diff --git a/docs/config.html b/docs/config.html
index b31888ed5..db309cd12 100644
--- a/docs/config.html
+++ b/docs/config.html
@@ -1399,9 +1399,9 @@
RagConfiguration
other IDs refer to entries in byok_rag.
Backward compatibility: - inline defaults to
[] (no inline RAG). - tool defaults to
-None which means all registered vector stores are used
-(identical to the previous tool.byok.enabled = True
-default).
+[] (no tool RAG).
+ If no RAG strategy is defined (inline and tool are empty), the RAG
+tool will register all stores available to llama-stack.
diff --git a/docs/config.json b/docs/config.json
index 545999be3..16578b742 100644
--- a/docs/config.json
+++ b/docs/config.json
@@ -282,9 +282,15 @@
},
"db_path": {
"description": "Path to RAG database.",
- "format": "file-path",
"title": "DB path",
"type": "string"
+ },
+ "score_multiplier": {
+ "default": 1.0,
+ "description": "Multiplier applied to relevance scores from this vector store. Used to weight results when querying multiple knowledge sources. Values > 1 boost this store's results; values < 1 reduce them.",
+ "minimum": 0,
+ "title": "Score multiplier",
+ "type": "number"
}
},
"required": [
@@ -467,18 +473,15 @@
"title": "Deployment environment",
"type": "string"
},
- "solr": {
- "anyOf": [
- {
- "$ref": "#/components/schemas/SolrConfiguration"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "description": "Configuration for Solr vector search operations.",
- "title": "Solr configuration"
+ "rag": {
+ "$ref": "#/components/schemas/RagConfiguration",
+ "description": "Configuration for all RAG strategies (inline and tool-based).",
+ "title": "RAG configuration"
+ },
+ "okp": {
+ "$ref": "#/components/schemas/OkpConfiguration",
+ "description": "OKP provider settings. Only used when 'okp' is listed in rag.inline or rag.tool.",
+ "title": "OKP configuration"
}
},
"required": [
@@ -898,6 +901,26 @@
"title": "ModelContextProtocolServer",
"type": "object"
},
+ "OkpConfiguration": {
+ "additionalProperties": false,
+ "description": "OKP (Offline Knowledge Portal) provider configuration.\n\nControls provider-specific behaviour for the OKP vector store.\nOnly relevant when ``\"okp\"`` is listed in ``rag.inline`` or ``rag.tool``.",
+ "properties": {
+ "offline": {
+ "default": true,
+ "description": "When True, use parent_id for OKP chunk source URLs. When False, use reference_url for chunk source URLs.",
+ "title": "OKP offline mode",
+ "type": "boolean"
+ },
+ "chunk_filter_query": {
+ "default": "is_chunk:true",
+ "description": "OKP filter query applied to every OKP search request. Defaults to 'is_chunk:true' to restrict results to chunk documents. To add extra constraints, extend the expression using boolean syntax, e.g. 'is_chunk:true AND product:*openshift*'.",
+ "title": "OKP chunk filter query",
+ "type": "string"
+ }
+ },
+ "title": "OkpConfiguration",
+ "type": "object"
+ },
"PostgreSQLDatabaseConfiguration": {
"additionalProperties": false,
"description": "PostgreSQL database configuration.\n\nPostgreSQL database is used by Lightspeed Core Stack service for storing\ninformation about conversation IDs. It can also be leveraged to store\nconversation history and information about quota usage.\n\nUseful resources:\n\n- [Psycopg: connection classes](https://www.psycopg.org/psycopg3/docs/api/connections.html)\n- [PostgreSQL connection strings](https://www.connectionstrings.com/postgresql/)\n- [How to Use PostgreSQL in Python](https://www.freecodecamp.org/news/postgresql-in-python/)",
