| operation required | string Enum: "start-flow" "stop-flow" "list-flows" "get-flow" "list-blueprints" "get-blueprint" "put-blueprint" "delete-blueprint" Request Body schema: application/jsonrequired | operation required | string Enum: "start-flow" "stop-flow" "list-flows" "get-flow" "list-blueprints" "get-blueprint" "put-blueprint" "delete-blueprint" Flow operation:
+" class="sc-iKGpAq sc-cCYyou dXXcln cFvDiF"> Flow operation:
start-flow: Start a new flow instance from a blueprintstop-flow: Stop a running flow instance/api/v1/config) manages st
put-blueprint: Create/update blueprint definitiondelete-blueprint: Delete blueprint definition
- | | flow-id | string Flow instance ID (required for start-flow, stop-flow, get-flow)
- | | blueprint-name | string Flow blueprint name (required for start-flow, get-blueprint, put-blueprint, delete-blueprint)
- | | object Flow blueprint definition (required for put-blueprint)
- | | description | string Flow description (optional for start-flow)
- | | object | flow-id | string Flow instance ID (required for start-flow, stop-flow, get-flow)
+ | | | blueprint-name | string Flow blueprint name (required for start-flow, get-blueprint, put-blueprint, delete-blueprint)
+ | | object Flow blueprint definition (required for put-blueprint)
+ | | description | string Flow description (optional for start-flow)
+ | | object Flow parameters (for start-flow).
+" class="sc-iKGpAq sc-cCYyou dXXcln cFvDiF"> Flow parameters (for start-flow).
All values are stored as strings, regardless of input type.
- |
ResponsesLocal development server
- http://localhost:8088/api/v1/flow Request samples Content typeapplication/json Example {"operation": "start-flow", "flow-id": "my-flow", "blueprint-name": "document-rag", "description": "My document processing flow", "parameters": {"model": "gpt-4", "temperature": "0.7"
}
} Response samples Content typeapplication/json Example Responses Local development server
+ http://localhost:8088/api/v1/flow Request samples Content typeapplication/json Example {"operation": "start-flow", "flow-id": "my-flow", "blueprint-name": "document-rag", "description": "My document processing flow", "parameters": {"model": "gpt-4", "temperature": "0.7"
}
} Response samples Content typeapplication/json Example Document library management (global service)
- Document library management Document library management Manage document library: add, remove, list documents, and control processing.
+" class="sc-iKGpAq sc-cCYyou dXXcln dHaogz"> Manage document library: add, remove, list documents, and control processing.
Document Library
The librarian service manages a persistent library of documents that can be:
@@ -780,7 +784,7 @@ for processing and handled asynchronously.
Stop ongoing library document processing.
list-processing
List current processing tasks and their status.
- Request Body schema: application/jsonrequired | operation required | string Enum: "add-document" "remove-document" "list-documents" "start-processing" "stop-processing" "list-processing" Request Body schema: application/jsonrequired | operation required | string Enum: "add-document" "remove-document" "list-documents" "start-processing" "stop-processing" "list-processing" Library operation:
+" class="sc-iKGpAq sc-cCYyou dXXcln cFvDiF"> Library operation:
add-document: Add document to libraryremove-document: Remove document from librarystop-processing: Stop library processinglist-processing: List processing status
- | | flow | | | collection | string Default: "default" | | user | string Default: "trustgraph" | | document-id | | | processing-id | string Processing task identifier
- | | object (DocumentMetadata) Document metadata for library management
- | | object (ProcessingMetadata) Processing metadata for library document processing
- | | content | string Document content (for add-document with inline content)
- | | Array of objects Search criteria for filtering documents
- |
ResponsesLocal development server
- http://localhost:8088/api/v1/librarian Request samples Content typeapplication/json Example Response samples Content typeapplication/json Example {"document-metadatas": [{"title": "Document 1", "author": "John Doe",
}, {"title": "Document 2", "author": "Jane Smith",
}
]
} | | collection | string Default: "default" | | user | string Default: "trustgraph" | | document-id | | | processing-id | string Processing task identifier
+ | | object (DocumentMetadata) Document metadata for library management
+ | | object (ProcessingMetadata) Processing metadata for library document processing
+ | | content | string Document content (for add-document with inline content)
+ | | Array of objects Search criteria for filtering documents
+ |
ResponsesLocal development server
+ http://localhost:8088/api/v1/librarian Request samples Content typeapplication/json Example Response samples Content typeapplication/json Example {"document-metadatas": [{"title": "Document 1", "author": "John Doe",
}, {"title": "Document 2", "author": "Jane Smith",
}
]
}Knowledge graph core management (global service)
- Knowledge graph core management Knowledge graph core management Manage knowledge graph cores - persistent storage of triples and embeddings.
