Skip to content
/Agents

Uniphore Business AI Cloud (1.0.0)

APIs for Uniphore Business AI platform spanning data, knowledge, models, and agents.

Metadata

KeyValue
ownerUniphore Technologies Pvt Ltd
teamBusiness AI
departmentEngineering
statusBeta
Download OpenAPI description
api.json
api.yaml
Languages
Servers
Demo Instance for Uniphore Business AI Cloud

https://forge-api-gateway-x-forge.dev.uniphorecloud.com/

Action Orchestrator

APIs for Actions Orchestration.

Operations

Agents

APIs for Agents.

Operations

Create Crews

Request

Headers
X-Tenant-Idany(X-Tenant-Id)required
X-User-Idany(X-User-Id)required
Bodyapplication/jsonrequired
nameany(Name)required

Name of the overall crew configuration or scenario.

descriptionany(Description)required

Summary of the crew’s purpose and functionality.

agentsArray of objects(Agents)required

List of agent definitions in this crew.

agents[].​nameany(Name)required

Unique name of the agent.

agents[].​roleany(Role)required

Title or function of the agent within the Crew.

agents[].​goalany(Goal)required

Primary objective or responsibility of the agent.

agents[].​backstoryBackstory (any)(Backstory)

Optional narrative to give context and personality to the agent.

Default ""
Any of:

Optional narrative to give context and personality to the agent.

any(Backstory)

Optional narrative to give context and personality to the agent.

Default ""
agents[].​toolsToolConfig (object) or Tools (any)(Tools)

List of tools this agent is allowed to use.

Any of:

List of tools this agent is allowed to use.

agents[].​llmLLMConfig (object) or LLM (any)(LLM)

The language model used to power the agent.

Any of:

Configuration for defining a LLM that can be bound to agents.

agents[].​max_iterany(Max Iterations)

Maximum number of reasoning iterations allowed during task execution.

Default 25
agents[].​reasoningReasoning (any)(Reasoning)

If true, the agent will perform reasoning steps before executing tasks.

Default false
Any of:

If true, the agent will perform reasoning steps before executing tasks.

any(Reasoning)

If true, the agent will perform reasoning steps before executing tasks.

Default false
agents[].​max_reasoning_stepsMax Reasoning Steps (any)(Max Reasoning Steps)

Maximum number of reasoning steps the agent can take before executing a task.

Default 5
Any of:

Maximum number of reasoning steps the agent can take before executing a task.

any(Max Reasoning Steps)

Maximum number of reasoning steps the agent can take before executing a task.

Default 5
agents[].​allow_code_executionAllow Code Execution (any)(Allow Code Execution)

If true, the agent can execute code as part of its reasoning process.

Default false
Any of:

If true, the agent can execute code as part of its reasoning process.

any(Allow Code Execution)

If true, the agent can execute code as part of its reasoning process.

Default false
agents[].​code_execution_modeCode Execution Mode (any)(Code Execution Mode)

Determines when the agent can execute code: 'safe' (default), or 'unsafe'.

Default "safe"
Any of:

Determines when the agent can execute code: 'safe' (default), or 'unsafe'.

any(Code Execution Mode)

Determines when the agent can execute code: 'safe' (default), or 'unsafe'.

Default "safe"
Enum"safe""unsafe"
agents[].​max_retry_limitMax Retry Limit (any)(Max Retry Limit)

Maximum number of retries allowed for task execution in case of failures.

Default 5
Any of:

Maximum number of retries allowed for task execution in case of failures.

any(Max Retry Limit)

Maximum number of retries allowed for task execution in case of failures.

Default 5
agents[].​knowledge_basesArray of Knowledge Bases (objects) or Knowledge Bases (any)(Knowledge Bases)

List of knowledge bases that the agent can access.

Any of:

List of knowledge bases that the agent can access.

tasksArray of objects(Tasks)required

List of task definitions to be executed by the agents.

tasks[].​nameany(Name)required

Unique identifier for the task.

tasks[].​descriptionany(Description)required

Instructions or objectives for the task.

tasks[].​agentany(Agent)required

Name of the agent responsible for executing the task.

tasks[].​expected_outputExpected Output (any)(Expected Output)

Description of the desired output format or structure.

Any of:

Description of the desired output format or structure.

any(Expected Output)

Description of the desired output format or structure.

tasks[].​async_executionany(Async Execution)

If true, the task can be executed asynchronously.

Default false
tasks[].​toolsToolConfig (object) or Tools (any)(Tools)

List of tools specific to this task.

Any of:

List of tools specific to this task.

tasks[].​contextArray of objects(Context)

List of prior task names whose outputs are needed as context for this task.

tasks[].​human_inputany(Human Input)

If true, the task expects manual human input or approval.

Default false
tasks[].​markdownany(Markdown)

If true, the task output should be formatted in Markdown.

Default false
tasks[].​output_formatOutput Format (any)(Output Format)

Format of the task output: 'markdown' or 'json'.

Any of:

Format of the task output: 'markdown' or 'json'.

any(Output Format)

Format of the task output: 'markdown' or 'json'.

