# ThoughtSpotRestApiSdk.AIApi All URIs are relative to *CLUSTER_URL* Method | HTTP request | Description ------------- | ------------- | ------------- [**createAgentConversation**](AIApi.md#createAgentConversation) | **POST** /api/rest/2.0/ai/agent/conversation/create | [**createAnalyst**](AIApi.md#createAnalyst) | **POST** /api/rest/2.0/ai/agent/analysts/create | [**createConversation**](AIApi.md#createConversation) | **POST** /api/rest/2.0/ai/conversation/create | [**deleteAnalyst**](AIApi.md#deleteAnalyst) | **POST** /api/rest/2.0/ai/agent/analysts/{analyst_identifier}/delete | [**deleteConversation**](AIApi.md#deleteConversation) | **DELETE** /api/rest/2.0/ai/agent/conversations/{conversation_identifier}/delete | [**exportMemory**](AIApi.md#exportMemory) | **POST** /api/rest/2.0/ai/memory/export | [**getAgentInstructions**](AIApi.md#getAgentInstructions) | **GET** /api/rest/2.0/ai/agent/instructions/get | [**getConversation**](AIApi.md#getConversation) | **GET** /api/rest/2.0/ai/agent/conversations/{conversation_identifier}/messages | [**getConversationList**](AIApi.md#getConversationList) | **GET** /api/rest/2.0/ai/agent/conversations | [**getDataSourceSuggestions**](AIApi.md#getDataSourceSuggestions) | **POST** /api/rest/2.0/ai/data-source-suggestions | [**getNLInstructions**](AIApi.md#getNLInstructions) | **POST** /api/rest/2.0/ai/instructions/get | [**getRelevantQuestions**](AIApi.md#getRelevantQuestions) | **POST** /api/rest/2.0/ai/relevant-questions/ | [**getShareInfo**](AIApi.md#getShareInfo) | **GET** /api/rest/2.0/ai/agent/conversations/{conversation_identifier}/get-share-info | [**getSharedContent**](AIApi.md#getSharedContent) | **GET** /api/rest/2.0/ai/agent/conversations/{conversation_identifier}/get-shared-content | [**importMemory**](AIApi.md#importMemory) | **POST** /api/rest/2.0/ai/memory/import | [**loadAnswer**](AIApi.md#loadAnswer) | **GET** /api/rest/2.0/ai/agent/conversations/{conversation_identifier}/answers/{answer_identifier}/details | [**queryGetDecomposedQuery**](AIApi.md#queryGetDecomposedQuery) | **POST** /api/rest/2.0/ai/analytical-questions | [**searchAnalysts**](AIApi.md#searchAnalysts) | **POST** /api/rest/2.0/ai/agent/analysts/search | [**sendAgentConversationMessage**](AIApi.md#sendAgentConversationMessage) | **POST** /api/rest/2.0/ai/agent/conversation/{conversation_identifier}/send | [**sendAgentConversationMessageStreaming**](AIApi.md#sendAgentConversationMessageStreaming) | **POST** /api/rest/2.0/ai/agent/conversation/{conversation_identifier}/send/stream | [**sendAgentMessage**](AIApi.md#sendAgentMessage) | **POST** /api/rest/2.0/ai/agent/{conversation_identifier}/converse | [**sendAgentMessageStreaming**](AIApi.md#sendAgentMessageStreaming) | **POST** /api/rest/2.0/ai/agent/converse/sse | [**sendMessage**](AIApi.md#sendMessage) | **POST** /api/rest/2.0/ai/conversation/{conversation_identifier}/converse | [**setAgentInstructions**](AIApi.md#setAgentInstructions) | **PUT** /api/rest/2.0/ai/agent/instructions/set | [**setNLInstructions**](AIApi.md#setNLInstructions) | **POST** /api/rest/2.0/ai/instructions/set | [**shareAnalyst**](AIApi.md#shareAnalyst) | **POST** /api/rest/2.0/ai/agent/analysts/{analyst_identifier}/share | [**shareConversation**](AIApi.md#shareConversation) | **POST** /api/rest/2.0/ai/agent/conversations/{conversation_identifier}/share | [**singleAnswer**](AIApi.md#singleAnswer) | **POST** /api/rest/2.0/ai/answer/create | [**stopConversation**](AIApi.md#stopConversation) | **POST** /api/rest/2.0/ai/agent/conversation/{conversation_identifier}/stop-response | [**updateAnalyst**](AIApi.md#updateAnalyst) | **POST** /api/rest/2.0/ai/agent/analysts/{analyst_identifier}/update | [**updateConversation**](AIApi.md#updateConversation) | **POST** /api/rest/2.0/ai/agent/conversations/{conversation_identifier}/update | # **createAgentConversation** > AgentConversation createAgentConversation(createAgentConversationRequest) Version: 26.2.0.cl or later Creates a new Spotter agent conversation based on the provided context and settings. The endpoint was in Beta from 26.2.0.cl through 26.4.0.cl. Requires `CAN_USE_SPOTTER` privilege and at least view access to the metadata object specified in the request. #### Usage guidelines The conversation context is defined by exactly one of the following parameters: - `metadata_context`: defines the conversation context by data source. The context type can be one of: - `DATA_SOURCE` *(available from 26.5.0.cl)*: targets a specific data source. Provide `data_source_identifier` in `data_source_context` for a single data source, or `data_source_identifiers` for multi-data-source context. The deprecated `guid` field is accepted for backwards compatibility. - `AUTO_MODE` *(available from 26.5.0.cl)*: automatically discovers and selects the most relevant datasets for the user\'s queries. - `analyst_identifier` *(available from 26.10.0.cl)*: unique identifier of a Spotter Analyst to start the conversation from. The conversation uses the analyst\'s configuration — its data sources, agent instructions, and connectors — so `metadata_context` must be omitted. The caller must be the analyst\'s author, have the analyst shared with them, or hold admin / Spotter-management privileges. Passing both `analyst_identifier` and `metadata_context`, or neither, is rejected. > **Note for callers on versions 26.2.0.cl – 26.4.0.cl (Beta):** use the lowercase `data_source` enum value with the `guid` field instead of the above. Example: `{ \"type\": \"data_source\", \"data_source_context\": { \"guid\": \"\" } }`. The `conversation_settings` parameter controls which Spotter capabilities are enabled for the conversation: - `enable_contextual_change_analysis` (default: `true`, **deprecated from 26.2.0.cl**) — always enabled in Spotter 3; setting this to `false` has no effect on versions >= 26.2.0.cl - `enable_natural_language_answer_generation` (default: `true`, **deprecated from 26.2.0.cl**) — always enabled in Spotter 3; setting this to `false` has no effect on versions >= 26.2.0.cl - `enable_reasoning` (default: `true`, **deprecated from 26.2.0.cl**) — always enabled in Spotter 3; setting this to `false` has no effect on versions >= 26.2.0.cl - `enable_save_chat` (default: `false`, *available from 26.5.0.cl*) — enables saving the conversation for later retrieval via conversation history If the request is successful, the response includes a unique `conversation_identifier` that must be passed to `sendAgentConversationMessage` or `sendAgentConversationMessageStreaming` to send messages within this conversation. The response also includes `conversation_id` with the same value for backwards compatibility; use `conversation_identifier` for new integrations. When the conversation is started from an analyst, the response additionally carries the analyst\'s `analyst_id`; it is `null` otherwise. #### Example request ```json { \"metadata_context\": { \"type\": \"DATA_SOURCE\", \"data_source_context\": { \"data_source_identifier\": \"a1b2c3d4-e5f6-7890-abcd-ef1234567890\" } }, \"conversation_settings\": {} } ``` #### Error responses | Code | Description | | ---- | --------------------------------------------------------------------------------------------------------------------------------------- | | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege, lacks view permission on the specified metadata object, or has no access to the analyst specified in `analyst_identifier`. | | 404 | Not found — no analyst with the given `analyst_identifier` exists in the caller\'s Org. | | 422 | Unprocessable entity — the request fails validation: both `analyst_identifier` and `metadata_context` were provided, neither was provided, or `metadata_context` is malformed (for example, `DATA_SOURCE` context without a data source identifier). | > ###### Note: > > - This endpoint was in Beta from 26.2.0.cl through 26.4.0.cl and is Generally Available from version 26.5.0.cl. > - This endpoint requires Spotter - please contact ThoughtSpot support to enable Spotter on your cluster. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, CreateAgentConversationRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.createAgentConversation( // CreateAgentConversationRequest { metadata_context: null, conversation_settings: null, analyst_identifier: "analyst_identifier_example", } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **createAgentConversationRequest** | **CreateAgentConversationRequest**| | ### Return type **AgentConversation** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **createAnalyst** > Analyst createAnalyst(createAnalystRequest) Creates a Spotter Analyst: a configured agent with a name, description, at least one data source, and optional agent instructions, MCP connectors, and starter prompts. Analysts created via API use the default icon until one is set in the UI. Requires at least one of `ADMINISTRATION`, `CAN_MANAGE_SPOTTER`, or `CAN_USE_SPOTTER` privileges, plus view access to every data source referenced in `sources`. Version: 26.10.0.cl or later Creates a Spotter Analyst: a configured agent with a name, description, data sources, and optional agent instructions, MCP connectors, and starter prompts that your users converse with in Spotter. Requires at least one of `ADMINISTRATION`, `CAN_MANAGE_SPOTTER`, or `CAN_USE_SPOTTER` privileges, plus view access to every data source referenced in `sources`. Use a bearer token for the Org in which the analyst should be created. #### Usage guidelines The request body is flat — all fields are top-level: - `name` (required): display name of the analyst. - `description` (required): up to 200 characters. - `instructions` (optional): natural-language instructions that guide the agent\'s behavior for this analyst. Instructions that conflict with system guardrails are rejected with `409`. - `sources` (required): at least one data source the analyst can query, each with an `identifier`, an optional `name`, and a `type` (`MODEL`, `ANSWER`, `LIVEBOARD`, or `CONVERSATION`). The caller must have view access to every referenced source. - `mcp_connector_identifiers` (optional): identifiers of MCP connectors to link to the analyst. - `starter_prompts` (optional): up to 4 plain-text prompts shown on the analyst landing page, each between 10 and 250 characters. Display order follows list position. If the request is successful, the response contains the created analyst, including the server-assigned `id`. In responses, sources are returned with `id` and `type`, connector identifiers as `mcp_connectors`, starter prompts as structured objects (`label`, `text`, `order`, `is_ai_generated`), the last-update time as `updated_time_in_millis` (epoch milliseconds), and the `created_by` and `updated_by` users. #### Error conditions - `403` — missing privileges, or no view access to a referenced data source. - `409` — `instructions` conflict with system guardrails. - `422` — validation failure, such as a missing required field (`name`, `description`, or `sources`), an empty `sources` list, too many starter prompts, or field-length violations. - `429` — rate limit exceeded. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, CreateAnalystRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.createAnalyst( // CreateAnalystRequest { name: "name_example", description: "description_example", instructions: "instructions_example", sources: [ { identifier: "identifier_example", name: "name_example", type: "MODEL", }, ], mcp_connector_identifiers: [], starter_prompts: [], } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **createAnalystRequest** | **CreateAnalystRequest**| | ### Return type **Analyst** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **createConversation** > Conversation createConversation(createConversationRequest) Version: 10.4.0.cl or later Creates a new conversation session tied to a specific data model for AI-driven natural language querying. Requires `CAN_USE_SPOTTER` privilege and at least view access to the metadata object specified in the request. #### Usage guidelines The request must include: - `metadata_identifier`: the unique ID of the data source that provides context for the conversation Optionally, you can provide: - `tokens`: a token string to set initial context for the conversation (e.g., `\"[sales],[item type],[state]\"`) If the request is successful, ThoughtSpot returns a unique `conversation_identifier` that must be passed to `sendMessage` to continue the conversation. #### Error responses | Code | Description | |------|-------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege or lacks view permission on the specified metadata object. | > ###### Note: > * This endpoint is currently in Beta. Breaking changes may be introduced before the endpoint is made Generally Available. > * This endpoint requires Spotter - please contact ThoughtSpot support to enable Spotter on your cluster. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, CreateConversationRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.createConversation( // CreateConversationRequest { metadata_identifier: "metadata_identifier_example", tokens: "tokens_example", } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **createConversationRequest** | **CreateConversationRequest**| | ### Return type **Conversation** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **deleteAnalyst** > AnalystDeleteResponse deleteAnalyst() Permanently deletes a Spotter Analyst. This operation is irreversible — deleted analysts cannot be recovered. The request has no body; the response contains the `id` of the deleted analyst. Requires ownership of the analyst, or `ADMINISTRATION` or `CAN_MANAGE_SPOTTER` privileges. Version: 26.10.0.cl or later Permanently deletes a Spotter Analyst. This operation is irreversible — deleted analysts cannot be recovered. Requires ownership of the analyst, or `ADMINISTRATION` or `CAN_MANAGE_SPOTTER` privileges. Users the analyst is shared with cannot delete it. Use a bearer token for the Org in which the analyst exists. #### Usage guidelines The request has no body — the analyst to delete is identified by the `analyst_identifier` path parameter, as returned by the create analyst API. A successful request returns the `id` of the deleted analyst. #### Error conditions - `400` — malformed analyst identifier. - `403` — the caller is not the analyst\'s author and lacks admin / Spotter-management privileges. - `404` — no analyst with the given identifier exists in the caller\'s Org. - `429` — rate limit exceeded. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, DeleteAnalystRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.deleteAnalyst( // string | Unique identifier of the analyst to delete. "analyst_identifier_example" ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **analystIdentifier** | [**string**] | Unique identifier of the analyst to delete. | defaults to undefined ### Return type **AnalystDeleteResponse** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: Not defined - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **deleteConversation** > void deleteConversation() Deletes an existing agent conversation. Version: 26.7.0.cl or later Permanently deletes an existing saved agent conversation and all its associated messages. This operation is irreversible — deleted conversations cannot be recovered. Requires `CAN_USE_SPOTTER` privilege and ownership of the conversation being deleted. #### Usage guidelines The request must include: - `conversation_identifier` *(path parameter)*: the unique ID of the conversation to delete, as returned by `createAgentConversation` or `getConversationList` A successful request returns an empty `204 No Content` response. The deleted conversation no longer appears in `getConversationList`. #### Example request ```bash DELETE /api/rest/2.0/ai/agent/conversations/{conversation_identifier}/delete ``` #### Error responses | Code | Description | |------|-------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege or does not own the specified conversation. | | 404 | Not Found — no conversation exists with the given `conversation_identifier` for the authenticated user. | > ###### Note: > > - Deletion is permanent and cannot be undone. Ensure the correct `conversation_identifier` is used before calling this endpoint. > - Only conversations created with `enable_save_chat: true` are persisted and can be deleted via this endpoint. > - Available from version 26.7.0.cl and later. > - This endpoint requires Spotter — please contact ThoughtSpot Support to enable Spotter on your cluster. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, DeleteConversationRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.deleteConversation( // string | Unique identifier of the conversation to delete. "conversation_identifier_example" ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **conversationIdentifier** | [**string**] | Unique identifier of the conversation to delete. | defaults to undefined ### Return type **void** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: Not defined - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **204** | Successfully deleted the agent conversation. | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **exportMemory** > ExportMemoryResponse exportMemory(exportMemoryRequest) Exports memory entries (rules, recipes, and always-apply rules) for the specified data-models as a single YAML payload. The payload can be edited locally and re-submitted through `importMemory`. Requires Spotter access (use/manage) and either edit or memory access on corresponding data model sources. Version: 26.8.0.cl or later This API allows users to export data-model memories for a given list of data-models. This exported yaml file can then be modified and used as input to the import API in target env. This API enables customers to migrate memories from a source env to a target env. This improves memory adoption for Spotter by giving the users a chance to develop their memories in one env and replicate the same in another env. #### Usage guidelines To export memory for one or more data-models, the request may include: - `sources`: A list of typed scope groups identifying which data-models to export memory for. Each group contains: - `type`: The source object type for this group — `DATA_MODEL`. - `identifiers`: An array of GUIDs or human-readable `obj_id`s of the data-models to export memory for. obj_ids are resolved server-side before forwarding. The API returns a response object with: - `content`: The serialized memory payload (YAML) — exactly the shape that the `importMemory` API consumes. Edit it locally and pass it back through `importMemory` to apply changes. #### Source Type - **DATA_MODEL**: The `identifiers` are data-model GUIDs. This is the default source type for Spotter memory and covers the rules, recipes and always-apply rules attached directly to a data-model. #### File format The exported `content` is a YAML document with a single top-level `memories` key holding a list of memory items — exactly the format the `importMemory` API consumes. The full format reference (an annotated example, memory item fields, per-type content, and `datamodel_sources` identification) is documented in the `importMemory` API\'s **File format** section. Exported files populate each source\'s `guid` and, if present, `obj_id` as well. #### Error responses | Code | Description | |------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have necessary permissions, or lacks read access on a referenced data-model, or the bearer token does not correspond to the data-model\'s org. | > ###### Note: > - To use this API, the user needs Spotter access (use/manage) and either edit or memory access on the data-model and they must use corresponding org related bearerToken where the data-model exists. > - This endpoint is currently in Beta. Breaking changes may be introduced before the endpoint is made Generally Available. > - Available from version 26.8.0.cl and later. > - This endpoint requires Spotter — please contact ThoughtSpot Support to enable Spotter on your cluster. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, ExportMemoryRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.exportMemory( // ExportMemoryRequest { sources: [ { type: "DATA_MODEL", identifiers: [ "identifiers_example", ], }, ], } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **exportMemoryRequest** | **ExportMemoryRequest**| | ### Return type **ExportMemoryResponse** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **getAgentInstructions** > AgentInstructions getAgentInstructions() Version: 26.6.0.cl or later Retrieves the admin instructions currently configured for the AI agent (Spotter). Admin instructions are tenant- and org-scoped text that guide agent behavior across all conversations. Requires admin privileges. Only users with org admin access can retrieve agent instructions. #### Usage guidelines No input parameters are required. The API returns the stored `AgentInstructions` record for the caller\'s tenant and org. If no instructions have been configured yet, the API returns a record with an empty `instructions` field and `null` values for `id`, `created_at`, `updated_at`, and `last_updated_by`. If the request is successful, the response includes: - `id`: unique identifier of the instructions record - `instructions`: the configured instructions text - `created_at`: ISO timestamp when the instructions were first saved - `updated_at`: ISO timestamp when the instructions were last updated - `last_updated_by`: user ID of the admin who last updated the instructions (may be `null` for older records) #### Error responses | Code | Description | |------|-------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have org admin privileges required to read agent instructions. | > ###### Note: > > - Use `setAgentInstructions` to create or update agent instructions. > - Available from version 26.6.0.cl and later. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, GetAgentInstructionsRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.getAgentInstructions().then((data:any) => { console.log('API called successfully. Returned data: ' + JSON.stringify(data)); }).catch((error:any) => console.error(error)); ``` ### Parameters This endpoint does not need any parameter. ### Return type **AgentInstructions** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: Not defined - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **getConversation** > ConversationMessageResponse getConversation() Retrieves the full public-safe content of a saved agent conversation: ordered turns (user messages and agent response items) and sanitized code-execution file metadata. Internal graph or branch state, Azure file identifiers, and messages with a `SYSTEM` source are omitted. The full answer payload is not embedded; fetch it separately via `loadAnswer` using the `answer_id` on each `answer` response item. Requires `CAN_USE_SPOTTER` privilege and access to the specified conversation. Version: 26.7.0.cl or later Retrieves the full public-safe content of a saved agent conversation. Returns ordered conversation messages — each carrying an optional user prompt (the user\'s message and any attachments) and the agent response items produced for that turn — plus sanitized metadata for any files generated by the code-execution tool. Use this endpoint to render a persisted conversation in a UI, build an audit trail, or post-process a completed conversation. The full answer payload is not embedded — fetch it separately via `loadAnswer` using the `answer_id` on each `answer` response item. Requires `CAN_USE_SPOTTER` privilege and access to the specified conversation. #### Usage guidelines The request must include: - `conversation_identifier` _(path parameter)_: the unique ID of the conversation, as returned by `createAgentConversation` or `getConversationList`. If the request is successful, the response contains two top-level fields: | Field | Type | Description | | ---------------------- | ------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------- | | `messages` | `ConversationMessage[]` | Ordered oldest to newest. Empty array when the conversation has no messages. | | `code_execution_files` | `CodeExecutionFileMetadata[]` | List of sanitized file metadata entries (one per `file_id`). Covers all code-execution-generated files referenced anywhere in the conversation. Empty array when there are none. | No other top-level fields are returned. #### ConversationMessage fields | Field | Type | Description | | --------------------- | ---------------------------- | -------------------------------------------------------------------------------------------------------------- | | `message_id` | `String` | Stable identifier for the turn. For liveboard-started synthetic first turns, this is the root node identifier. | | `timestamp_in_millis` | `Long` | Milliseconds since Unix epoch for the turn. | | `user_prompt` | `UserPrompt` | User-authored prompt that started the turn (message and attachments). `null` for liveboard-started synthetic first turns. | | `response_items` | `ConversationResponseItem[]` | Agent-side output produced in response to this turn. Empty array for in-progress turns. | #### UserPrompt fields | Field | Type | Description | | ------------- | ---------------------- | ---------------------------------------------------------------------------------------------------- | | `message` | `UserMessage` | User query that started the turn. `null` for liveboard-started synthetic first turns. | | `attachments` | `UserAttachmentItem[]` | Files or connector resources attached to the user message. Empty array when there are no attachments. | #### UserMessage fields | Field | Type | Description | | ------------ | -------- | --------------------------------------------- | | `message_id` | `String` | Unique identifier of the user-source message. | | `content` | `String` | Text body of the user query. | #### UserAttachmentItem fields Discriminated by `type`. Only `\"file\"` or `\"resource\"` are valid values. Only the fields for the indicated variant are populated. See `ConversationResponseItem` below for the field definitions of the `file` and `resource` variants — `UserAttachmentItem` uses the same fields. #### ConversationResponseItem fields Every item carries a `type` discriminator and these shared fields: | Field | Type | Description | | --------------------- | --------- | ------------------------------------------------------------------------------------------------------------------------------ | | `type` | `String` | Discriminator. One of `\"text\"`, `\"tool_call\"`, `\"tool_result\"`, `\"answer\"`, `\"file\"`, `\"resource\"`, `\"search_datasets\"`. | | `timestamp_in_millis` | `Long` | Milliseconds since Unix epoch when this item was produced. | | `is_thinking` | `Boolean` | `true` when the item represents internal agent reasoning rather than user-facing output. Consumers may hide or collapse these. | | `step_title` | `String` | Human-readable label for the agent step producing this item (e.g. `\"Searching\"`, `\"Visualising\"`). | Variant-specific