+" class="sc-iKGpAq sc-cCYyou dXXcln dHaogz"> Manage knowledge graph cores - persistent storage of triples and embeddings.
Knowledge Cores
Knowledge cores are the foundational storage units for:
@@ -890,7 +894,7 @@ Removes data from flow instance but doesn't delete the core.
- Multiple messages with
triples or graph-embeddings
- Final message with
eos: true to signal completion
- Request Body schema: application/jsonrequired | operation required | string Enum: "list-kg-cores" "get-kg-core" "put-kg-core" "delete-kg-core" "load-kg-core" "unload-kg-core" Request Body schema: application/jsonrequired | operation required | string Enum: "list-kg-cores" "get-kg-core" "put-kg-core" "delete-kg-core" "load-kg-core" "unload-kg-core" Knowledge core operation:
+" class="sc-iKGpAq sc-cCYyou dXXcln cFvDiF"> Knowledge core operation:
list-kg-cores: List knowledge cores for userget-kg-core: Get knowledge core by IDload-kg-core: Load knowledge core into flowunload-kg-core: Unload knowledge core from flow
- | | user | string Default: "trustgraph" User identifier (for list-kg-cores, put-kg-core, delete-kg-core)
- | | id | string Knowledge core ID (for get, put, delete, load, unload)
- | | flow | string Flow ID (for load-kg-core)
- | | collection | string Default: "default" Collection identifier (for load-kg-core)
- | | object Triples to store (for put-kg-core)
- | | object Graph embeddings to store (for put-kg-core)
- |
ResponsesLocal development server
- http://localhost:8088/api/v1/knowledge Request samples Content typeapplication/json Example Response samples Content typeapplication/json Example {"ids": ["core-123", "core-456", "core-789"
]
}| user | string Default: "trustgraph" User identifier (for list-kg-cores, put-kg-core, delete-kg-core)
+ | | | id | string Knowledge core ID (for get, put, delete, load, unload)
+ | | flow | string Flow ID (for load-kg-core)
+ | | collection | string Default: "default" Collection identifier (for load-kg-core)
+ | | object Triples to store (for put-kg-core)
+ | | object Graph embeddings to store (for put-kg-core)
+ |
ResponsesLocal development server
+ http://localhost:8088/api/v1/knowledge Request samples Content typeapplication/json Example Response samples Content typeapplication/json Example {"ids": ["core-123", "core-456", "core-789"
]
}Collection metadata management (global service)
- Collection metadata management Collection metadata management Manage collection metadata for organizing documents and knowledge.
+" class="sc-iKGpAq sc-cCYyou dXXcln dHaogz"> Manage collection metadata for organizing documents and knowledge.
Collections
Collections are organizational units for grouping:
@@ -982,45 +986,45 @@ If it exists, metadata is updated. Allows setting name, description, and tags.delete-collection
Delete a collection by user and collection ID. This removes the metadata but
typically does not delete the associated data (documents, knowledge cores).