@@ -1110,6 +1133,30 @@
"title": "RHIdentityConfiguration",
"type": "object"
},
+ "RagConfiguration": {
+ "additionalProperties": false,
+ "description": "RAG strategy configuration.\n\nControls which RAG sources are used for inline and tool-based retrieval.\n\nEach strategy lists RAG IDs to include. The special ID ``\"okp\"`` defined in constants,\nactivates the OKP provider; all other IDs refer to entries in ``byok_rag``.\n\nBackward compatibility:\n - ``inline`` defaults to ``[]`` (no inline RAG).\n - ``tool`` defaults to ``[]`` (no tool RAG).\n\nIf no RAG strategy is defined (inline and tool are empty),\nthe RAG tool will register all stores available to llama-stack.",
+ "properties": {
+ "inline": {
+ "description": "RAG IDs whose sources are injected as context before the LLM call. Use 'okp' to enable OKP inline RAG. Empty by default (no inline RAG).",
+ "items": {
+ "type": "string"
+ },
+ "title": "Inline RAG IDs",
+ "type": "array"
+ },
+ "tool": {
+ "description": "RAG IDs made available to the LLM as a file_search tool. Use 'okp' to include the OKP vector store. When omitted, all registered BYOK vector stores are used (backward compatibility).",
+ "items": {
+ "type": "string"
+ },
+ "title": "Tool RAG IDs",
+ "type": "array"
+ }
+ },
+ "title": "RagConfiguration",
+ "type": "object"
+ },
"SQLiteDatabaseConfiguration": {
"additionalProperties": false,
"description": "SQLite database configuration.",
@@ -1195,26 +1242,6 @@
"title": "ServiceConfiguration",
"type": "object"
},
- "SolrConfiguration": {
- "additionalProperties": false,
- "description": "Solr configuration for vector search queries.\n\nControls whether to use offline or online mode when building document URLs\nfrom vector search results, and enables/disables Solr vector IO functionality.",
- "properties": {
- "enabled": {
- "default": false,
- "description": "When True, enables Solr vector IO functionality for vector search queries. When False, disables Solr vector search processing.",
- "title": "Solr enabled",
- "type": "boolean"
- },
- "offline": {
- "default": true,
- "description": "When True, use parent_id for chunk source URLs. When False, use reference_url for chunk source URLs.",
- "title": "Offline mode",
- "type": "boolean"
- }
- },
- "title": "SolrConfiguration",
- "type": "object"
- },
"SplunkConfiguration": {
"additionalProperties": false,
"description": "Splunk HEC (HTTP Event Collector) configuration.\n\nSplunk HEC allows sending events directly to Splunk over HTTP/HTTPS.\nThis configuration is used to send telemetry events for inference\nrequests to the corporate Splunk deployment.\n\nUseful resources:\n\n - [Splunk HEC Docs](https://docs.splunk.com/Documentation/SplunkCloud)\n - [About HEC](https://docs.splunk.com/Documentation/Splunk/latest/Data)",
diff --git a/docs/config.md b/docs/config.md
index 00c0ae747..10246df56 100644
--- a/docs/config.md
+++ b/docs/config.md
@@ -529,8 +529,10 @@ activates the OKP provider; all other IDs refer to entries in ``byok_rag``.
Backward compatibility:
- ``inline`` defaults to ``[]`` (no inline RAG).
- - ``tool`` defaults to ``None`` which means all registered vector stores
- are used (identical to the previous ``tool.byok.enabled = True`` default).
+ - ``tool`` defaults to ``[]`` (no tool RAG).
+
+If no RAG strategy is defined (inline and tool are empty),
+the RAG tool will register all stores available to llama-stack.
