schema.wildfly-ai_1_0.xsd Maven / Gradle / Ivy
The AI subsystem root element.
The AI subsystem root type.
The chat language models.
The chat embedding models.
The chat embedding models.
The chat content retrievers.
The embedding models.
An embedding-model provider definition element.
An embedding-model provider definition element.
The embedding stores.
An in-memory embedding-store provider definition element.
A Neo4J embedding-store provider definition element.
A Weaviate embedding-store provider definition element.
The content retrievers.
A content retriever retriving content from an embedding store definition element.
A content retriever retriving content from a web search definition element.
The chat language models.
A chat model provider element.
A chat model provider element.
A chat model provider element.
A provider of an OpenAI chat model.
The name of this provider.
The key to connect to the OpenAI model.
The base url to the chat model endpoint
The connection timeout of the chat model
The frequency penalty of the chat model
Whether to log API requests
Whether to log API responses
The maximum number of token of the chat model
The name of the model to use
The organization id of the chat model
The presence penalty of the chat model
The seed of the chat model
The temperature of the chat model
The top P of the chat model
A provider of an Mistral AI chat model.
The name of this provider.
The key to connect to the Mistral AI model.
The base url to the chat model endpoint
The connection timeout of the chat model
Whether to log API requests
Whether to log API responses
The maximum number of token of the chat model
The name of the model to use
The seed of the chat model
Whether to inject a safety prompt before all conversations.
The temperature of the chat model
The top P of the chat model
A provider of Ollama chat model.
The name of this provider.
The base url to the chat model endpoint
The connection timeout of the chat model
Whether to log API requests
Whether to log API responses
The maximum number of retries for API requests
The model used on Ollama.
The temperature of the chat model
A provider of Ollama embedding model.
The name of this provider.
The base url to the chat model endpoint
The connection timeout of the chat model
Whether to log API requests
Whether to log API responses
The model used on Ollama.
A provider of embedding model.
The name of this provider.
The module to load the embedding model from.
The class from which the embedding model will be instanciated.
A provider of in-memory embedding store.
The name of this provider.
The actual filesystem path. Treated as an absolute path, unless the
'relative-to' attribute is specified, in which case the value
is treated as relative to that path.
Reference to a filesystem path defined in the "paths" section
of the server configuration.
A provider of Neo4J embedding store.
Credential to be used by the configuration.
The name of this provider.
The bolt url to Neo4J server.
The name of the Neo4J database.
The dimension of the embedding vector.
The optional embeddingProperty name
The optional id property name (default: "id").
The optional index name (default: "vector")
The optional label name (default: "Document")
The optional metadata prefix (default: "")
The optional retrieval query
(default: "RETURN properties(node) AS metadata, node.`idProperty` AS `idProperty`, node.`textProperty` AS `textProperty`, node.`embeddingProperty` AS `embeddingProperty`, score")
The optional textProperty property name (default: "text")
The username for connecting to Neo4J server.
A provider of Weaviate embedding store.
The name of this provider.
If true the object id is a hashed ID based on provided text segment else a random ID will be generated.
How the consistency is tuned when writting into weaviate embedding store.
The object class for collections on Weaviate store.
The name of outbound the socket-binding to use to connect ot the Weaviate store.
If the connection to the Weaviate store is secured.
The list of metedata fields to get from the weaviate store.
A content retriever retriving content from an embedding store.
The name of this provider.
The embedding store to retrieve content from the embedding model from.
The embedding model to use.
The maximum number of contents to retrieve.
The minimum relevance score for the returned contents.Contentss scoring below this score are excluded from the results.
A content retriever retriving content from a web search.
The Google Custom Search Engine to retrieve content from.
The Tavily Search Engine to retrieve content from.
The name of this provider.
The maximum number of contents to retrieve.
A Google Custom Search Engine to retrieve content from.
The Google Search API key for accessing the Google Custom Search API.
The connection timeout of the search
The Custom Search ID parameter for search the entire web.
If your Search Engine is restricted to only searching specific sites, you can set this parameter to true.
Whether to log API requests
Whether to log API responses
The maximum number of retries for API requests
A Tavily Search Engine to retrieve content from.
The unique API key.
The URL to call the Tavily APi from: "https://api.tavily.com".
The connection timeout of the search
A list of domains to specifically exclude from the search results.
Include answers in the search results.
A list of domains to specifically include in the search results.
Include raw content in the search results.
The depth of the search. It can be basic or advanced. Default is basic for quick results and advanced for indepth high quality results but longer response time. Advanced calls equals 2 requests.
© 2015 - 2024 Weber Informatics LLC | Privacy Policy