- Request Body schema: application/jsonrequired | operation required | string Enum: "list-collections" "update-collection" "delete-collection" Request Body schema: application/jsonrequired | operation required | string Enum: "list-collections" "update-collection" "delete-collection" Collection operation:
+" class="sc-iKGpAq sc-cCYyou dXXcln cFvDiF"> Collection operation:
list-collections: List collections for userupdate-collection: Create or update collection metadatadelete-collection: Delete collection
- | | user | string Default: "trustgraph" | | collection | string Collection identifier (for update, delete)
- | | timestamp | | | name | string Human-readable collection name (for update)
- | | description | string Collection description (for update)
- | | tags | Array of strings Collection tags for organization (for update)
- | | tag-filter | Array of strings Filter collections by tags (for list)
- | | limit | integer Default: 0 Maximum number of results (for list)
- |
ResponsesLocal development server
- http://localhost:8088/api/v1/collection-management Request samples Content typeapplication/json Example Response samples Content typeapplication/json Example | user | string Default: "trustgraph" | | | collection | string Collection identifier (for update, delete)
+ | | timestamp | | | name | string Human-readable collection name (for update)
+ | | description | string Collection description (for update)
+ | | tags | Array of strings Collection tags for organization (for update)
+ | | tag-filter | Array of strings Filter collections by tags (for list)
+ | | limit | integer Default: 0 Maximum number of results (for list)
+ |
ResponsesLocal development server
+ http://localhost:8088/api/v1/collection-management Request samples Content typeapplication/json Example Response samples Content typeapplication/json Example Services hosted within flow instances
- Agent service - conversational AI with reasoning Agent service - conversational AI with reasoning AI agent that can understand questions, reason about them, and take actions.
+" class="sc-iKGpAq sc-cCYyou dXXcln dHaogz"> AI agent that can understand questions, reason about them, and take actions.
Agent Overview
The agent service provides a conversational AI that:
@@ -1104,29 +1108,29 @@ Each step has: thought, action, arguments, observation.</p>
Multi-turn Conversations
Include history array with previous steps to maintain context.
Each step has: thought, action, arguments, observation.
- Request Body schema: application/jsonrequired | question required | string User question or prompt for the agent
- | | state | string Agent state for continuation (optional, for multi-turn)
- | | group | Array of strings Group identifiers for collaborative agents (optional)
- | | Array of objects Conversation history (optional, list of previous agent steps)
- | | user | string Default: "trustgraph" User identifier for multi-tenancy
- | | streaming | boolean Default: false Enable streaming response delivery
- |
ResponsesLocal development server
- http://localhost:8088/api/v1/flow/{flow}/service/agent Request samples Content typeapplication/json Example Response samples Content typeapplication/json Example Document RAG - retrieve and generate from documents Request Body schema: application/jsonrequired | question required | string User question or prompt for the agent
+ | | state | string Agent state for continuation (optional, for multi-turn)
+ | | group | Array of strings Group identifiers for collaborative agents (optional)
+ | | Array of objects Conversation history (optional, list of previous agent steps)
+ | | user | string Default: "trustgraph" User identifier for multi-tenancy
+ | | streaming | boolean Default: false Enable streaming response delivery
+ |
ResponsesLocal development server
+ http://localhost:8088/api/v1/flow/{flow}/service/agent Request samples Content typeapplication/json Example Response samples Content typeapplication/json Example Document RAG - retrieve and generate from documents Retrieval-Augmented Generation over document embeddings.
+" class="sc-iKGpAq sc-cCYyou dXXcln dHaogz"> Retrieval-Augmented Generation over document embeddings.
Document RAG Overview
Document RAG combines:
@@ -1192,27 +1196,27 @@ Each step has: thought, action, arguments, observation.