| Field | Type | Description |
diff --git a/docs/config.png b/docs/config.png
index c60b6c539..31763792c 100644
Binary files a/docs/config.png and b/docs/config.png differ
diff --git a/docs/config.puml b/docs/config.puml
index 69497edcc..b2b739014 100644
--- a/docs/config.puml
+++ b/docs/config.puml
@@ -202,7 +202,7 @@ class "RHIdentityConfiguration" as src.models.config.RHIdentityConfiguration {
}
class "RagConfiguration" as src.models.config.RagConfiguration {
inline : list[str]
- tool : Optional[list[str]]
+ tool : list[str]
}
class "SQLiteDatabaseConfiguration" as src.models.config.SQLiteDatabaseConfiguration {
db_path : str
diff --git a/docs/config.svg b/docs/config.svg
index 816cbd1e5..23093209c 100644
--- a/docs/config.svg
+++ b/docs/config.svg
@@ -1,759 +1,759 @@
-
+
-
-
-
- A2AStateConfiguration
-
- config
- postgres : Optional[PostgreSQLDatabaseConfiguration]
- sqlite : Optional[SQLiteDatabaseConfiguration]
- storage_type
-
- check_a2a_state_configuration() -> Self
+
+
+
+ A2AStateConfiguration
+
+ config
+ postgres : Optional[PostgreSQLDatabaseConfiguration]
+ sqlite : Optional[SQLiteDatabaseConfiguration]
+ storage_type
+
+ check_a2a_state_configuration() -> Self
-
-
-
- APIKeyTokenConfiguration
-
- api_key
-
+
+
+
+ APIKeyTokenConfiguration
+
+ api_key
+
-
-
-
- AccessRule
-
- actions : list[Action]
- role : str
-
+
+
+
+ AccessRule
+
+ actions : list[Action]
+ role : str
+
-
-
-
- Action
-
- name
-
+
+
+
+ Action
+
+ name
+
-
-
-
- AuthenticationConfiguration
-
- api_key_config : Optional[APIKeyTokenConfiguration]
- api_key_configuration
- jwk_config : Optional[JwkConfiguration]
- jwk_configuration
- k8s_ca_cert_path : Optional[FilePath]
- k8s_cluster_api : Optional[AnyHttpUrl]
- module : str
- rh_identity_config : Optional[RHIdentityConfiguration]
- rh_identity_configuration
- skip_for_health_probes : bool
- skip_tls_verification : bool
-
- check_authentication_model() -> Self
+
+
+
+ AuthenticationConfiguration
+
+ api_key_config : Optional[APIKeyTokenConfiguration]
+ api_key_configuration
+ jwk_config : Optional[JwkConfiguration]
+ jwk_configuration
+ k8s_ca_cert_path : Optional[FilePath]
+ k8s_cluster_api : Optional[AnyHttpUrl]
+ module : str
+ rh_identity_config : Optional[RHIdentityConfiguration]
+ rh_identity_configuration
+ skip_for_health_probes : bool
+ skip_tls_verification : bool
+
+ check_authentication_model() -> Self
-
-
-
- AuthorizationConfiguration
-
- access_rules : list[AccessRule]
-
+
+
+
+ AuthorizationConfiguration
+
+ access_rules : list[AccessRule]
+
-
-
-
- AzureEntraIdConfiguration
-
- client_id
- client_secret
- scope : str
- tenant_id
-
+
+
+
+ AzureEntraIdConfiguration
+
+ client_id
+ client_secret
+ scope : str
+ tenant_id
+
-
-
-
- ByokRag
-
- db_path : str
- embedding_dimension
- embedding_model : str
- rag_id : str
- rag_type : str
- score_multiplier : float
- vector_db_id : str
-
+
+
+
+ ByokRag
+
+ db_path : str
+ embedding_dimension
+ embedding_model : str
+ rag_id : str
+ rag_type : str
+ score_multiplier : float
+ vector_db_id : str
+
-
-
-
- CORSConfiguration
-
- allow_credentials : bool
- allow_headers : list[str]
- allow_methods : list[str]
- allow_origins : list[str]
-
- check_cors_configuration() -> Self
+
+
+
+ CORSConfiguration
+
+ allow_credentials : bool
+ allow_headers : list[str]
+ allow_methods : list[str]
+ allow_origins : list[str]
+
+ check_cors_configuration() -> Self
-
-
-
- Configuration
-
- a2a_state
- authentication
- authorization : Optional[AuthorizationConfiguration]
- azure_entra_id : Optional[AzureEntraIdConfiguration]
- byok_rag : list[ByokRag]
- conversation_cache
- customization : Optional[Customization]
- database
- deployment_environment : str
- inference