fields: - **`text`** — agent text output: `content` (String), `content_type` (`ContentMimeType` enum), `file_reference` (FileReference). - **`tool_call`** — agent invoked a tool: `tool_call_id` (String), `tool_name` (String), `arguments` (JSON object). - **`tool_result`** — result returned from a tool invocation: `tool_call_id`, `tool_name`, `content`, `content_type` (`ContentMimeType` enum), `success` (Boolean). - **`answer`** — slim reference to a saved answer: `answer_id` (String), `tool_call_id`, `tool_name`. - **`file`** — uploaded or generated files: `files` (`PublicFileInfo[]`). - **`resource`** — MCP connector resource: `title`, `uri`, `name`, `mime_type`, `description`, `size` (Int), `connector_id`, `connector_name`, `connector_slug`, `transport_type` (`TransportType` enum). - **`search_datasets`** — dataset discovery result: `text` (String), `data_sources` (`DataSourceInfo[]`). Clients should switch on `type` and ignore unknown variants for forward-compatibility. #### content_type values `content_type` is the `ContentMimeType` enum. The following values are defined: | Value | Wire MIME | Meaning | | --------------------------- | --------------------------- | ---------------------------------------------------- | | `TEXT_PLAIN` | `text/plain` | Plain text. Default for `tool_result`. | | `TEXT_MARKDOWN` | `text/markdown` | Markdown. Default for `text`. | | `TEXT_X_MARKDOWN_WITH_CODE` | `text/x-markdown-with-code` | Markdown whose body starts with a fenced code block. | | `TEXT_HTML` | `text/html` | Raw HTML. | #### transport_type values `transport_type` is the `TransportType` enum used on the `resource` variant. | Value | Meaning | | ------------------ | --------------------------------------------- | | `STREAMABLE_HTTP` | Streamable HTTP transport (default for MCP). | | `SSE` | Server-sent events transport. | #### FileReference fields | Field | Type | Description | | ------------------------ | -------- | ------------------------------------------------------------ | | `file_id` | `String` | Unique identifier of the code-execution-generated file. | | `display_name` | `String` | Human-readable file name. | | `created_time_in_millis` | `Long` | Milliseconds since Unix epoch when the file was created. | Cross-reference `file_id` against `code_execution_files` to retrieve full metadata including the `expired` flag before attempting a download. #### PublicFileInfo fields | Field | Type | Description | | ------------------------ | -------- | -------------------------------------------------------- | | `file_id` | `String` | Unique identifier of the file. | | `display_name` | `String` | Human-readable file name. | | `file_type` | `String` | File type such as `csv`, `pdf`, or `png`. | | `created_time_in_millis` | `Long` | Milliseconds since Unix epoch when the file was created. | | `size_bytes` | `Int` | File size in bytes. | #### CodeExecutionFileMetadata fields Each entry in the `code_execution_files` array contains: | Field | Type | Description | | ------------------------ | --------- | ------------------------------------------------------------------------------------------------------------------------------- | | `file_id` | `String` | Unique identifier of the file. | | `display_name` | `String` | Human-readable file name. | | `file_type` | `String` | File type such as `csv`, `pdf`, or `png`. | | `created_time_in_millis` | `Long` | Milliseconds since Unix epoch when the file was created. | | `expired` | `Boolean` | When `true`, the underlying file is no longer retrievable from code-execution storage; UIs should disable download and preview. | #### Loading answer payloads Each `AnswerResponseItem` in the response contains an `answer_id` field. Pass this value as the `answer_identifier` parameter to `loadAnswer` to retrieve the full answer payload (TML tokens, visualization metadata) for that item. #### Example request ```bash GET /api/rest/2.0/ai/agent/conversations/{conversation_identifier}/messages ``` #### Example response ```json { \"messages\": [ { \"message_id\": \"node_u_01\", \"timestamp_in_millis\": 1744000000000, \"user_prompt\": { \"message\": { \"message_id\": \"msg_u_01\", \"content\": \"Show me revenue by region as a chart.\" }, \"attachments\": [] }, \"response_items\": [ { \"type\": \"tool_call\", \"tool_call_id\": \"toolu_01ABC\", \"tool_name\": \"search_datasets\", \"step_title\": \"Searching datasets\", \"arguments\": { \"query\": \"revenue\" }, \"timestamp_in_millis\": 1744000001000, \"is_thinking\": false }, { \"type\": \"answer\", \"answer_id\": \"ans_01XYZ\", \"tool_call_id\": \"toolu_02DEF\", \"tool_name\": \"fetch_and_visualize\", \"step_title\": \"Visualising\", \"timestamp_in_millis\": 1744000004000, \"is_thinking\": false }, { \"type\": \"text\", \"content\": \"Revenue is highest in APAC.\", \"content_type\": \"TEXT_MARKDOWN\", \"timestamp_in_millis\": 1744000005000, \"is_thinking\": false, \"step_title\": null, \"file_reference\": { \"file_id\": \"revenue_by_region.csv\", \"display_name\": \"revenue_by_region.csv\", \"created_time_in_millis\": 1744027200000 } } ] } ], \"code_execution_files\": [ { \"file_id\": \"revenue_by_region.csv\", \"display_name\": \"revenue_by_region.csv\", \"file_type\": \"csv\", \"created_time_in_millis\": 1744027200000, \"expired\": false } ] } ``` #### Example: liveboard-started conversation When a conversation is initiated from a saved liveboard visualization rather than a user query, the first turn is synthetic. `user_prompt` is `null`, and `response_items` contains a single `answer` item referencing the seed visualization. ```json { \"messages\": [ { \"message_id\": \"ROOT_NODE\", \"timestamp_in_millis\": 1743999000000, \"user_prompt\": null, \"response_items\": [ { \"type\": \"answer\", \"answer_id\": \"lb_seed_01\", \"tool_call_id\": null, \"tool_name\": null, \"step_title\": null, \"timestamp_in_millis\": 1743999000000, \"is_thinking\": false } ] } ], \"code_execution_files\": [] } ``` Subsequent turns follow the normal user-to-agent pattern. #### Error responses | Code | Description | | ---- | --------------------------------------------------------------------------------------------------------------------------- | | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege or lacks access to the specified conversation. | | 404 | Not Found — no conversation exists with the given identifier for the authenticated user. | > ###### Note: > > - Messages with an internal `SYSTEM` source are always dropped from the response. > - In-progress turns are still returned with an empty `response_items` array so clients can render the user message immediately. > - Do not assume every `tool_call` has a paired `tool_result` or `answer` — an interrupted conversation can leave a dangling call. > - Available from version 26.7.0.cl and later. > - This endpoint requires Spotter — please contact ThoughtSpot Support to enable Spotter on your cluster. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, GetConversationRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.getConversation( // string | Unique identifier of the conversation to load. "conversation_identifier_example" ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **conversationIdentifier** | [**string**] | Unique identifier of the conversation to load. | defaults to undefined ### Return type **ConversationMessageResponse** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: Not defined - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **getConversationList** > AgentConversationHistoryResponse getConversationList() Retrieves the list of saved agent conversations for the currently authenticated user. Only conversations created with `enable_save_chat: true` are returned. Version: 26.7.0.cl or later Retrieves a paginated list of saved agent conversations for the currently authenticated user. Only conversations that were created with `enable_save_chat: true` in `createAgentConversation` are returned. Requires `CAN_USE_SPOTTER` privilege. #### Usage guidelines The request supports the following optional query parameters: - `limit`: maximum number of conversations to return. Use this together with `offset` for pagination. - `offset`: number of conversations to skip before returning results. Defaults to `0`. - `skip_empty`: when `true` (default), conversations with no messages are excluded from the results. Set to `false` to include empty conversations. If the request is successful, the response includes a `conversations` array. Each entry contains: - `conversation_identifier`: the unique ID of the conversation, used as input to `sendAgentConversationMessage`, `updateConversation`, `deleteConversation`, `stopConversation`, and `loadAnswer` - `conversation_title`: the display name of the conversation - `created_at`: ISO 8601 timestamp of when the conversation was created - `updated_at`: ISO 8601 timestamp of the most recent update to the conversation - `data_source_identifiers`: list of unique IDs of the data sources associated with the conversation - `data_source_names`: array of `{ id, name }` objects for the data sources associated with the conversation - `is_pinned`: whether the current user has pinned this conversation. Pinned conversations are surfaced first in the list. Available from version 26.10.0.cl. - `analyst_id`: unique identifier of the Spotter Analyst the conversation is associated with, or `null` when the conversation is not associated with an analyst. Available from version 26.10.0.cl. #### Pagination Use `limit` and `offset` to page through large result sets: ``` GET /api/rest/2.0/ai/agent/conversations?limit=20&offset=0 → first page GET /api/rest/2.0/ai/agent/conversations?limit=20&offset=20 → second page ``` #### Pagination and `has_more` The response includes a `has_more: Boolean` field. When `true`, there are additional conversations beyond the current page — increment `offset` by `limit` to fetch the next page. When `has_more` is `false`, the current page is the last. Note that `total_count` is not returned; use `has_more` to drive paging controls. #### Example response ```json { \"conversations\": [ { \"conversation_identifier\": \"abc123\", \"conversation_title\": \"Sales by Region Q1\", \"created_at\": \"2026-03-01T10:00:00Z\", \"updated_at\": \"2026-03-05T14:23:00Z\", \"data_source_identifiers\": [\"ds-001\"], \"data_source_names\": [{ \"id\": \"ds-001\", \"name\": \"Retail Sales\" }], \"is_pinned\": true } ], \"has_more\": false } ``` #### Error responses | Code | Description | |------|-------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege. | > ###### Note: > > - Only conversations created with `enable_save_chat: true` appear in this list. Conversations created with `enable_save_chat: false` (the default) are not persisted and cannot be retrieved. > - Available from version 26.7.0.cl and later. > - This endpoint requires Spotter — please contact ThoughtSpot Support to enable Spotter on your cluster. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, GetConversationListRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.getConversationList( // number | Maximum number of conversations to return. Used for pagination. (optional) 30 , // number | Number of conversations to skip before returning results. Used for pagination. (optional) 0 , // boolean | When true, excludes conversations with no messages. Defaults to true. (optional) true ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **limit** | [**number**] | Maximum number of conversations to return. Used for pagination. | (optional) defaults to 30 **offset** | [**number**] | Number of conversations to skip before returning results. Used for pagination. | (optional) defaults to 0 **skipEmpty** | [**boolean**] | When true, excludes conversations with no messages. Defaults to true. | (optional) defaults to true ### Return type **AgentConversationHistoryResponse** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: Not defined - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **getDataSourceSuggestions** > EurekaDataSourceSuggestionResponse getDataSourceSuggestions(getDataSourceSuggestionsRequest) Version: 10.15.0.cl or later Suggests the most relevant data sources for a given natural language query, ranked by confidence with LLM-generated reasoning. Requires `CAN_USE_SPOTTER` privilege and at least view-level access to the underlying metadata entities referenced in the response. #### Usage guidelines The request must include: - `query`: the natural language question to find relevant data sources for If the request is successful, the API returns a ranked list of suggested data sources, each containing: - `confidence`: a float score indicating the model\'s confidence in the relevance of the suggestion - `details`: metadata about the data source - `data_source_identifier`: the unique ID of the data source - `data_source_name`: the display name of the data source - `description`: a description of the data source - `reasoning`: LLM-generated rationale explaining why the data source was recommended #### Error responses | Code | Description | |------|--------------------------------------------------------------------------------------------------------------------------------------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege or lacks view permission on the underlying metadata entities. | > ###### Note: > * This endpoint is currently in Beta. Breaking changes may be introduced before it is made Generally Available. > * This endpoint requires Spotter — please contact ThoughtSpot Support to enable Spotter on your cluster. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, GetDataSourceSuggestionsRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.getDataSourceSuggestions( // GetDataSourceSuggestionsRequest { query: "query_example", } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **getDataSourceSuggestionsRequest** | **GetDataSourceSuggestionsRequest**| | ### Return type **EurekaDataSourceSuggestionResponse** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **getNLInstructions** > EurekaGetNLInstructionsResponse getNLInstructions(getNLInstructionsRequest) Version: 10.15.0.cl or later Retrieves existing natural language (NL) instructions configured for a specific data model. These instructions guide the AI system in understanding data context and generating more accurate responses. Requires `CAN_USE_SPOTTER` privilege, at least view access on the data model, and a bearer token corresponding to the org where the data model exists. #### Usage guidelines The request must include: - `data_source_identifier`: the unique ID of the data model to retrieve instructions for If the request is successful, the API returns: - `nl_instructions_info`: an array of instruction objects, each containing: - `instructions`: the configured text instructions for AI processing - `scope`: the scope of the instruction — currently only `GLOBAL` is supported #### Instructions scope - **GLOBAL**: Instructions that apply globally across the system on the given data-model (currently only global instructions are supported) #### Error responses | Code | Description | |------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege, lacks view access on the data model, or the bearer token does not correspond to the org where the data model exists. | > ###### Note: > > - To use this API, the user needs at least view access on the data model, and must use the bearer token corresponding to the org where the data model exists. > - This endpoint is currently in Beta. Breaking changes may be introduced before the endpoint is made Generally Available. > - Available from version 10.15.0.cl and later. > - This endpoint requires Spotter — please contact ThoughtSpot Support to enable Spotter on your cluster. > - Use this API to review currently configured instructions before modifying them with `setNLInstructions`. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, GetNLInstructionsRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.getNLInstructions( // GetNLInstructionsRequest { data_source_identifier: "data_source_identifier_example", } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **getNLInstructionsRequest** | **GetNLInstructionsRequest**| | ### Return type **EurekaGetNLInstructionsResponse** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **getRelevantQuestions** > EurekaGetRelevantQuestionsResponse getRelevantQuestions(getRelevantQuestionsRequest) Version: 10.13.0.cl or later Breaks down a natural language query into a series of smaller analytical sub-questions, each mapped to a relevant data source. Requires `CAN_USE_SPOTTER` privilege and at least view-level access to the referenced metadata objects. #### Usage guidelines The request must include: - `query`: the natural language question to decompose into analytical sub-questions - `metadata_context`: at least one of the following context identifiers to guide question generation: - `conversation_identifier` — an existing conversation session ID - `answer_identifiers` — a list of Answer GUIDs - `liveboard_identifiers` — a list of Liveboard GUIDs - `data_source_identifiers` — a list of data source GUIDs Optional parameters for refining the output: - `ai_context`: additional context to improve response quality - `content` — supplementary text or CSV data as string input - `instructions` — custom text instructions for the AI system - `limit_relevant_questions`: maximum number of questions to return (default: `5`) - `bypass_cache`: if `true`, forces fresh computation instead of returning cached results If the request is successful, the API returns a list of relevant analytical questions, each containing: - `query`: the generated sub-question - `data_source_identifier`: the unique ID of the data source the question targets - `data_source_name`: the display name of the corresponding data source #### Error responses | Code | Description | |------|---------------------------------------------------------------------------------------------------------------------------------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege or lacks view access to the referenced metadata objects. | > ###### Note: > * This endpoint is currently in Beta. Breaking changes may be introduced before the endpoint is made Generally Available. > * This endpoint requires Spotter - please contact ThoughtSpot support to enable Spotter on your cluster. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, GetRelevantQuestionsRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.getRelevantQuestions( // GetRelevantQuestionsRequest { metadata_context: null, limit_relevant_questions: 1, bypass_cache: true, query: "query_example", ai_context: null, } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **getRelevantQuestionsRequest** | **GetRelevantQuestionsRequest**| | ### Return type **EurekaGetRelevantQuestionsResponse** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **getShareInfo** > ConversationShareStatusResponse getShareInfo() Returns the current share state for a conversation the caller owns: whether the shared view is outdated relative to the latest conversation content, and the list of principals that currently have access. Requires `CAN_USE_SPOTTER` privilege and ownership of the specified conversation. Version: 26.9.0.cl or later ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, GetShareInfoRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.getShareInfo( // string | Unique identifier of the conversation. "conversation_identifier_example" ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **conversationIdentifier** | [**string**] | Unique identifier of the conversation. | defaults to undefined ### Return type **ConversationShareStatusResponse** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: Not defined - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **getSharedContent** > SharedConversationResponse getSharedContent() Returns the full read-only view of a shared conversation, including ordered messages and data source metadata. Accessible by the conversation owner and any principal (user or group) that has been granted access. Requires `CAN_USE_SPOTTER` privilege. Version: 26.9.0.cl or later ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, GetSharedContentRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.getSharedContent( // string | Unique identifier of the source conversation. "conversation_identifier_example" ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **conversationIdentifier** | [**string**] | Unique identifier of the source conversation. | defaults to undefined ### Return type **SharedConversationResponse** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: Not defined - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **importMemory** > ImportMemoryResponse importMemory(importMemoryRequest) Imports memory entries (rules, recipes, and always-apply rules) from a YAML payload, typically a payload produced by `exportMemory` and edited locally. The imported entries replace the existing memory for the data-models referenced in the payload. `dry_run` is required. Pass `true` first to validate the payload and review the preview counts and any row-level failures without making changes, then re-run with `dry_run = false` to apply the import. An import is not applied if any row fails validation. Requires Spotter access (use/manage) and either edit or memory access on corresponding data model sources. Version: 26.8.0.cl or later This API allows users to import data-model memories using a given yaml file. This yaml file can be obtained from the export memory API in source env and can be modified and used as input to the import API in target env. This API enables customers to migrate memories from a source env to a target env. This improves memory adoption for Spotter by giving the users a chance to develop their memories in one env and replicate the same in another env. #### Usage guidelines To import memory, the request must include: - `content`: The full serialized memory payload to import (YAML). Typically the `content` value returned by the `exportMemory` API, edited locally and re-submitted. The payload itself identifies which data-models the memory applies to, so no separate identifier list is required. - `dry_run`: Required. When `true`, validate the payload and return preview counts without writing anything; when `false`, apply the import. Always run with `dry_run = true` first, then re-run with `dry_run = false` once you are satisfied with the preview. The import replaces the existing global memories on the data-models referenced in the payload with the entries supplied in the payload. The API returns a response object with: - `status`: The terminal status of the import (`SUCCESS`, `VALIDATION_FAILED`, or `FAILED`). - `summary`: Per `(memory_type, source)` counts. In a dry run the `deleted_record_count`/`inserted_record_count` are previews; in a real import they are actuals. On `VALIDATION_FAILED`, `summary` is `null` when validation fails before any item is processed (e.g. an unresolved or inaccessible data-model source) and an empty list otherwise — treat both as \"no counts available\". - `validation_failures`: Per-item validation failures, each with `line_number`, `reason`, `field_name`, and `message` for click-to-locate and inline highlighting. - `diagnostics`: Groups of diagnostic messages, each with a `sub_status` (`WARNING`, `FAILURE`, `ROLLED_BACK`, or `UNKNOWN`) and a `messages` list. This is the single channel for both non-fatal warnings (under `WARNING`, e.g. when some older memory entries could not be fully cleaned up) and fatal causes (e.g. the failure reason under `FAILURE`, or a `ROLLED_BACK` group when new entries were undone). - `operation_id`: A server-generated identifier for this import operation; include it when contacting support to help correlate server-side logs. Populated once the server registers the import operation; `null` when the request fails earlier (e.g. while parsing the payload or resolving its data-model sources). #### File format The payload is a YAML document with a single top-level `memories` key holding a list of memory items. Each item is self-contained: a `type`, a typed `content` block, a `datamodel_sources` list, and optional `tags`. Typically you don\'t hand-author this file — you obtain it from `exportMemory`, edit it, and submit it back through `importMemory`. ```yaml memories: - type: RULE content: rule_definition: \"Always filter revenue to closed-won deals.\" datamodel_sources: - guid: 11111111-1111-1111-1111-111111111111 obj_id: sales_data_model tags: - finance - type: RULE content: rule_definition: \"Exclude internal test accounts from all results.\" datamodel_sources: - obj_id: sales_data_model - type: RECIPE content: user_query: \"top accounts by revenue\" recipe: | {\"steps\": [...serialized recipe blob...]} datamodel_sources: - obj_id: sales_data_model - type: RECIPE content: user_query: \"monthly new customer count\" recipe: | {\"steps\": [...serialized recipe blob...]} datamodel_sources: - obj_id: sales_data_model - type: ALWAYS_APPLY_RULES content: rules: - \"Never show internal test accounts.\" - \"Round currency to whole dollars.