- collection: Target specific document collection
- user: Multi-tenant isolation
- Request Body schema: application/jsonrequired | query required | | | user | string Default: "trustgraph" User identifier for multi-tenancy
- | | collection | string Default: "default" Collection to search within
- | | doc-limit | integer [ 1 .. 100 ] Default: 20 Maximum number of documents to retrieve
- | | streaming | boolean Default: false Enable streaming response delivery
- |
ResponsesLocal development server
- http://localhost:8088/api/v1/flow/{flow}/service/document-rag Request samples Content typeapplication/json Example Response samples Content typeapplication/json Example Graph RAG - retrieve and generate from knowledge graph Request Body schema: application/jsonrequired | query required | | | user | string Default: "trustgraph" User identifier for multi-tenancy
+ | | collection | string Default: "default" Collection to search within
+ | | doc-limit | integer [ 1 .. 100 ] Default: 20 Maximum number of documents to retrieve
+ | | streaming | boolean Default: false Enable streaming response delivery
+ |
ResponsesLocal development server
+ http://localhost:8088/api/v1/flow/{flow}/service/document-rag Request samples Content typeapplication/json Example Response samples Content typeapplication/json Example Graph RAG - retrieve and generate from knowledge graph Retrieval-Augmented Generation over knowledge graph.
+" class="sc-iKGpAq sc-cCYyou dXXcln dHaogz"> Retrieval-Augmented Generation over knowledge graph.
Graph RAG Overview
Graph RAG combines:
@@ -1302,33 +1306,33 @@ Each step has: thought, action, arguments, observation.
- Multi-hop reasoning ("What's the path from A to B?")
- Structural analysis ("What are the main entities related to X?")
- Request Body schema: application/jsonrequired | query required | | | user | string Default: "trustgraph" User identifier for multi-tenancy
- | | collection | string Default: "default" Collection to search within
- | | entity-limit | integer [ 1 .. 200 ] Default: 50 Maximum number of entities to retrieve
- | | triple-limit | integer [ 1 .. 100 ] Default: 30 Maximum number of triples to retrieve per entity
- | | max-subgraph-size | integer [ 10 .. 5000 ] Default: 1000 Maximum total subgraph size (triples)
- | | max-path-length | integer [ 1 .. 5 ] Default: 2 Maximum path length for graph traversal
- | | streaming | boolean Default: false Enable streaming response delivery
- |
ResponsesLocal development server
- http://localhost:8088/api/v1/flow/{flow}/service/graph-rag Request samples Content typeapplication/json Example Response samples Content typeapplication/json Example {"response": "Quantum physics and computer science intersect primarily through quantum computing.\nThe knowledge graph shows connections through:\n- Quantum algorithms (Shor's algorithm, Grover's algorithm)\n- Quantum information theory\n- Computational complexity theory\n", "end-of-stream": false
}Text completion - direct LLM generation Request Body schema: application/jsonrequired | query required | | | user | string Default: "trustgraph" User identifier for multi-tenancy
+ | | collection | string Default: "default" Collection to search within
+ | | entity-limit | integer [ 1 .. 200 ] Default: 50 Maximum number of entities to retrieve
+ | | triple-limit | integer [ 1 .. 100 ] Default: 30 Maximum number of triples to retrieve per entity
+ | | max-subgraph-size | integer [ 10 .. 5000 ] Default: 1000 Maximum total subgraph size (triples)
+ | | max-path-length | integer [ 1 .. 5 ] Default: 2 Maximum path length for graph traversal
+ | | streaming | boolean Default: false Enable streaming response delivery
+ |
ResponsesLocal development server
+ http://localhost:8088/api/v1/flow/{flow}/service/graph-rag Request samples Content typeapplication/json Example Response samples Content typeapplication/json Example {"response": "Quantum physics and computer science intersect primarily through quantum computing.\nThe knowledge graph shows connections through:\n- Quantum algorithms (Shor's algorithm, Grover's algorithm)\n- Quantum information theory\n- Computational complexity theory\n", "end-of-stream": false
}Text completion - direct LLM generation Direct text completion using LLM without retrieval augmentation.
+" class="sc-iKGpAq sc-cCYyou dXXcln dHaogz"> Direct text completion using LLM without retrieval augmentation.
Text Completion Overview
Pure LLM generation for:
@@ -1422,23 +1426,23 @@ Each step has: thought, action, arguments, observation.