- llama_stack
- mcp_servers : list[ModelContextProtocolServer]
- name : str
- okp
- quota_handlers
- rag
- service
- splunk : Optional[SplunkConfiguration]
- user_data_collection
-
- dump(filename: str | Path) -> None
- validate_mcp_auth_headers() -> Self
+
+
+
+ Configuration
+
+ a2a_state
+ authentication
+ authorization : Optional[AuthorizationConfiguration]
+ azure_entra_id : Optional[AzureEntraIdConfiguration]
+ byok_rag : list[ByokRag]
+ conversation_cache
+ customization : Optional[Customization]
+ database
+ deployment_environment : str
+ inference
+ llama_stack
+ mcp_servers : list[ModelContextProtocolServer]
+ name : str
+ okp
+ quota_handlers
+ rag
+ service
+ splunk : Optional[SplunkConfiguration]
+ user_data_collection
+
+ dump(filename: str | Path) -> None
+ validate_mcp_auth_headers() -> Self
-
-
-
- ConfigurationBase
-
- model_config
-
+
+
+
+ ConfigurationBase
+
+ model_config
+
-
-
-
- ConversationHistoryConfiguration
-
- memory : Optional[InMemoryCacheConfig]
- postgres : Optional[PostgreSQLDatabaseConfiguration]
- sqlite : Optional[SQLiteDatabaseConfiguration]
- type : Optional[Literal['noop', 'memory', 'sqlite', 'postgres']]
-
- check_cache_configuration() -> Self
+
+
+
+ ConversationHistoryConfiguration
+
+ memory : Optional[InMemoryCacheConfig]
+ postgres : Optional[PostgreSQLDatabaseConfiguration]
+ sqlite : Optional[SQLiteDatabaseConfiguration]
+ type : Optional[Literal['noop', 'memory', 'sqlite', 'postgres']]
+
+ check_cache_configuration() -> Self
-
-
-
- CustomProfile
-
- path : str
- prompts : dict[str, str]
-
- get_prompts() -> dict[str, str]
+
+
+
+ CustomProfile
+
+ path : str
+ prompts : dict[str, str]
+
+ get_prompts() -> dict[str, str]
-
-
-
- Customization
-
- agent_card_config : Optional[dict[str, Any]]
- agent_card_path : Optional[FilePath]
- custom_profile : Optional[CustomProfile]
- disable_query_system_prompt : bool
- disable_shield_ids_override : bool
- profile_path : Optional[str]
- system_prompt : Optional[str]
- system_prompt_path : Optional[FilePath]
-
- check_customization_model() -> Self
+
+
+
+ Customization
+
+ agent_card_config : Optional[dict[str, Any]]
+ agent_card_path : Optional[FilePath]
+ custom_profile : Optional[CustomProfile]
+ disable_query_system_prompt : bool
+ disable_shield_ids_override : bool
+ profile_path : Optional[str]
+ system_prompt : Optional[str]
+ system_prompt_path : Optional[FilePath]
+
+ check_customization_model() -> Self
-
-
-
- DatabaseConfiguration
-
- config
- db_type
- postgres : Optional[PostgreSQLDatabaseConfiguration]
- sqlite : Optional[SQLiteDatabaseConfiguration]
-
- check_database_configuration() -> Self
+
+
+
+ DatabaseConfiguration
+
+ config
+ db_type
+ postgres : Optional[PostgreSQLDatabaseConfiguration]
+ sqlite : Optional[SQLiteDatabaseConfiguration]
+
+ check_database_configuration() -> Self
-
-
-
- InMemoryCacheConfig
-
- max_entries
-
+
+
+
+ InMemoryCacheConfig
+
+ max_entries
+
-
-
-
- InferenceConfiguration
-
- default_model : Optional[str]
- default_provider : Optional[str]
-
- check_default_model_and_provider() -> Self
+
+
+
+ InferenceConfiguration
+
+ default_model : Optional[str]
+ default_provider : Optional[str]
+
+ check_default_model_and_provider() -> Self
-
-
-
- JsonPathOperator
-
- name
-
+
+
+
+ JsonPathOperator
+
+ name
+
-
-
-
- JwkConfiguration
-
- jwt_configuration
- url
-
+
+
+
+ JwkConfiguration
+
+ jwt_configuration
+ url
+
-
-
-
- JwtConfiguration
-
- role_rules : list[JwtRoleRule]
- user_id_claim : str
- username_claim : str
-
+
+
+
+ JwtConfiguration
+
+ role_rules : list[JwtRoleRule]
+ user_id_claim : str
+ username_claim : str
+
-
-
-
- JwtRoleRule
-
- compiled_regex
- jsonpath : str
- negate : bool
