Reference
- Sessions
- Apps
- Agents
- Tasks
- Tools
- Models
- Datasources
- All Objects
Get Apps
Retrieve a JSON list of all apps the user has access to. Will also return a list of all tasks, tools, agents, models and datasources as a front end helper
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
The resourceSlug is a url parameter of the teamId associated with the user. Anywhere the resourceSlug is used can be interpreted as a teamId
Path Parameters
The resourceSlug is a url parameter of the teamId associated with the user. Anywhere the resourceSlug is used can be interpreted as a teamId
Response
cross site token
Unique Mongodb identifier for the object
Organisation the agent is linked to (generally the org of the user that created the agent)
Team the agent is linked to (generally the team of the user that created the agent)
Name of the agent
Fed into the LLM to help it provide a more detailed and correct response
The goal of the agent is fed into the LLM, this allows the LLM to know it's role in the RAG pipeline
A detailed description of what the LLM will be doing
The linked ObjectId of the model being used by this agent (this links to a Model object)
A secondary model used to execute function calls (this links to a Model object), set to null if unused automatically by the API
True or false check to determine if custom verbosity is used in agent, higher verbosity requires agent to include more of the retrieved documents at the expense of longer answers, lower verbosity can result in shorter answers but can also ommit crucial details
True or false check to determine if the agent is allowed to delegate tasks to other agents in the context of an app
Array of the tools the agent can access to improve performance and abstract tool functionality from agent usage
Unique identifier for the task.
Identifier of the organization to which the task belongs.
Identifier of the team to which the task belongs.
The name of the task.
A detailed description of the task.
Identifier of the agent associated with the task.
The expected output of the task.
List of tool identifiers associated with the task.
Indicates if the task is executed asynchronously.
Contextual information related to the task.
The JSON output of the task.
The Pydantic output of the task.
The file output of the task.
Icon associated with the task, either an attachment or an object containing the icon details.
this is NOT a unique id for the IconAttachment, this is a Mongo id that links to an Asset object (neet to implement assets in docs)
Mongodb Object id, unique identifier, length of 24 characters fitting the following regex; [a-f0-9]{24}
Filename of the attachment at the point of upload
Indicates if the task requires human input.
Indicates if only the final output should be displayed.
Indicates if the task is hidden from standard views.
Array of form field configurations associated with the task.
The position of the form field within the form layout.
The data type of the form field.
string, number, radio, checkbox, select, multiselect, date The name attribute of the form field.
The label displayed for the form field.
An optional description for the form field.
Indicates if the form field is required.
Options available for fields like radio, select, or multiselect.
A tooltip providing additional information about the form field.
Indicates if the output of the task is structured.
Mongodb Object id, unique identifier, length of 24 characters fitting the following regex; [a-f0-9]{24}
Identifier of the organization to which the tool belongs.
Identifier of the team to which the tool belongs.
The name of the tool.
A detailed description of the tool.
The type of tool.
function, rag The schema associated with the tool.
The type of retriever used by the tool.
raw, self_query, time_weighted, multi_query Configuration settings for the retriever.
Array of metadata field information objects.
The name of the metadata field.
A description of the metadata field.
The data type of the metadata field.
string, integer, float Number of results to retrieve.
Identifier of the datasource associated with the tool.
The current state of the tool.
pending, ready, error Data related to the tool, including runtime, environment variables, and more.
The name of the data.
The runtime environment for the tool.
Indicates if the tool is a built-in feature.
A description of the data.
API key associated with the tool.
Environment variables required by the tool.
Code associated with the tool.
Requirements needed by the tool.
Key used to match OpenAPI specifications.
Icon associated with the tool.
this is NOT a unique id for the IconAttachment, this is a Mongo id that links to an Asset object (neet to implement assets in docs)
Mongodb Object id, unique identifier, length of 24 characters fitting the following regex; [a-f0-9]{24}
Filename of the attachment at the point of upload
Indicates whether the tool is hidden.