- Want to leverage knowledge graph relationships
- Require citations or provenance
- Request Body schema: application/jsonrequired | system required | string System prompt that sets behavior and context for the LLM
- | | prompt required | string User prompt or question
- | | streaming | boolean Default: false Enable streaming response delivery
- |
ResponsesLocal development server
- http://localhost:8088/api/v1/flow/{flow}/service/text-completion Request samples Content typeapplication/json Example {"system": "You are a helpful assistant that provides concise answers.", "prompt": "Explain the concept of recursion in programming."
} Response samples Content typeapplication/json Example {"response": "Recursion is a programming technique where a function calls itself\nto solve a problem by breaking it down into smaller, similar subproblems.\nEach recursive call works on a simpler version until reaching a base case.\n", "in-token": 45, "out-token": 128, "model": "gpt-4", "end-of-stream": false
}Prompt service - template-based generation Request Body schema: application/jsonrequired | system required | string System prompt that sets behavior and context for the LLM
+ | | prompt required | string User prompt or question
+ | | streaming | boolean Default: false Enable streaming response delivery
+ |
ResponsesLocal development server
+ http://localhost:8088/api/v1/flow/{flow}/service/text-completion Request samples Content typeapplication/json Example {"system": "You are a helpful assistant that provides concise answers.", "prompt": "Explain the concept of recursion in programming."
} Response samples Content typeapplication/json Example {"response": "Recursion is a programming technique where a function calls itself\nto solve a problem by breaking it down into smaller, similar subproblems.\nEach recursive call works on a simpler version until reaching a base case.\n", "in-token": 45, "out-token": 128, "model": "gpt-4", "end-of-stream": false
}Prompt service - template-based generation Execute stored prompt templates with variable substitution.
+" class="sc-iKGpAq sc-cCYyou dXXcln dHaogz"> Execute stored prompt templates with variable substitution.
Prompt Service Overview
The prompt service enables:
@@ -1556,25 +1560,25 @@ Each step has: thought, action, arguments, observation.
- Data transformation
- Any repeatable LLM task with consistent prompting
- Request Body schema: application/jsonrequired | id required | string Prompt template ID (stored in config)
- | | object Template variables as key-value pairs (values are JSON strings)
- | | object Alternative to terms - variables as native JSON values (auto-converted)
- | | streaming | boolean Default: false Enable streaming response delivery
- |
ResponsesLocal development server
- http://localhost:8088/api/v1/flow/{flow}/service/prompt Request samples Content typeapplication/json Example Response samples Content typeapplication/json Example Embeddings - text to vector conversion Request Body schema: application/jsonrequired | id required | string Prompt template ID (stored in config)
+ | | object Template variables as key-value pairs (values are JSON strings)
+ | | object Alternative to terms - variables as native JSON values (auto-converted)
+ | | streaming | boolean Default: false Enable streaming response delivery
+ |
ResponsesLocal development server
+ http://localhost:8088/api/v1/flow/{flow}/service/prompt Request samples Content typeapplication/json Example Response samples Content typeapplication/json Example Embeddings - text to vector conversion Convert text to embedding vectors for semantic similarity search.
+" class="sc-iKGpAq sc-cCYyou dXXcln dHaogz"> Convert text to embedding vectors for semantic similarity search.
Embeddings Overview
Embeddings transform text into dense vector representations that:
@@ -1630,19 +1634,19 @@ For bulk operations, use document-load or text-load services.</p>
Single Request
Unlike batch embedding APIs, this endpoint processes one text at a time.
For bulk operations, use document-load or text-load services.
- Request Body schema: application/jsonrequired | text required | string Text to convert to embedding vector
- |
ResponsesLocal development server
- http://localhost:8088/api/v1/flow/{flow}/service/embeddings Request samples Content typeapplication/json Example Response samples Content typeapplication/json {"vectors": [0.023, -0.142, 0.089, 0.234, -0.067, 0.156, 0.201, -0.178, 0.045, 0.312
]
} |