provider. openai |
|
spring.ai.openai.api-key |
String |
The API key for authentication. API KEY |
|
spring.ai.openai.chat.options.model |
String |
The specific model version to use. gpt-5-mini |
|
spring.ai.openai.chat.options.temperature |
Float |
Controls randomness in responses (0.0 to 1.0). Lower values make output more focused and deterministic. 1 |
MCP Server Configuration
The Model Context Protocol (MCP) Server allows external applications to interact with OpenKM's core functionalities.
| Property | Type | Description |
|---|---|---|
|
spring.ai.mcp.server.enabled |
Boolean |
Enables or disables the MCP server. Set to false |
|
spring.ai.mcp.server.instructions |
String |
Instructions and description for the MCP server. This server provides basic OpenKM application information and tools. OpenKM is a document management system that allows you to manage your documents. You can use this server to interact with OpenKM's core functionalities through the MCP protocol. |
|
spring.ai.mcp.server.request-timeout |
Duration |
Request timeout duration. 60s |
|
okm.mcp.security.allowed.ips |
String |
Restricts which IP addresses can access the MCP service. Use * to allow all IPs, or specify a specific IP address (e.g., 10.0.0.50) to restrict access. * |
Additional parameters for MCP-specific logging:
To enable detailed logging for the MCP service, add the following parameters to openkm.properties:
logging.level.com.openkm.mcp=DEBUGlogging.level.com.openkm.config.MCPToolSecurityAspect=DEBUG
MCP Client Configuration
OpenKM includes an MCP (Model Context Protocol) client that allows it to connect to external MCP servers.
Important: Do not enable the Spring AI auto-configuration for the MCP client. The parameter spring.ai.mcp.client.enabled must always be set to false. OpenKM uses manual configuration instead.
| Property | Type | Description |
|---|---|---|
|
spring.ai.mcp.client.enabled |
Boolean |
Spring AI MCP client auto-configuration. Must always be false |
|
okm.mcp.manual.client.enabled |
Boolean |
Enables or disables the manual MCP client configuration. false |
|
okm.mcp.manual.connections.server1.url |
String |
URL of the first MCP server to connect to. http://localhost:8080 |
|
okm.mcp.manual.connections.server1.sse-endpoint |
String |
Server-Sent Events (SSE) endpoint for the MCP server. /openkm/sse |
|
okm.mcp.manual.connections.server1.token |
String |
Authentication token for OpenKM. We recommend generating a token with a validity period of one year or more. |
The MCP client supports multiple server connections. To add additional servers, use the same parameter pattern with different server identifiers:
okm.mcp.manual.connections.server2.urlokm.mcp.manual.connections.server2.sse-endpointokm.mcp.manual.connections.server2.token
RAG (Retrieval-Augmented Generation) Configuration
RAG enhances AI responses by retrieving relevant information from a vector database. OpenKM supports different vector store backends.
MariaDB example configuration
| Property | Value |
|---|---|
|
spring.ai.model.embedding |
openai |
|
spring.ai.vectorstore.mariadb.initialize-schema |
true |
|
spring.ai.vectorstore.type |
mariadb |
PostgreSQL example configuration
The PostgreSQL server must have vector support available before enabling this option. This means the server needs the vector extension installed — either by adding the corresponding extension package to an existing PostgreSQL installation, or by using a PostgreSQL Docker image that already includes vector support. Check the documentation for your operating system or Docker distribution for the appropriate installation method.
| Property | Value |
|---|---|
|
spring.ai.model.embedding |
openai |
|
spring.ai.vectorstore.pgvector.initialize-schema |
true |
|
spring.ai.vectorstore.type |
pgvector |
|
spring.ai.vectorstore.similarity.threshold |
0.7 |
Indexing Documents into the RAG
Enabling the RAG through the configuration file is a necessary but not sufficient step. Simply activating it does not cause documents to be automatically vectorized or made available to the Smart Search or Chatbot features. Users must explicitly define which documents, or which areas of the repository, should be indexed in the vector store.
This selective indexing approach is intentional: indexing the entire repository is technically possible, but is generally not recommended, as it may introduce noise into AI responses and increase both storage and processing costs.
Configuring the Feed RAG Automation Rule
OpenKM ships with a built-in automation rule named Feed RAG, designed precisely for this purpose. This rule must be reviewed and activated through the Automation module and works as follows:
- Event: The rule is triggered by the Document text extraction event, at the post phase, that is, after the text has been successfully extracted from a document.
- Validation: A
PathContainscondition determines which documents qualify for indexing. Typically, this is configured with one or more repository folder paths so that only documents stored within those folders are vectorized. - Action: The
FeedRAGaction performs the actual vectorization and stores the document embeddings in the configured vector store.
The most common configuration involves targeting one or several specific folders in the repository, ensuring that only the relevant content is made available to the AI features.
The Feed RAG rule is included with OpenKM by default. Users only need to review and adapt its PathContains validation to match the folders they wish to index.