- operator
- roles : list[str]
- value : Any
-
- check_jsonpath() -> Self
- check_regex_pattern() -> Self
- check_roles() -> Self
+
+
+
+ JwtRoleRule
+
+ compiled_regex
+ jsonpath : str
+ negate : bool
+ operator
+ roles : list[str]
+ value : Any
+
+ check_jsonpath() -> Self
+ check_regex_pattern() -> Self
+ check_roles() -> Self
-
-
-
- LlamaStackConfiguration
-
- api_key : Optional[SecretStr]
- library_client_config_path : Optional[str]
- timeout
- url : Optional[AnyHttpUrl]
- use_as_library_client : Optional[bool]
-
- check_llama_stack_model() -> Self
+
+
+
+ LlamaStackConfiguration
+
+ api_key : Optional[SecretStr]
+ library_client_config_path : Optional[str]
+ timeout
+ url : Optional[AnyHttpUrl]
+ use_as_library_client : Optional[bool]
+
+ check_llama_stack_model() -> Self
-
-
-
- ModelContextProtocolServer
-
- authorization_headers : dict[str, str]
- headers : list[str]
- name : str
- provider_id : str
- resolved_authorization_headers
- timeout : Optional[PositiveInt]
- url : str
-
- resolve_auth_headers() -> Self
- validate_headers(value: list[str]) -> list[str]
+
+
+
+ ModelContextProtocolServer
+
+ authorization_headers : dict[str, str]
+ headers : list[str]
+ name : str
+ provider_id : str
+ resolved_authorization_headers
+ timeout : Optional[PositiveInt]
+ url : str
+
+ resolve_auth_headers() -> Self
+ validate_headers(value: list[str]) -> list[str]
-
-
-
- OkpConfiguration
-
- chunk_filter_query : str
- offline : bool
-
+
+
+
+ OkpConfiguration
+
+ chunk_filter_query : str
+ offline : bool
+
-
-
-
- PostgreSQLDatabaseConfiguration
-
- ca_cert_path : Optional[FilePath]
- db : str
- gss_encmode : str
- host : str
- namespace : Optional[str]
- password
- port
- ssl_mode : str
- user : str
-
- check_postgres_configuration() -> Self
+
+
+
+ PostgreSQLDatabaseConfiguration
+
+ ca_cert_path : Optional[FilePath]
+ db : str
+ gss_encmode : str
+ host : str
+ namespace : Optional[str]
+ password
+ port
+ ssl_mode : str
+ user : str
+
+ check_postgres_configuration() -> Self
-
-
-
- QuotaHandlersConfiguration
-
- enable_token_history : bool
- limiters : list[QuotaLimiterConfiguration]
- postgres : Optional[PostgreSQLDatabaseConfiguration]
- scheduler
- sqlite : Optional[SQLiteDatabaseConfiguration]
-
+
+
+
+ QuotaHandlersConfiguration
+
+ enable_token_history : bool
+ limiters : list[QuotaLimiterConfiguration]
+ postgres : Optional[PostgreSQLDatabaseConfiguration]
+ scheduler
+ sqlite : Optional[SQLiteDatabaseConfiguration]
+
-
-
-
- QuotaLimiterConfiguration
-
- initial_quota
- name : str
- period : str
- quota_increase
- type : Literal['user_limiter', 'cluster_limiter']
-
+
+
+
+ QuotaLimiterConfiguration
+
+ initial_quota
+ name : str
+ period : str
+ quota_increase
+ type : Literal['user_limiter', 'cluster_limiter']
+
-
-
-
- QuotaSchedulerConfiguration
-
- database_reconnection_count
- database_reconnection_delay
- period
-
+
+
+
+ QuotaSchedulerConfiguration
+
+ database_reconnection_count
+ database_reconnection_delay
+ period
+
-
-
-
- RHIdentityConfiguration
-
- required_entitlements : Optional[list[str]]
-
+
+
+
+ RHIdentityConfiguration
+
+ required_entitlements : Optional[list[str]]
+
-
-
-
- RagConfiguration
-
- inline : list[str]
- tool : Optional[list[str]]
-
+
+
+
+ RagConfiguration
+
+ inline : list[str]
+ tool : list[str]
+
-
-
-
- SQLiteDatabaseConfiguration
-
- db_path : str
-
+
+
+
+ SQLiteDatabaseConfiguration
+
+ db_path : str
+
-
-
-
- ServiceConfiguration
-
- access_log : bool
- auth_enabled : bool
- base_url : Optional[str]
- color_log : bool
- cors
- host : str
- port
- root_path : str
- tls_config
- workers
-
- check_service_configuration() -> Self
- validate_root_path(value: str) -> str
+
+
+
