> ## Documentation Index > Fetch the complete documentation index at: https://docs.recallrai.com/llms.txt > Use this file to discover all available pages before exploring further. # Get Context > Retrieve AI context including relevant memories and recent conversations. Generate context for LLM prompts by retrieving the most relevant memories and recent messages for a user. Use this to manually inject memory context into your AI applications. **Path Parameters:** - `custom_user_id` (str): Unique identifier for the user - `session_id` (UUID): Session UUID to get context from **Query Parameters:** - `recall_strategy` (RecallStrategy): Memory retrieval strategy. Options: low_latency, balanced, agentic and auto. Default: balanced - `min_top_k` (int): Minimum number of memories to return. Range: 5-50. Default: 15 - `max_top_k` (int): Maximum number of memories to return. Range: 10-100. Default: 50 - `memories_threshold` (float): Similarity threshold for memories. Range: 0.2-0.8. Default: 0.6 - `summaries_threshold` (float): Similarity threshold for session summaries. Range: 0.2-0.8. Default: 0.5 - `last_n_messages` (int): Number of last messages to include in context. Range: 1-100. Optional - `last_n_summaries` (int): Number of last summaries to include in context. Range: 1-20. Optional - `timezone` (str): Timezone for formatting timestamps (e.g., 'America/New_York'). Default: UTC - `include_system_prompt` (bool): Whether to include the default system prompt. Default: true - `stream` (bool): Whether to stream status updates via Server-Sent Events. Default: false **Returns:** - When `stream=false`: JSON `GetContextResponse` with `is_final=true` and `context` field - When `stream=true`: SSE stream of `GetContextResponse` events with progress updates, ending with a final event containing the context ## OpenAPI ````yaml https://api.recallrai.com/api/openapi.json get /api/v1/users/{custom_user_id}/sessions/{session_id}/context openapi: 3.1.0 info: title: api-backend description: This powers the Recallr AI API Backend version: 0.1.0 servers: - url: https://api.recallrai.com description: Production server security: [] paths: /api/v1/users/{custom_user_id}/sessions/{session_id}/context: get: tags: - Sessions summary: Get Context description: >- Retrieve AI context including relevant memories and recent conversations. Generate context for LLM prompts by retrieving the most relevant memories and recent messages for a user. Use this to manually inject memory context into your AI applications. **Path Parameters:** - `custom_user_id` (str): Unique identifier for the user - `session_id` (UUID): Session UUID to get context from **Query Parameters:** - `recall_strategy` (RecallStrategy): Memory retrieval strategy. Options: low_latency, balanced, agentic and auto. Default: balanced - `min_top_k` (int): Minimum number of memories to return. Range: 5-50. Default: 15 - `max_top_k` (int): Maximum number of memories to return. Range: 10-100. Default: 50 - `memories_threshold` (float): Similarity threshold for memories. Range: 0.2-0.8. Default: 0.6 - `summaries_threshold` (float): Similarity threshold for session summaries. Range: 0.2-0.8. Default: 0.5 - `last_n_messages` (int): Number of last messages to include in context. Range: 1-100. Optional - `last_n_summaries` (int): Number of last summaries to include in context. Range: 1-20. Optional - `timezone` (str): Timezone for formatting timestamps (e.g., 'America/New_York'). Default: UTC - `include_system_prompt` (bool): Whether to include the default system prompt. Default: true - `stream` (bool): Whether to stream status updates via Server-Sent Events. Default: false **Returns:** - When `stream=false`: JSON `GetContextResponse` with `is_final=true` and `context` field - When `stream=true`: SSE stream of `GetContextResponse` events with progress updates, ending with a final event containing the context operationId: >- get_context_api_v1_users__custom_user_id__sessions__session_id__context_get parameters: - name: custom_user_id in: path required: true schema: type: string title: The custom user ID to get the context for - name: session_id in: path required: true schema: type: string format: uuid title: The session ID to get the context from - name: recall_strategy in: query required: false schema: $ref: '#/components/schemas/RecallStrategy' title: The recall strategy to use default: auto - name: min_top_k in: query required: false schema: type: integer maximum: 50 minimum: 5 title: Minimum number of memories to return default: 15 - name: max_top_k in: query required: false schema: type: integer maximum: 100 minimum: 10 title: Maximum number of memories to return default: 50 - name: memories_threshold in: query required: false schema: type: number maximum: 0.8 minimum: 0.2 title: Similarity threshold for memories default: 0.6 - name: summaries_threshold in: query required: false schema: type: number maximum: 0.8 minimum: 0.2 title: Similarity threshold for session summaries default: 0.5 - name: last_n_messages in: query required: false schema: anyOf: - type: integer maximum: 100 minimum: 1 - type: 'null' title: Number of last messages to include in context - name: last_n_summaries in: query required: false schema: anyOf: - type: integer maximum: 20 minimum: 1 - type: 'null' title: Number of last summaries to include in context - name: timezone in: query required: false schema: type: string title: >- Timezone for formatting timestamps (e.g., 'America/New_York'). Defaults to UTC. default: UTC - name: include_system_prompt in: query required: false schema: type: boolean title: Whether to include the default system prompt. Defaults to True default: true - name: stream in: query required: false schema: type: boolean title: >- Whether to stream status updates via Server-Sent Events. Defaults to False default: false - name: include_metadata_ids in: query required: false schema: type: boolean title: >- Whether to include memory IDs and session IDs that contributed to the context. Defaults to False default: false - name: X-Recallr-Project-Id in: header required: true schema: type: string format: uuid title: X-Recallr-Project-Id - name: X-Recallr-Api-Key in: header required: true schema: type: string title: X-Recallr-Api-Key responses: '200': description: Context retrieved successfully content: application/json: schema: $ref: '#/components/schemas/GetContextResponse' example: is_final: true context: '# Relevant memories and context.' text/event-stream: schema: type: string description: SSE data payload is JSON matching GetContextResponse. x-event-schema: $ref: '#/components/schemas/GetContextResponse' example: >+ data: {"is_final":false,"status_update_message":"Analyzing conversation..."} data: {"is_final":true,"context":"# Relevant memories."} '401': description: Authentication required '402': description: Payment required '404': description: Session not found '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' '500': description: Internal server error components: schemas: RecallStrategy: type: string enum: - low_latency - balanced - agentic - auto title: RecallStrategy description: Type of recall strategy. GetContextResponse: properties: is_final: type: boolean title: Is Final status_update_message: anyOf: - type: string - type: 'null' title: Status Update Message error_message: anyOf: - type: string - type: 'null' title: Error Message context: anyOf: - type: string - type: 'null' title: Context metadata: anyOf: - $ref: '#/components/schemas/ContextMetadata' - type: 'null' type: object required: - is_final title: GetContextResponse HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ContextMetadata: properties: memory_ids: anyOf: - items: type: string type: array - type: 'null' title: Memory Ids session_ids: anyOf: - items: type: string type: array - type: 'null' title: Session Ids agent_reasoning: anyOf: - type: string - type: 'null' title: Agent Reasoning vector_search_queries: anyOf: - items: type: string type: array - type: 'null' title: Vector Search Queries keywords: anyOf: - items: type: string type: array - type: 'null' title: Keywords session_summaries_search_queries: anyOf: - items: type: string type: array - type: 'null' title: Session Summaries Search Queries date_range_filters: anyOf: - items: $ref: '#/components/schemas/QueryDateRangeFilter' type: array - type: 'null' title: Date Range Filters recall_strategy_used: anyOf: - $ref: '#/components/schemas/RecallStrategy' - type: 'null' type: object title: ContextMetadata description: Metadata for context generation. ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError QueryDateRangeFilter: properties: filter_type: $ref: '#/components/schemas/DateRangeFilterType' start_date: type: string format: date-time title: Start Date end_date: type: string format: date-time title: End Date type: object required: - filter_type - start_date - end_date title: QueryDateRangeFilter description: |- Represents a single date range filter extracted from user query. Examples: - "What did I mention last month?" -> start_date: 2025-12-01, end_date: 2025-12-31, filter_type: created_at - "What happened yesterday?" -> start_date: 2026-01-06, end_date: 2026-01-06, filter_type: event_date DateRangeFilterType: type: string enum: - event_date - created_at title: DateRangeFilterType description: Type of date field to filter on when querying memories. ````