\" datamodel_sources: - guid: 22222222-2222-2222-2222-222222222222 ``` A file can contain multiple `RULE` and multiple `RECIPE` items for a data-model, but at most one `ALWAYS_APPLY_RULES` item per data-model. ##### Memory item fields | Field | Required | Type | Description | |-------|----------|------|-------------| | `type` | Yes | String enum | One of `RULE`, `RECIPE`, or `ALWAYS_APPLY_RULES`. | | `content` | Yes | Mapping | Type-specific content block (see below). | | `datamodel_sources` | Yes | Non-empty list | The data-model(s) the memory attaches to. | | `tags` | No | List of strings | Free-form labels. | ##### Memory types and content | `type` | Content fields | Notes | |--------|----------------|-------| | `RULE` | `rule_definition` — required, non-empty string | A single semantic rule. | | `RECIPE` | `recipe` and `user_query` — both required, non-empty strings | `recipe` is an opaque serialized blob; `user_query` is the natural-language query it answers. | | `ALWAYS_APPLY_RULES` | `rules` — required, non-empty list of non-empty strings | Data-model-wide always-apply rules. At most one `ALWAYS_APPLY_RULES` item per data-model. | ##### Identifying data-models (`datamodel_sources`) Each item must list at least one source. Each entry identifies a data-model by at least one of: - `guid` — the data-model GUID. - `obj_id` — a stable object ID, resolved to a GUID server-side. If both are supplied, `obj_id` takes precedence and `guid` is ignored entirely; `guid` takes effect only when `obj_id` is absent. Exported files populate `guid` and, if present, `obj_id` as well. > ⚠️ **Cross-environment import:** When `obj_id` is present it is > authoritative — the accompanying `guid` is **not** used as a fallback. > If an `obj_id` does not exist in the target environment, that item > fails with `UNRESOLVED_SOURCE`. Remove or correct stale `obj_id` > values before importing across environments. #### Validations reference The payload is fully validated before anything is written. This applies to `dry_run = true` and `dry_run = false` alike: if any item fails validation, the entire import is rejected — no partial writes — and all failures are returned together so you can fix them in one pass. ##### Limits Default limits (may be adjusted in future if the need arises): | Limit | Default | |-------|---------| | Uploaded file size | 10 MiB | | Total memory items | 10,000 | | `rule_definition` length | 1,000 characters | | `user_query` length | 1,000 characters | | `recipe` length | 2,000 characters | | `rules` combined length (`ALWAYS_APPLY_RULES`) | 2,000 characters | | Tags per item | 10 | | Characters per tag | 50 | The `rules` limit in `ALWAYS_APPLY_RULES` is a combined budget across all entries in the list, not per entry. ##### Structural rules - The document must be a mapping with a `memories` key whose value is a list. - Unknown keys — at the top level, within an item, or under `content` — are rejected. - Each item\'s `type` must be one of the three supported values, and `content` must match that type\'s shape. - Null, empty-string, or wrong-typed values in a required field are treated as missing. - Non-string or empty `tags` entries are dropped silently; certain tags reserved for internal use are stripped automatically before the item is stored. ##### Cross-item rules - A data-model referenced by more than one `ALWAYS_APPLY_RULES` item is rejected — combine them into a single item\'s `rules` list. ##### Failure reasons Each entry in `validation_failures` carries one of: | Reason | Meaning | |--------|---------| | `SCHEMA` | YAML structure is invalid or unsupported. | | `VALIDATION` | A required field is missing/empty, a count exceeds a limit, or a GUID is malformed. | | `CHAR_LIMIT` | A content field or tag exceeds its size limit. | | `UNRESOLVED_SOURCE` | A `guid` or `obj_id` could not be resolved to an existing data-model. | | `ACCESS_DENIED` | The caller lacks sufficient access on the referenced data-model. | #### Dry run `dry_run` is required and has no default, so the import is always a deliberate two-step flow: 1. **First, call with `dry_run = true`.** This validates the payload and previews what would happen — the counts in `summary` and any `validation_failures` — without writing anything. 2. **Then, after reviewing a clean preview, call again with `dry_run = false`** (same `content`). This applies the import. It refuses to write when any item fails validation, so fix the reported `validation_failures` and resubmit. > ###### Important: > Never call `dry_run = false` without first inspecting a `dry_run = true` preview. A real import deletes and replaces existing global memories on the referenced data-models. #### Error responses | Code | Description | |------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have the necessary Spotter permissions, or the bearer token does not correspond to the data-model\'s org. Per-data-model access failures do not use this code — they surface as `ACCESS_DENIED` validation failures with HTTP `200` (see Logical failures below). | #### Logical failures Validation and write failures are not returned in the error envelope. The call returns `200` with a terminal `status` of `VALIDATION_FAILED` or `FAILED`, and the details live in `validation_failures` / `diagnostics`: - **VALIDATION_FAILED** — one or more items failed schema/semantic validation; nothing was written. Inspect `validation_failures`, fix the items, and resubmit. - **FAILED** — the import did not complete. Inspect `diagnostics`: a `ROLLED_BACK` group means writing the new entries failed and any entries written before the failure were undone (existing memory is intact, no destructive change), while a `FAILURE` group carries another non-validation cause. Sample `VALIDATION_FAILED` responses (HTTP 200): **Invalid data-model (unresolved source):** ```json { \"status\": \"VALIDATION_FAILED\", \"summary\": null, \"validation_failures\": [ { \"line_number\": 2, \"reason\": \"UNRESOLVED_SOURCE\", \"field_name\": \"datamodel_sources[0].guid\", \"message\": \"unknown datamodel guid: 55555555-5555-5555-5555-555555555555\" } ], \"diagnostics\": [ { \"sub_status\": \"FAILURE\", \"messages\": [ \"unknown datamodel guid: 55555555-5555-5555-5555-555555555555\" ] } ], \"operation_id\": null } ``` **Inaccessible data-models:** ```json { \"status\": \"VALIDATION_FAILED\", \"summary\": null, \"validation_failures\": [ { \"line_number\": 2, \"reason\": \"ACCESS_DENIED\", \"field_name\": \"datamodel_sources[0]\", \"message\": \"Insufficient permissions on datamodel \'44444444-4444-4444-4444-444444444444\'\" }, { \"line_number\": 8, \"reason\": \"ACCESS_DENIED\", \"field_name\": \"datamodel_sources[0]\", \"message\": \"Insufficient permissions on datamodel \'33333333-3333-3333-3333-333333333333\'\" } ], \"diagnostics\": [ { \"sub_status\": \"FAILURE\", \"messages\": [ \"Memory import validation failed with 2 error(s): Insufficient permissions on datamodel \'44444444-4444-4444-4444-444444444444\'; Insufficient permissions on datamodel \'33333333-3333-3333-3333-333333333333\'\" ] } ], \"operation_id\": null } ``` **Character-limit validations:** ```json { \"status\": \"VALIDATION_FAILED\", \"summary\": [], \"validation_failures\": [ { \"line_number\": 3, \"reason\": \"CHAR_LIMIT\", \"field_name\": \"content.rule_definition\", \"message\": \"content.rule_definition is 1073 characters; max allowed is 1000\" }, { \"line_number\": 49, \"reason\": \"CHAR_LIMIT\", \"field_name\": \"content.user_query\", \"message\": \"content.user_query is 1150 characters; max allowed is 1000\" }, { \"line_number\": 49, \"reason\": \"CHAR_LIMIT\", \"field_name\": \"content.recipe\", \"message\": \"content.recipe is 3574 characters; max allowed is 2000\" } ], \"diagnostics\": [ { \"sub_status\": \"FAILURE\", \"messages\": [ \"Validation failures present; fix them and re-run to see the DRY_RUN preview.\" ] } ], \"operation_id\": \"66666666-6666-6666-6666-666666666666\" } ``` > ###### Note: > - To use this API, the user needs Spotter access (use/manage) and either edit or memory access on the data-model and they must use corresponding org related bearerToken where the data-model exists. > - This endpoint is currently in Beta. Breaking changes may be introduced before the endpoint is made Generally Available. > - Available from version 26.8.0.cl and later. > - This endpoint requires Spotter — please contact ThoughtSpot Support to enable Spotter on your cluster. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, ImportMemoryRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.importMemory( // ImportMemoryRequest { content: "content_example", dry_run: true, } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **importMemoryRequest** | **ImportMemoryRequest**| | ### Return type **ImportMemoryResponse** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **loadAnswer** > LoadAnswerResponse loadAnswer() Loads the full answer payload for a specific answer item in an agent conversation. Returns structured answer data including the TML query, token breakdown, visualization metadata, and agent context state. Pass the `answer_id` from an `AnswerResponseItem` in the `getConversation` response as the `answer_identifier` parameter. Requires `CAN_USE_SPOTTER` privilege and access to the specified conversation. Version: 26.7.0.cl or later Loads the answer details for a specific answer item in an agent conversation. Returns structured answer data including the TML token list, visualization metadata, and agent context state. Use this endpoint to retrieve the full answer representation for an answer item — for example, to re-render a chart, export a query, or inspect the generated TML. Requires `CAN_USE_SPOTTER` privilege and access to the specified conversation. #### Usage guidelines The request must include: - `conversation_identifier` *(path parameter)*: the unique ID of the conversation, as returned by `createAgentConversation` - `answer_identifier` *(path parameter)*: the `answer_id` field from an `AnswerResponseItem` in the `getConversation` response If the request is successful, the response contains an `answer` object with the following fields: | Field | Type | Description | |-------|------|-------------| | `title` | `String` | Display title of the generated answer (e.g., `\"sales by month\"`). | | `description` | `String` | Optional description of the answer. | | `session_identifier` | `String` | Unique identifier of the session in which this answer was generated. | | `generation_number` | `Int` | Generation sequence number of this answer within the session. | | `tokens` | `[String]` | Ordered list of TML token strings that make up the answer query (e.g., `[\"[sales]\", \"[date].\'monthly\'\"]`). | | `visualization_type` | `VizType` | Suggested visualization type: `Chart`, `Table`, or `Undefined`. `null` if no suggestion is available. | | `formulas` | `[String]` | List of formula names referenced in the answer. Empty if none are used. | | `parameters` | `[String]` | List of parameter names applied to the answer. Empty if none are used. | | `sub_queries` | `[JSON]` | List of sub-query objects used in the answer. Empty if none are present. | | `ac_state` | `ACState` | Agent context state, including `transaction_identifier` and `generation_number`, used to correlate this answer with a specific agent turn. | #### ACState fields | Field | Type | Description | |-------|------|-------------| | `transaction_identifier` | `String` | Unique identifier of the agent transaction that produced this answer. | | `generation_number` | `Int` | Generation number within the transaction. | #### Example request ```bash GET /api/rest/2.0/ai/agent/conversations/{conversation_identifier}/answers/{answer_identifier}/details ``` #### Example response ```json { \"answer\": { \"title\": \"sales by month\", \"description\": \"\", \"session_identifier\": \"7b00b801-73f4-4639-af5e-e775584ceba6\", \"generation_number\": 1, \"tokens\": [\"[sales]\", \"[date].\'monthly\'\"], \"visualization_type\": null, \"formulas\": [], \"parameters\": [], \"sub_queries\": [], \"ac_state\": { \"transaction_identifier\": \"7f6c9948-b4c7-4098-bb1f-6c67bc0e5699\", \"generation_number\": 1 } } } ``` #### Typical usage scenario 1. Call `getConversation` to retrieve the full conversation history. 2. Locate an `AnswerResponseItem` in `response_items` — note its `answer_id` field. 3. Call `loadAnswer` with the `conversation_identifier` and `answer_id` as `answer_identifier`. 4. The returned `tokens` array can be used to open the answer in the ThoughtSpot search interface or rendered as pill chips in the UI. #### Error responses | Code | Description | |------|-------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege or lacks access to the specified conversation. | | 404 | Not Found — no conversation or message exists with the given identifiers for the authenticated user. | | 422 | Unprocessable Entity — the message does not contain an answer of the expected type. | > ###### Note: > > - This endpoint only loads answer-type messages. Other message types are not supported. > - `visualization_type` may be `null` if the agent did not produce a visualization suggestion for this answer. > - `formulas`, `parameters`, and `sub_queries` are returned as empty arrays when not applicable — they are never `null`. > - Available from version 26.7.0.cl and later. > - This endpoint requires Spotter — please contact ThoughtSpot Support to enable Spotter on your cluster. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, LoadAnswerRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.loadAnswer( // string | Unique identifier of the conversation. "conversation_identifier_example" , // string | Unique identifier of the answer to load. Use the `answer_id` field from an `AnswerResponseItem` returned by `getConversation`. "answer_identifier_example" ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **conversationIdentifier** | [**string**] | Unique identifier of the conversation. | defaults to undefined **answerIdentifier** | [**string**] | Unique identifier of the answer to load. Use the `answer_id` field from an `AnswerResponseItem` returned by `getConversation`. | defaults to undefined ### Return type **LoadAnswerResponse** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: Not defined - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **queryGetDecomposedQuery** > EurekaDecomposeQueryResponse queryGetDecomposedQuery(queryGetDecomposedQueryRequest) Version: 10.7.0.cl or later **Deprecated** — Use `getRelevantQuestions` instead (available from 10.13.0.cl). Breaks down a topical or goal-oriented natural language question into smaller, actionable analytical sub-questions, each mapped to a relevant data source for independent execution. Requires `CAN_USE_SPOTTER` privilege and at least view-level access to the referenced metadata objects. #### Usage guidelines The request accepts the following parameters: - `nlsRequest`: contains the user `query` to decompose, along with optional `instructions` and `bypassCache` flag - `worksheetIds`: list of data source identifiers to scope the decomposition - `answerIds`: list of Answer GUIDs whose data guides the response - `liveboardIds`: list of Liveboard GUIDs whose data guides the response - `conversationId`: an existing conversation session ID for context continuity - `content`: supplementary text or CSV data to improve response quality - `maxDecomposedQueries`: maximum number of sub-questions to return (default: `5`) If the request is successful, the API returns a `decomposedQueryResponse` containing a list of `decomposedQueries`, each with: - `query`: the generated analytical sub-question - `worksheetId`: the unique ID of the data source the question targets - `worksheetName`: the display name of the corresponding data source #### Error responses | Code | Description | |------|---------------------------------------------------------------------------------------------------------------------------------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege or lacks view access to the referenced metadata objects. | > ###### Note: > * This endpoint is deprecated since 10.13.0.cl. Use `getRelevantQuestions` for new integrations. > * This endpoint is currently in Beta. Breaking changes may be introduced before the endpoint is made Generally Available. > * This endpoint requires Spotter — please contact ThoughtSpot support to enable Spotter on your cluster. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, QueryGetDecomposedQueryRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.queryGetDecomposedQuery( // QueryGetDecomposedQueryRequest { answerIds: [ "answerIds_example", ], content: [ "content_example", ], conversationId: "conversationId_example", liveboardIds: [ "liveboardIds_example", ], maxDecomposedQueries: 1, nlsRequest: null, worksheetIds: [ "worksheetIds_example", ], } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **queryGetDecomposedQueryRequest** | **QueryGetDecomposedQueryRequest**| | ### Return type **EurekaDecomposeQueryResponse** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **searchAnalysts** > AnalystSearchResponse searchAnalysts(searchAnalystsRequest) Searches Spotter Analysts. Two modes: - Fetch mode: when `analyst_identifier` is provided, the response contains exactly that analyst and all other filters are ignored. - List mode: returns a paginated list of analysts visible to the caller, optionally filtered by a case-insensitive substring match on the analyst name (`query`) and by ownership (`type`). Results are ordered by most recently accessed. Requires at least one of `ADMINISTRATION`, `CAN_MANAGE_SPOTTER`, or `CAN_USE_SPOTTER` privileges. Version: 26.10.0.cl or later Searches Spotter Analysts. Use this endpoint to page through the analysts visible to you, or to fetch a single analyst by its identifier. Requires at least one of `ADMINISTRATION`, `CAN_MANAGE_SPOTTER`, or `CAN_USE_SPOTTER` privileges. Use a bearer token for the Org whose analysts should be searched. #### Usage guidelines The endpoint operates in one of two modes: **Fetch mode** — when `analyst_identifier` is provided, the response contains exactly that analyst (`total_size` is 1) and all other filters are ignored. The caller must have access to the analyst (owner, shared with, or admin/Spotter-management privileges). **List mode** — when `analyst_identifier` is omitted, the response is a paginated list of analysts the caller can see, ordered by most recently accessed: - `record_size` (optional): number of records per page. Default 50, between 1 and 500. - `record_offset` (optional): zero-based index of the first record. Default 0, maximum 10000. - `query` (optional): case-insensitive substring match applied to the analyst **name only**. - `type` (optional): ownership filter — `ALL` (default; created by or shared with me), `CREATED_BY_ME`, or `SHARED_TO_ME`. The response contains `analysts` — the page of matching analysts — and `total_size`, the total number of matches before pagination. Each analyst includes its `id`, `name`, `description`, `instructions`, `sources` (with `id`, `type`, and display `name`), enriched `mcp_connectors` (with `id`, `name`, and `icon_url`), `icon_id`, `starter_prompts` (including the server-managed fixed prompt, marked `is_fixed`), `updated_time_in_millis` and `last_accessed_time_in_millis` (epoch milliseconds), and `created_by` / `updated_by` user references (with `id`, `name`, and `display_name`). #### Error conditions - `403` — missing privileges, or (fetch mode) no access to the requested analyst. - `404` — (fetch mode) no analyst with the given identifier exists in the caller\'s Org. - `422` — validation failure, such as `record_size` or `record_offset` out of range. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, SearchAnalystsRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.searchAnalysts( // SearchAnalystsRequest { analyst_identifier: "analyst_identifier_example", record_size: 50, record_offset: 0, query: "query_example", type: "ALL", } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **searchAnalystsRequest** | **SearchAnalystsRequest**| | ### Return type **AnalystSearchResponse** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **sendAgentConversationMessage** > any sendAgentConversationMessage(sendAgentConversationMessageRequest) Version: 26.5.0.cl or later Sends natural language messages to an existing Spotter agent conversation and returns the complete response synchronously. Requires `CAN_USE_SPOTTER` privilege and access to the metadata object associated with the conversation. The user must have access to the conversation session referenced by `conversation_identifier`. A conversation must first be created using the `createAgentConversation` API. #### Usage guidelines The request must include: - `conversation_identifier`: the unique session ID returned by `createAgentConversation`, used for context continuity and message tracking - `messages`: an array of one or more text messages to send to the agent The API returns an array of response objects, each containing: - `type`: the kind of response — `text`, `answer`, or `error` - `message`: the main content of the response - `metadata`: additional information depending on the message type (e.g., answer metadata includes analytics and visualization details) #### Error responses | Code | Description | |------|----------------------------------------------------------------------------------------------------------------------------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege or lacks permission on the referenced conversation. | > ###### Note: > > - This endpoint is Generally Available from version 26.5.0.cl. > - This endpoint requires Spotter - please contact ThoughtSpot support to enable Spotter on your cluster. > - For real-time streamed responses, use `sendAgentConversationMessageStreaming` instead. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, SendAgentConversationMessageRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.sendAgentConversationMessage( // string | Unique identifier for the conversation (used to track context) "conversation_identifier_example" , // SendAgentConversationMessageRequest { messages: [ "messages_example", ], } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **sendAgentConversationMessageRequest** | **SendAgentConversationMessageRequest**| | **conversationIdentifier** | [**string**] | Unique identifier for the conversation (used to track context) | defaults to undefined ### Return type **any** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **sendAgentConversationMessageStreaming** > SendAgentMessageResponse sendAgentConversationMessageStreaming(sendAgentConversationMessageStreamingRequest) Version: 26.5.0.cl or later Sends one or more natural language messages to an existing Spotter agent conversation and returns the response as a real-time Server-Sent Events stream. Requires `CAN_USE_SPOTTER` privilege and access to the metadata object associated with the conversation. The user must have access to the conversation session referenced by `conversation_identifier`. A conversation must first be created using the `createAgentConversation` API. #### Usage guidelines The request must include: - `conversation_identifier`: the unique session ID returned by `createAgentConversation`, used for context continuity and message tracking - `messages`: an array of one or more text messages to send to the agent If the request is valid, the API returns a Server-Sent Events (SSE) stream. Each line has the form `data: [{\"type\": \"...\", ...}]` — a JSON array of event objects. Event types include: - `ack`: confirms receipt of the request (`node_id`) - `conv_title`: conversation title (`title`, `conv_id`) - `notification`: status updates on operations (`group_id`, `metadata`, `code` — e.g. `TOOL_CALL_NOTIFICATION`, `nls_start`, `FINAL_RESPONSE_NOTIFICATION`) - `text-chunk`: incremental content chunks (`id`, `group_id`, `metadata` with `format` and `type` such as `thinking` or `text`, `content`) - `text`: full text block with same structure as `text-chunk` - `answer`: structured answer with metadata (`id`, `group_id`, `metadata` with `sage_query`, `session_id`, `title`, etc., `title`) - `error`: if a failure occurs #### Error responses | Code | Description | | ---- | -------------------------------------------------------------------------------------------------------------------------------- | | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege or lacks permission on the referenced conversation. | > ###### Note: > > - This endpoint is Generally Available from version 26.5.0.cl. > - This endpoint requires Spotter - please contact ThoughtSpot support to enable Spotter on your cluster. > - The streaming protocol uses Server-Sent Events (SSE). > - For the complete response in a single payload, use `sendAgentConversationMessage` instead. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, SendAgentConversationMessageStreamingRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.sendAgentConversationMessageStreaming( // string | Unique identifier for the conversation (used to track context) "conversation_identifier_example" , // SendAgentConversationMessageStreamingRequest { messages: [ "messages_example", ], } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **sendAgentConversationMessageStreamingRequest** | **SendAgentConversationMessageStreamingRequest**| | **conversationIdentifier** | [**string**] | Unique identifier for the conversation (used to track context) | defaults to undefined ### Return type **SendAgentMessageResponse** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **sendAgentMessage** > any sendAgentMessage(sendAgentMessageRequest) Version: 26.2.0.cl or later **Deprecated** — Use `sendAgentConversationMessage` instead. Send natural language messages to an existing Spotter agent conversation and returns the complete response synchronously. Requires `CAN_USE_SPOTTER` privilege and access to the metadata object associated with the conversation. The user must have access to the conversation session referenced by `conversation_identifier`. A conversation must first be created using the `createAgentConversation` API. #### Usage guidelines The request must include: - `conversation_identifier`: the unique session ID returned by `createAgentConversation`, used for context continuity and message tracking - `messages`: an array of one or more text messages to send to the agent The API returns an array of response objects, each containing: - `type`: the kind of response — `text`, `answer`, or `error` - `message`: the main content of the response - `metadata`: additional information depending on the message type (e.g., answer metadata includes analytics and visualization details) #### Error responses | Code | Description | |------|----------------------------------------------------------------------------------------------------------------------------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege or lacks permission on the referenced conversation. | > ###### Note: > > - This endpoint is deprecated. Use `sendAgentConversationMessage` for new integrations. > - This endpoint is currently in Beta. Breaking changes may be introduced before the endpoint is made Generally Available. > - This endpoint requires Spotter - please contact ThoughtSpot support to enable Spotter on your cluster. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, SendAgentMessageRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.sendAgentMessage( // string | Unique identifier for the conversation (used to track context) "conversation_identifier_example" , // SendAgentMessageRequest { messages: [ "messages_example", ], } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **sendAgentMessageRequest** | **SendAgentMessageRequest**| | **conversationIdentifier** | [**string**] | Unique identifier for the conversation (used to track context) | defaults to undefined ### Return type **any** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **sendAgentMessageStreaming** > SendAgentMessageResponse sendAgentMessageStreaming(sendAgentMessageStreamingRequest) Version: 26.2.0.cl or later **Deprecated** — Use `sendAgentConversationMessageStreaming` instead. Sends one or more natural language messages to an existing Spotter agent conversation and returns the response as a real-time Server-Sent Events stream. Requires `CAN_USE_SPOTTER` privilege and access to the metadata object associated with the conversation. The user must have access to the conversation session referenced by `conversation_identifier`. A conversation must first be created using the `createAgentConversation` API. #### Usage guidelines The request must include: - `conversation_identifier`: the unique session ID returned by `createAgentConversation`, used for context continuity and message tracking - `messages`: an array of one or more text messages to send to the agent If the request is valid, the API returns a Server-Sent Events (SSE) stream. Each line has the form `data: [{\"type\": \"...