+ ServiceConfiguration
+
+ access_log : bool
+ auth_enabled : bool
+ base_url : Optional[str]
+ color_log : bool
+ cors
+ host : str
+ port
+ root_path : str
+ tls_config
+ workers
+
+ check_service_configuration() -> Self
+ validate_root_path(value: str) -> str
-
-
-
- SplunkConfiguration
-
- enabled : bool
- index : Optional[str]
- source : str
- timeout
- token_path : Optional[FilePath]
- url : Optional[str]
- verify_ssl : bool
-
- check_splunk_configuration() -> Self
+
+
+
+ SplunkConfiguration
+
+ enabled : bool
+ index : Optional[str]
+ source : str
+ timeout
+ token_path : Optional[FilePath]
+ url : Optional[str]
+ verify_ssl : bool
+
+ check_splunk_configuration() -> Self
-
-
-
- TLSConfiguration
-
- tls_certificate_path : Optional[FilePath]
- tls_key_password : Optional[FilePath]
- tls_key_path : Optional[FilePath]
-
- check_tls_configuration() -> Self
+
+
+
+ TLSConfiguration
+
+ tls_certificate_path : Optional[FilePath]
+ tls_key_password : Optional[FilePath]
+ tls_key_path : Optional[FilePath]
+
+ check_tls_configuration() -> Self
-
-
-
- UserDataCollection
-
- feedback_enabled : bool
- feedback_storage : Optional[str]
- transcripts_enabled : bool
- transcripts_storage : Optional[str]
-
- check_storage_location_is_set_when_needed() -> Self
+
+
+
+ UserDataCollection
+
+ feedback_enabled : bool
+ feedback_storage : Optional[str]
+ transcripts_enabled : bool
+ transcripts_storage : Optional[str]
+
+ check_storage_location_is_set_when_needed() -> Self
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
+
+
-
-
- a2a_state
+
+
+ a2a_state
-
-
- authentication
+
+
+ authentication
-
-
- cors
+
+
+ cors
-
-
- conversation_cache
+
+
+ conversation_cache
-
-
- custom_profile
+
+
+ custom_profile
-
-
- database
+
+
+ database
-
-
- inference
+
+
+ inference
-
-
- operator
+
+
+ operator
-
-
- jwt_configuration
+
+
+ jwt_configuration
-
-
- llama_stack
+
+
+ llama_stack
-
-
- okp
+
+
+ okp
-
-
- quota_handlers
+
+
+ quota_handlers
-
-
- scheduler
+
+
+ scheduler
-
-
- rag
+
+
+ rag
-
-
- sqlite
+
+
+ sqlite
-
-
- service
+
+
+ service
-
-
- tls_config
+
+
+ tls_config
-
-
- user_data_collection
+
+
+ user_data_collection
-
+
diff --git a/docs/openapi.md b/docs/openapi.md
index 8c4f77d8a..25ae432bb 100644
--- a/docs/openapi.md
+++ b/docs/openapi.md
@@ -4969,14 +4969,16 @@ activates the OKP provider; all other IDs refer to entries in ``byok_rag``.
Backward compatibility:
- ``inline`` defaults to ``[]`` (no inline RAG).
- - ``tool`` defaults to ``None`` which means all registered vector stores
- are used (identical to the previous ``tool.byok.enabled = True`` default).
+ - ``tool`` defaults to ``[]`` (no tool RAG).
+
+If no RAG strategy is defined (inline and tool are empty),
+the RAG tool will register all stores available to llama-stack.
| Field | Type | Description |
|-------|------|-------------|
| inline | array | RAG IDs whose sources are injected as context before the LLM call. Use 'okp' to enable OKP inline RAG. Empty by default (no inline RAG). |
-| tool | | RAG IDs made available to the LLM as a file_search tool. Use 'okp' to include the OKP vector store. When omitted, all registered BYOK vector stores are used (backward compatibility). |
+| tool | array | RAG IDs made available to the LLM as a file_search tool. Use 'okp' to include the OKP vector store. When omitted, all registered BYOK vector stores are used (backward compatibility). |
## ReadinessResponse
@@ -5029,6 +5031,161 @@ Attributes:
| source | | Index name identifying the knowledge source from configuration |
+## ResponseInput
+
+
+
+
+
+## ResponseItem
+
+
+
+
+
+## ResponsesRequest
+
+
+Model representing a request for the Responses API following LCORE specification.