Identifier of the function associated with the tool.
Identifier of the tool's revision.
Logs related to the function's execution.
Unique Mongodb identifier for the object
Organisation the agent is linked to (generally the org of the user that created the agent)
Team the agent is linked to (generally the team of the user that created the agent)
Name of the agent
Fed into the LLM to help it provide a more detailed and correct response
The goal of the agent is fed into the LLM, this allows the LLM to know it's role in the RAG pipeline
A detailed description of what the LLM will be doing
The linked ObjectId of the model being used by this agent (this links to a Model object)
A secondary model used to execute function calls (this links to a Model object), set to null if unused automatically by the API
True or false check to determine if custom verbosity is used in agent, higher verbosity requires agent to include more of the retrieved documents at the expense of longer answers, lower verbosity can result in shorter answers but can also ommit crucial details
True or false check to determine if the agent is allowed to delegate tasks to other agents in the context of an app
Array of the tools the agent can access to improve performance and abstract tool functionality from agent usage
Unique identifier for the model.
Identifier of the organization to which the model belongs.
Identifier of the team to which the model belongs.
The name of the model.
The specific AI model used.
The length of the embeddings generated by the model.
The type of the model.
The general type of the model (e.g., embedding, language model).
Configuration settings for the model.
The model configuration setting.
API key for accessing the model.
The base URL for the model's API.
API key for accessing Cohere services.
API key for accessing Groq services.
Unique identifier for the datasource.
Identifier of the organization to which the datasource belongs.
Identifier of the team to which the datasource belongs.
The name of the datasource.
Optional description of the datasource.
The original name of the datasource.
The name of the file associated with the datasource, if applicable.
The type of source for the datasource.
The identifier of the data source.
The identifier of the data destination.
The identifier of the workspace associated with the datasource.
The identifier of the connection associated with the datasource.
The record count details for the datasource, including total, successful, and failed records.
Configuration settings for the datasource connection.
Optional prefix to be added to the destination's namespace. Can be null.
The name of the datasource connection.
The identifier of the data source.
The identifier of the data destination.
The status of the datasource connection. This should match the enum values defined by the Airbyte API and should allow creation in a paused state.
Configuration settings for the datasource connection. Structure is dependent on the datasource type.
Specifies the behavior for handling non-breaking schema updates.
Scheduling information for the datasource connection.
Specifies where the data should be stored geographically.
Defines how the namespace should be determined for the data.
The format of the namespace, can be null if not applicable.
The date and time when the datasource was created.
The date and time when the datasource was last synced. Null indicates it has never been synced.
The current status of the datasource.
draft, processing, embedding, ready Schema discovered during the data source connection. The structure depends on the source type.
Configuration settings for chunking unstructured data, including partitioning and chunking strategies, character limits, and similarity thresholds.
The partitioning strategy used for unstructured data.
auto, fast, hi_res, ocr_only The chunking strategy used for unstructured data.
basic, by_title, by_page, by_similarity The maximum number of characters allowed per chunk.
The number of characters after which a new chunk is created.
The number of characters to overlap between chunks.
Threshold for similarity when chunking by similarity, with a value between 0.0 and 1.0.
0 < x < 1Indicates whether to apply overlap to all chunks or only between adjacent chunks.
The field used for embedding within the datasource.
The field used to apply time weighting within the datasource.
Identifier of the embedding model used, if applicable.
Indicates whether the datasource is hidden from standard views.
Configuration settings for processing streams of data, breaking them into smaller chunks for more manageable processing.
Configuration settings for a specific stream, used to break down large volumes of data into smaller, manageable chunks for processing.
List of child stream identifiers that are checked for inclusion in the sync.
List of fields that make up the primary key for the stream.
The synchronization mode used for the stream.
List of fields that act as the cursor for incremental syncs.
A temporary field to limit CRON frequency based on the plan. This will be replaced with a more robust solution in the future.