\", ...}]` — a JSON array of event objects. Event types include: - `ack`: confirms receipt of the request (`node_id`) - `conv_title`: conversation title (`title`, `conv_id`) - `notification`: status updates on operations (`group_id`, `metadata`, `code` — e.g. `TOOL_CALL_NOTIFICATION`, `nls_start`, `FINAL_RESPONSE_NOTIFICATION`) - `text-chunk`: incremental content chunks (`id`, `group_id`, `metadata` with `format` and `type` such as `thinking` or `text`, `content`) - `text`: full text block with same structure as `text-chunk` - `answer`: structured answer with metadata (`id`, `group_id`, `metadata` with `sage_query`, `session_id`, `title`, etc., `title`) - `error`: if a failure occurs #### Error responses | Code | Description | |------|----------------------------------------------------------------------------------------------------------------------------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege or lacks permission on the referenced conversation. | > ###### Note: > > - This endpoint is deprecated. Use `sendAgentConversationMessageStreaming` for new integrations. > - This endpoint is currently in Beta. Breaking changes may be introduced before the endpoint is made Generally Available. > - This endpoint requires Spotter - please contact ThoughtSpot support to enable Spotter on your cluster. > - The streaming protocol uses Server-Sent Events (SSE). ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, SendAgentMessageStreamingRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.sendAgentMessageStreaming( // SendAgentMessageStreamingRequest { conversation_identifier: "conversation_identifier_example", messages: [ "messages_example", ], } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **sendAgentMessageStreamingRequest** | **SendAgentMessageStreamingRequest**| | ### Return type **SendAgentMessageResponse** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **sendMessage** > Array sendMessage(sendMessageRequest) Version: 10.4.0.cl or later Sends a follow-up message to an existing conversation within the context of a data model. Requires `CAN_USE_SPOTTER` privilege and at least view access to the metadata object specified in the request. A conversation must first be created using the `createConversation` API. #### Usage guidelines The request must include: - `conversation_identifier`: the unique session ID returned by `createConversation` - `metadata_identifier`: the unique ID of the data source used for the conversation - `message`: a natural language string with the follow-up question If the request is successful, the API returns an array of response messages, each containing: - `session_identifier`: the unique ID of the generated response - `generation_number`: the generation number of the response - `message_type`: the type of the response (e.g., `TSAnswer`) - `visualization_type`: the generated visualization type (`Chart`, `Table`, or `Undefined`) - `tokens` / `display_tokens`: the search tokens and user-friendly display tokens for the response #### Error responses | Code | Description | |------|-----------------------------------------------------------------------------------------------------------------------------------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege or lacks view permission on the specified metadata object. | > ###### Note: > * This endpoint is currently in Beta. Breaking changes may be introduced before the endpoint is made Generally Available. > * This endpoint requires Spotter - please contact ThoughtSpot support to enable Spotter on your cluster. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, SendMessageRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.sendMessage( // string | Unique identifier of the conversation. "conversation_identifier_example" , // SendMessageRequest { metadata_identifier: "metadata_identifier_example", message: "message_example", } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **sendMessageRequest** | **SendMessageRequest**| | **conversationIdentifier** | [**string**] | Unique identifier of the conversation. | defaults to undefined ### Return type **Array** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **setAgentInstructions** > AgentInstructions setAgentInstructions(setAgentInstructionsRequest) Version: 26.6.0.cl or later Creates or updates the admin instructions for the AI agent (Spotter). Admin instructions are tenant- and org-scoped text that guide agent behavior across all conversations. If instructions already exist for the org, they are replaced (upsert semantics). Requires admin privileges. Only users with org admin access can set agent instructions. #### Usage guidelines The request must include: - `instructions`: the instructions text to apply to the agent (maximum 5000 characters) Instructions are validated against system guardrails before being saved. If the instructions contain content that conflicts with guardrails, the request is rejected with a `409` error and the existing instructions remain unchanged. If the request is successful, the response includes the saved `AgentInstructions` record: - `id`: unique identifier of the record - `instructions`: the saved instructions text - `created_at`: ISO timestamp when the instructions were first created - `updated_at`: ISO timestamp of this update - `last_updated_by`: user ID of the admin who performed this update #### Error responses | Code | Description | |------|-------------| | 400 | Bad request — the request body is missing required fields or the `instructions` field exceeds the maximum allowed length of 5000 characters. | | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have org admin privileges required to set agent instructions. | | 409 | Conflict — the provided instructions conflict with system guardrails. Review and revise the instructions text before retrying. | | 500 | Internal server error. | > ###### Note: > > - This operation uses upsert semantics: it creates the instructions record if none exists, or replaces the existing one. > - Instructions take effect immediately for new conversations created after the update. > - Use `getAgentInstructions` to retrieve the current instructions before making changes. > - Available from version 26.6.0.cl and later. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, SetAgentInstructionsRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.setAgentInstructions( // SetAgentInstructionsRequest { instructions: "instructions_example", } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **setAgentInstructionsRequest** | **SetAgentInstructionsRequest**| | ### Return type **AgentInstructions** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **setNLInstructions** > EurekaSetNLInstructionsResponse setNLInstructions(setNLInstructionsRequest) Version: 10.15.0.cl or later This API allows users to set natural language (NL) instructions for a specific data-model to improve AI-generated answers and query processing. These instructions help guide the AI system to better understand the data context and provide more accurate responses. Requires `CAN_USE_SPOTTER` privilege, either edit access or `SPOTTER_COACHING_PRIVILEGE` on the data model, and a bearer token corresponding to the org where the data model exists. #### Usage guidelines To set NL instructions for a data-model, the request must include: - `data_source_identifier`: The unique ID of the data-model for which to set NL instructions - `nl_instructions_info`: An array of instruction objects, each containing: - `instructions`: Array of text instructions for the LLM - `scope`: The scope of the instruction (`GLOBAL`). Currently only `GLOBAL` is supported. It can be extended to data-model-user scope in future. #### Instructions scope - **GLOBAL**: instructions that apply to all users querying this data model If the request is successful, the API returns: - `success`: a boolean indicating whether the operation completed successfully #### Error responses | Code | Description | |------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege, lacks edit access or `SPOTTER_COACHING_PRIVILEGE` on the data model, or the bearer token does not correspond to the org where the data model exists. | > ###### Note: > > - To use this API, the user needs either edit access or `SPOTTER_COACHING_PRIVILEGE` on the data model, and must use the bearer token corresponding to the org where the data model exists. > - This endpoint is currently in Beta. Breaking changes may be introduced before the endpoint is made Generally Available. > - Available from version 10.15.0.cl and later. > - This endpoint requires Spotter — please contact ThoughtSpot Support to enable Spotter on your cluster. > - Instructions help improve the accuracy and relevance of AI-generated responses for the specified data-model. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, SetNLInstructionsRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.setNLInstructions( // SetNLInstructionsRequest { data_source_identifier: "data_source_identifier_example", nl_instructions_info: [ { instructions: [ "instructions_example", ], scope: "GLOBAL", }, ], } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **setNLInstructionsRequest** | **SetNLInstructionsRequest**| | ### Return type **EurekaSetNLInstructionsResponse** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **shareAnalyst** > any shareAnalyst(shareAnalystRequest) Updates share permissions on a Spotter Analyst, one entry per principal (user or group). `READ_ONLY` and `MODIFY` grant or change the principal\'s access; `NO_ACCESS` revokes it. Granting access also shares the analyst\'s data sources with the principal so the analyst keeps working for them. A successful share returns an empty `204 No Content` response. Requires ownership of the analyst, or `ADMINISTRATION` or `CAN_MANAGE_SPOTTER` privileges. Version: 26.10.0.cl or later Updates share permissions on a Spotter Analyst for one or more principals (users or groups). Requires ownership of the analyst, or `ADMINISTRATION` or `CAN_MANAGE_SPOTTER` privileges. Use a bearer token for the Org in which the analyst exists. #### Usage guidelines The analyst is identified by the `analyst_identifier` path parameter. The request body contains a `permissions` array with one entry per principal: - `principal.identifier` (required): unique identifier of the user or group. - `principal.type` (required): `USER` or `USER_GROUP`. - `share_mode` (required): `READ_ONLY` or `MODIFY` grants (or changes) the principal\'s access; `NO_ACCESS` revokes it. A principal may appear at most once per request. When access is granted, the analyst\'s data sources are automatically shared with the principal as well, so the analyst keeps working for them. A successful request returns an empty `204 No Content` response. #### Error conditions - `400` — malformed analyst identifier. - `403` — the caller is not the analyst\'s author and lacks admin / Spotter-management privileges. - `404` — no analyst with the given identifier exists in the caller\'s Org. - `422` — validation failure, such as an empty `permissions` array, a duplicate principal, or a missing field. - `429` — rate limit exceeded. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, ShareAnalystRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.shareAnalyst( // string | Unique identifier of the analyst to share. "analyst_identifier_example" , // ShareAnalystRequest { permissions: [ { principal: { identifier: "identifier_example", type: "USER", }, share_mode: "READ_ONLY", content_share_mode: "READ_ONLY", }, ], } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **shareAnalystRequest** | **ShareAnalystRequest**| | **analystIdentifier** | [**string**] | Unique identifier of the analyst to share. | defaults to undefined ### Return type **any** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **shareConversation** > void shareConversation(shareConversationRequest) Grants or revokes access to a shared conversation for one or more principals (users or groups). When principals are added, a read-only shared view of the conversation is created from its current state. Use `refresh_shared_content` to regenerate the shared view with the latest conversation content. Requires `CAN_USE_SPOTTER` privilege and ownership of the specified conversation. Version: 26.9.0.cl or later ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, ShareConversationRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.shareConversation( // string | Unique identifier of the conversation to share. "conversation_identifier_example" , // ShareConversationRequest { refresh_shared_content: false, grant: [ { principal_identifier: "principal_identifier_example", principal_type: "USER", }, ], revoke: [ { principal_identifier: "principal_identifier_example", principal_type: "USER", }, ], notify_on_share: true, } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **shareConversationRequest** | **ShareConversationRequest**| | **conversationIdentifier** | [**string**] | Unique identifier of the conversation to share. | defaults to undefined ### Return type **void** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **204** | Successfully updated the share access for the conversation. | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **singleAnswer** > ResponseMessage singleAnswer(singleAnswerRequest) Version: 10.4.0.cl or later Processes a natural language query against a specified data model and returns a single AI-generated answer without requiring a conversation session. Requires `CAN_USE_SPOTTER` privilege and at least view access to the metadata object specified in the request. #### Usage guidelines The request must include: - `query`: a natural language question (e.g., \"What were total sales last quarter?