+
+Attributes:
+ input: Input text or structured input items containing the query.
+ model: Model identifier in format "provider/model". Auto-selected if not provided.
+ conversation: Conversation ID linking to an existing conversation. Accepts both
+ OpenAI and LCORE formats. Mutually exclusive with previous_response_id.
+ include: Explicitly specify output item types that are excluded by default but
+ should be included in the response.
+ instructions: System instructions or guidelines provided to the model (acts as
+ the system prompt).
+ max_infer_iters: Maximum number of inference iterations the model can perform.
+ max_output_tokens: Maximum number of tokens allowed in the response.
+ max_tool_calls: Maximum number of tool calls allowed in a single response.
+ metadata: Custom metadata dictionary with key-value pairs for tracking or logging.
+ parallel_tool_calls: Whether the model can make multiple tool calls in parallel.
+ previous_response_id: Identifier of the previous response in a multi-turn
+ conversation. Mutually exclusive with conversation.
+ prompt: Prompt object containing a template with variables for dynamic
+ substitution.
+ reasoning: Reasoning configuration for the response.
+ safety_identifier: Safety identifier for the response.
+ store: Whether to store the response in conversation history. Defaults to True.
+ stream: Whether to stream the response as it is generated. Defaults to False.
+ temperature: Sampling temperature controlling randomness (typically 0.0–2.0).
+ text: Text response configuration specifying output format constraints (JSON
+ schema, JSON object, or plain text).
+ tool_choice: Tool selection strategy ("auto", "required", "none", or specific
+ tool configuration).
+ tools: List of tools available to the model (file search, web search, function
+ calls, MCP tools). Defaults to all tools available to the model.
+ generate_topic_summary: LCORE-specific flag indicating whether to generate a
+ topic summary for new conversations. Defaults to True.
+ shield_ids: LCORE-specific list of safety shield IDs to apply. If None, all
+ configured shields are used.
+ solr: LCORE-specific Solr vector_io provider query parameters (e.g. filter
+ queries). Optional.
+
+
+| Field | Type | Description |
+|-------|------|-------------|
+| input | | |
+| model | | |
+| conversation | | |
+| include | | |
+| instructions | | |
+| max_infer_iters | | |
+| max_output_tokens | | |
+| max_tool_calls | | |
+| metadata | | |
+| parallel_tool_calls | | |
+| previous_response_id | | |
+| prompt | | |
+| reasoning | | |
+| safety_identifier | | |
+| store | boolean | |
+| stream | boolean | |
+| temperature | | |
+| text | | |
+| tool_choice | | |
+| tools | | |
+| generate_topic_summary | | |
+| shield_ids | | |
+| solr | | |
+
+
+## ResponsesResponse
+
+
+Model representing a response from the Responses API following LCORE specification.
+
+Attributes:
+ created_at: Unix timestamp when the response was created.
+ completed_at: Unix timestamp when the response was completed, if applicable.
+ error: Error details if the response failed or was blocked.
+ id: Unique identifier for this response.
+ model: Model identifier in "provider/model" format used for generation.
+ object: Object type identifier, always "response".
+ output: List of structured output items containing messages, tool calls, and
+ other content. This is the primary response content.
+ parallel_tool_calls: Whether the model can make multiple tool calls in parallel.
+ previous_response_id: Identifier of the previous response in a multi-turn
+ conversation.
+ prompt: The input prompt object that was sent to the model.
+ status: Current status of the response (e.g., "completed", "blocked",
+ "in_progress").
+ temperature: Temperature parameter used for generation (controls randomness).
+ text: Text response configuration object used for OpenAI responses.
+ top_p: Top-p sampling parameter used for generation.
+ tools: List of tools available to the model during generation.
+ tool_choice: Tool selection strategy used (e.g., "auto", "required", "none").
+ truncation: Strategy used for handling content that exceeds context limits.
+ usage: Token usage statistics including input_tokens, output_tokens, and
+ total_tokens.
+ instructions: System instructions or guidelines provided to the model.
+ max_tool_calls: Maximum number of tool calls allowed in a single response.