Enum"markdown""json"
tasks[].​output_json_structureOutput JSON Structure (object) or Output JSON Structure (any)(Output JSON Structure)

Dictionary defining the structure of the expected JSON output, if output_format is 'json'.

Any of:

Dictionary defining the structure of the expected JSON output, if output_format is 'json'.

tasks[].​output_json_schemaOutput JSON Schema (object) or Output JSON Schema (any)(Output JSON Schema)

JSON schema defining the structure of the expected output, if output_format is 'json'.

Any of:

JSON schema defining the structure of the expected output, if output_format is 'json'.

processany(Process)

Execution strategy: 'sequential' or 'hierarchical'.

Default "sequential"
Enum"sequential""hierarchical"
function_calling_llmany(Function Calling LLM)

LLM used for any function-calling tasks or operations.

Default "gpt-4o-mini"
manager_agentManager Agent (any)(Manager Agent)

Name of the agent acting as the manager.

Any of:

Name of the agent acting as the manager.

any(Manager Agent)

Name of the agent acting as the manager.

manager_llmManager LLM (any)(Manager LLM)

LLM used specifically for the manager agent.

Any of:

LLM used specifically for the manager agent.

any(Manager LLM)

LLM used specifically for the manager agent.

planningPlanning (any)(Planning)

Enables dynamic planning of task execution by the manager agent.

Any of:

Enables dynamic planning of task execution by the manager agent.

any(Planning)

Enables dynamic planning of task execution by the manager agent.

planning_llmPlanning LLM (any)(Planning LLM)

LLM used specifically for dynamic planning.

Any of:

LLM used specifically for dynamic planning.

any(Planning LLM)

LLM used specifically for dynamic planning.

curl -i -X POST \
  https://forge-api-gateway-x-forge.dev.uniphorecloud.com/crewai-agents/api/v1/crews \
  -H 'Content-Type: application/json' \
  -H 'X-Tenant-Id: ' \
  -H 'X-User-Id: ' \
  -d '{
    "name": null,
    "description": null,
    "agents": [
      {
        "name": null,
        "role": null,
        "goal": null,
        "backstory": "",
        "tools": {
          "tool_ids": [
            null
          ],
          "tool_definitions": [
            {
              "name": null,
              "integration_name": null,
              "description": null,
              "result_as_answer": false
            }
          ]
        },
        "llm": {
          "provider": null,
          "llm": null,
          "top_p": null,
          "temperature": null,
          "output_token_limit": null
        },
        "max_iter": 25,
        "reasoning": false,
        "max_reasoning_steps": 5,
        "allow_code_execution": false,
        "code_execution_mode": "safe",
        "max_retry_limit": 5,
        "knowledge_bases": [
          {
            "id": null,
            "name": null
          }
        ]
      }
    ],
    "tasks": [
      {
        "name": null,
        "description": null,
        "agent": null,
        "expected_output": {},
        "async_execution": false,
        "tools": {
          "tool_ids": [
            null
          ],
          "tool_definitions": [
            {
              "name": null,
              "integration_name": null,
              "description": null,
              "result_as_answer": false
            }
          ]
        },
        "context": [
          null
        ],
        "human_input": false,
        "markdown": false,
        "output_format": "markdown",
        "output_json_structure": {
          "property1": null,
          "property2": null
        },
        "output_json_schema": {
          "property1": null,
          "property2": null
        }
      }
    ],
    "process": "sequential",
    "function_calling_llm": "gpt-4o-mini",
    "manager_agent": {},
    "manager_llm": {},
    "planning": {},
    "planning_llm": {}
  }'

Responses

Successful Response

Bodyapplication/json
any
Response
application/json
null

Delete All Crews

Request

Headers
X-Tenant-Idany(X-Tenant-Id)required
X-User-Idany(X-User-Id)required
curl -i -X DELETE \
  https://forge-api-gateway-x-forge.dev.uniphorecloud.com/crewai-agents/api/v1/crews \
  -H 'X-Tenant-Id: ' \
  -H 'X-User-Id: '

Responses

Successful Response

Bodyapplication/json
any
Response
application/json
null

Get Crews

Request

Path
crew_idany(Crew Id)required
Headers
X-Tenant-Idany(X-Tenant-Id)required
X-User-Idany(X-User-Id)required
curl -i -X GET \
  'https://forge-api-gateway-x-forge.dev.uniphorecloud.com/crewai-agents/api/v1/crews/{crew_id}' \
  -H 'X-Tenant-Id: ' \
  -H 'X-User-Id: '

Responses

Successful Response

Bodyapplication/json
any
Response
application/json
null

Darwin

APIs for Darwin.

Operations

Evaluation

APIs for Evaluation of models

Operations

Inferencing

Pegasus APIs for Inferencing.

Operations

Meta Prompting

APIs for Meta Prompting & Prompt Management.

Operations

Platform Config

APIs for Platform Setup - Workflows, Sources, Destinations, Knowledge Bases etc.

Operations

Question & Answer

APIs for Question & Answering

Operations

Tag

APIs for Tag.

Operations

User Management

APIs for User Management - Users, Roles, Permissions etc.

Operations