\") - `metadata_identifier`: the unique ID of the data source to query against If the request is successful, the API returns a response message containing: - `session_identifier`: the unique ID of the generated response - `generation_number`: the generation number of the response - `message_type`: the type of the response (e.g., `TSAnswer`) - `visualization_type`: the generated visualization type (`Chart`, `Table`, or `Undefined`) - `tokens` / `display_tokens`: the search tokens and user-friendly display tokens for the response #### Error responses | Code | Description | |------|-----------------------------------------------------------------------------------------------------------------------------------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege or lacks view permission on the specified metadata object. | > ###### Note: > * This endpoint is currently in Beta. Breaking changes may be introduced before the endpoint is made Generally Available. > * This endpoint requires Spotter - please contact ThoughtSpot support to enable Spotter on your cluster. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, SingleAnswerRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.singleAnswer( // SingleAnswerRequest { query: "query_example", metadata_identifier: "metadata_identifier_example", } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **singleAnswerRequest** | **SingleAnswerRequest**| | ### Return type **ResponseMessage** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **stopConversation** > void stopConversation() Stops an in-progress agent conversation response. Version: 26.6.0.cl or later Version: 26.6.0.cl or later Stops an in-progress agent response for the specified conversation. Use this endpoint to cancel a response that is actively being generated — for example, when the user navigates away, reformulates their question, or no longer needs the current result. Requires `CAN_USE_SPOTTER` privilege and access to the specified conversation. #### Usage guidelines The request must include: - `conversation_identifier` *(path parameter)*: the unique ID of the conversation whose active response should be stopped, as returned by `createAgentConversation` A successful request returns an empty `204 No Content` response. If there is no active response in progress at the time of the call, the request is still treated as successful. After stopping a response, the conversation session remains active. You can continue sending messages using `sendAgentConversationMessage` or `sendAgentConversationMessageStreaming`. #### Example request ```bash POST /api/rest/2.0/ai/agent/conversation/{conversation_identifier}/stop-response ``` #### Typical usage scenario This endpoint is useful when integrating Spotter into a chat UI where users can cancel a long-running query. For example: 1. User sends a message via `sendAgentConversationMessageStreaming`. 2. User clicks a \"Stop generating\" button while the response is streaming. 3. Your client calls `stopConversation` with the active `conversation_identifier`. 4. The stream is terminated and the user can ask a new question. #### Error responses | Code | Description | |------|-------------| | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege or lacks access to the specified conversation. | > ###### Note: > > - Calling this endpoint when no response is in progress does not return an error. > - The conversation context is preserved after stopping — previous messages and answers remain accessible. > - Available from version 26.6.0.cl and later. > - This endpoint requires Spotter — please contact ThoughtSpot Support to enable Spotter on your cluster. > - This feature is available only for **Spotter 3** (`SPOTTER3`) version. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, StopConversationRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.stopConversation( // string | Unique identifier of the conversation to stop. "conversation_identifier_example" ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **conversationIdentifier** | [**string**] | Unique identifier of the conversation to stop. | defaults to undefined ### Return type **void** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: Not defined - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **204** | Successfully stopped the in-progress agent conversation response for the given. | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **updateAnalyst** > Analyst updateAnalyst(updateAnalystRequest) Updates a Spotter Analyst. The request body is identical to `createAnalyst` and the update is a full replace: the analyst is rewritten from the request, and optional fields omitted from the request are reset (no instructions, no MCP connectors, no starter prompts). Requires ownership of the analyst, or `ADMINISTRATION` or `CAN_MANAGE_SPOTTER` privileges. Users the analyst is shared with cannot edit it. Version: 26.10.0.cl or later Updates a Spotter Analyst. The request body is identical to the create analyst API, and the update is a full replace: the analyst is rewritten from the request, and optional fields omitted from the request are reset. Requires ownership of the analyst, or `ADMINISTRATION` or `CAN_MANAGE_SPOTTER` privileges. Users the analyst is shared with can use it but cannot edit it. Use a bearer token for the Org in which the analyst exists. #### Usage guidelines The request body is flat — all fields are top-level: - `name` (required): display name of the analyst. - `description` (required): up to 200 characters. - `instructions` (optional): natural-language instructions that guide the agent\'s behavior. Instructions that conflict with system guardrails are rejected with `409`. Omitting this field clears any existing instructions. - `sources` (required): at least one data source the analyst can query, each with an `identifier`, an optional `name`, and a `type` (`MODEL`, `ANSWER`, `LIVEBOARD`, or `CONVERSATION`). Replaces the existing list in full. When new sources are added, they are automatically shared with users the analyst was previously shared with, so those users keep a working analyst. - `mcp_connector_identifiers` (optional): identifiers of MCP connectors. Replaces the existing list in full; omit or pass an empty array to clear. - `starter_prompts` (optional): up to 4 plain-text prompts, each between 10 and 250 characters; display order follows list position. Replaces the existing list in full; omit or pass an empty array to clear. If the request is successful, the response contains the updated analyst, including the refreshed `updated_time_in_millis` timestamp (epoch milliseconds) and `updated_by` user. In responses, sources are returned with `id` and `type`, connector identifiers as `mcp_connectors`, and starter prompts as structured objects (`label`, `text`, `order`, `is_ai_generated`). #### Error conditions - `400` — malformed analyst identifier. - `403` — the caller is not the analyst\'s author and lacks admin / Spotter-management privileges. - `404` — no analyst with the given identifier exists in the caller\'s Org. - `409` — `instructions` conflict with system guardrails. - `422` — validation failure, such as a missing required field (`name`, `description`, or `sources`), an empty `sources` list, too many starter prompts, or field-length violations. - `429` — rate limit exceeded. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, UpdateAnalystRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.updateAnalyst( // string | Unique identifier of the analyst to update. "analyst_identifier_example" , // UpdateAnalystRequest { name: "name_example", description: "description_example", instructions: "instructions_example", sources: [ { identifier: "identifier_example", name: "name_example", type: "MODEL", }, ], mcp_connector_identifiers: [], starter_prompts: [], } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **updateAnalystRequest** | **UpdateAnalystRequest**| | **analystIdentifier** | [**string**] | Unique identifier of the analyst to update. | defaults to undefined ### Return type **Analyst** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **200** | Common successful response | - | **201** | Common error response | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md) # **updateConversation** > void updateConversation(updateConversationRequest) Updates attributes of an existing agent conversation. Supports updating the display title and the pinned state; additional conversation attributes may be supported in future versions. At least one updatable attribute must be provided in the request body. Each attribute is applied independently, so omitted attributes are left unchanged. Version: 26.7.0.cl or later Updates attributes of an existing saved agent conversation. Supports updating the conversation\'s display `title` and its `is_pinned` state; additional updatable attributes may be supported in future versions. At least one updatable attribute must be supplied in the request body. Use this endpoint to rename a conversation, or to pin a conversation so that it is surfaced first in the conversation list for quick access. Requires `CAN_USE_SPOTTER` privilege and ownership of the conversation being updated. #### Usage guidelines The request must include: - `conversation_identifier` *(path parameter)*: the unique ID of the conversation to update, as returned by `createAgentConversation` or `getConversationList` - At least one updatable attribute in the request body: - `title` *(optional)*: the new display name for the conversation. An empty or whitespace-only value is replaced with a default title rather than rejected. - `is_pinned` *(optional)*: `true` to pin the conversation, `false` to unpin it. Available from version 26.10.0.cl. Each attribute is applied independently: omitted attributes are left unchanged, so you can update the title and the pinned state in a single request or in separate requests. Updating `is_pinned` is idempotent — pinning an already-pinned conversation, or unpinning an already-unpinned one, succeeds with no side effects. A successful request returns an empty `204 No Content` response. Updated attributes are reflected immediately in subsequent calls to `getConversationList`. #### Example request Rename a conversation: ```bash POST /api/rest/2.0/ai/agent/conversations/{conversation_identifier}/update Content-Type: application/json { \"title\": \"Revenue Breakdown by Product Line\" } ``` Pin a conversation: ```bash POST /api/rest/2.0/ai/agent/conversations/{conversation_identifier}/update Content-Type: application/json { \"is_pinned\": true } ``` Update both attributes in a single request: ```bash POST /api/rest/2.0/ai/agent/conversations/{conversation_identifier}/update Content-Type: application/json { \"title\": \"Revenue Breakdown by Product Line\", \"is_pinned\": true } ``` #### Error responses | Code | Description | |------|-------------| | 400 | Bad Request — the request body supplies neither `title` nor `is_pinned`, or `is_pinned` is not a boolean. | | 401 | Unauthorized — authentication token is missing, expired, or invalid. | | 403 | Forbidden — the authenticated user does not have `CAN_USE_SPOTTER` privilege or does not own the specified conversation. | | 404 | Not Found — no conversation exists with the given `conversation_identifier` for the authenticated user. | | 422 | Unprocessable Entity — the request body is malformed or contains an invalid field value. | > ###### Note: > > - Only conversations created with `enable_save_chat: true` can be updated. Unsaved conversations are not persisted and do not have a retrievable identifier. > - There is no limit on the number of conversations a user can pin. > - Available from version 26.7.0.cl and later. The `is_pinned` attribute is available from version 26.10.0.cl and later. > - This endpoint requires Spotter — please contact ThoughtSpot Support to enable Spotter on your cluster. ### Example ```typescript import { createBearerAuthenticationConfig, AIApi, UpdateConversationRequest } from '@thoughtspot/rest-api-sdk'; const configuration = createBearerAuthenticationConfig("CLUSTER_SERVER_URL", { username: "YOUR_USERNAME", password: "YOUR_PASSWORD", }); const apiInstance = new AIApi(configuration); apiInstance.updateConversation( // string | Unique identifier of the conversation to update. "conversation_identifier_example" , // UpdateConversationRequest { title: "title_example", is_pinned: true, } ).then((data:any) => { console.log('API called successfully. Returned data: ' + data); }).catch((error:any) => console.error(error)); ``` ### Parameters Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **updateConversationRequest** | **UpdateConversationRequest**| | **conversationIdentifier** | [**string**] | Unique identifier of the conversation to update. | defaults to undefined ### Return type **void** ### Authorization [bearerAuth](README.md#bearerAuth) ### HTTP request headers - **Content-Type**: application/json - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| **204** | Successfully updated the agent conversation. | - | **400** | Operation failed | - | **401** | Unauthorized access. | - | **403** | Forbidden access. | - | **500** | Operation failed | - | [[Back to top]](#) [[Back to API list]](README.md#documentation-for-api-endpoints) [[Back to Model list]](README.md#documentation-for-models) [[Back to README]](README.md)