+ reasoning: Reasoning configuration (effort level) used for the response.
+ max_output_tokens: Upper bound for tokens generated in the response.
+ safety_identifier: Safety/guardrail identifier applied to the request.
+ metadata: Additional metadata dictionary with custom key-value pairs.
+ store: Whether the response was stored.
+ conversation: Conversation ID linking this response to a conversation thread
+ (LCORE-specific).
+ available_quotas: Remaining token quotas for the user (LCORE-specific).
+ output_text: Aggregated text output from all output_text items in the
+ output array.
+
+
+| Field | Type | Description |
+|-------|------|-------------|
+| created_at | integer | |
+| completed_at | | |
+| error | | |
+| id | string | |
+| model | string | |
+| object | string | |
+| output | array | |
+| parallel_tool_calls | boolean | |
+| previous_response_id | | |
+| prompt | | |
+| status | string | |
+| temperature | | |
+| text | | |
+| top_p | | |
+| tools | | |
+| tool_choice | | |
+| truncation | | |
+| usage | | |
+| instructions | | |
+| max_tool_calls | | |
+| reasoning | | |
+| max_output_tokens | | |
+| safety_identifier | | |
+| metadata | | |
+| store | | |
+| conversation | | |
+| available_quotas | object | |
+| output_text | string | |
+
+
## RlsapiV1Attachment
@@ -5187,6 +5344,62 @@ SQLite database configuration.
| db_path | string | Path to file where SQLite database is stored |
+## SearchRankingOptions
+
+
+Options for ranking and filtering search results.
+
+This class configures how search results are ranked and filtered. You can use algorithm-based
+rerankers (weighted, RRF) or neural rerankers. Defaults from VectorStoresConfig are
+used when parameters are not provided.
+
+Examples:
+ # Weighted ranker with custom alpha
+ SearchRankingOptions(ranker="weighted", alpha=0.7)
+
+ # RRF ranker with custom impact factor
+ SearchRankingOptions(ranker="rrf", impact_factor=50.0)
+
+ # Use config defaults (just specify ranker type)
+ SearchRankingOptions(ranker="weighted") # Uses alpha from VectorStoresConfig
+
+ # Score threshold filtering
+ SearchRankingOptions(ranker="weighted", score_threshold=0.5)
+
+:param ranker: (Optional) Name of the ranking algorithm to use. Supported values:
+ - "weighted": Weighted combination of vector and keyword scores
+ - "rrf": Reciprocal Rank Fusion algorithm
+ - "neural": Neural reranking model (requires model parameter, Part II)
+ Note: For OpenAI API compatibility, any string value is accepted, but only the above values are supported.
+:param score_threshold: (Optional) Minimum relevance score threshold for results. Default: 0.0
+:param alpha: (Optional) Weight factor for weighted ranker (0-1).
+ - 0.0 = keyword only
+ - 0.5 = equal weight (default)
+ - 1.0 = vector only
+ Only used when ranker="weighted" and weights is not provided.
+ Falls back to VectorStoresConfig.chunk_retrieval_params.weighted_search_alpha if not provided.
+:param impact_factor: (Optional) Impact factor (k) for RRF algorithm.
+ Lower values emphasize higher-ranked results. Default: 60.0 (optimal from research).
+ Only used when ranker="rrf".
+ Falls back to VectorStoresConfig.chunk_retrieval_params.rrf_impact_factor if not provided.
+:param weights: (Optional) Dictionary of weights for combining different signal types.
+ Keys can be "vector", "keyword", "neural". Values should sum to 1.0.
+ Used when combining algorithm-based reranking with neural reranking (Part II).
+ Example: {"vector": 0.3, "keyword": 0.3, "neural": 0.4}
+:param model: (Optional) Model identifier for neural reranker (e.g., "vllm/Qwen3-Reranker-0.6B").
+ Required when ranker="neural" or when weights contains "neural" (Part II).
+
+
+| Field | Type | Description |
+|-------|------|-------------|
+| ranker | | |
+| score_threshold | | |
+| alpha | | Weight factor for weighted ranker |
+| impact_factor | | Impact factor for RRF algorithm |
+| weights | | Weights for combining vector, keyword, and neural scores. Keys: 'vector', 'keyword', 'neural' |
+| model | | Model identifier for neural reranker |
+
+
## SecurityScheme