> ## Documentation Index > Fetch the complete documentation index at: https://getalchemystai.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Search and summarize context based on steering prompt > This endpoint performs a context search using the context processor, joins all matching context chunks into a single string, then sends that joined context along with the user's query to an LLM via OpenRouter (model `poolside/laguna-m.1` pinned to the `poolside/fp4` provider) to produce a natural-language answer grounded in the retrieved context. By default the response only includes the generated `answer`. Pass `?context=true` to also receive the joined context string that was used to ground the answer. ## OpenAPI ````yaml POST /api/v1/context/search/steer openapi: 3.1.0 info: title: Alchemyst AI API v1 documentation version: 1.0.0 description: v1 API documentation for Alchemyst AI servers: - url: https://platform-backend.getalchemystai.com description: production security: [] tags: [] paths: /api/v1/context/search/steer: post: tags: - context summary: Search context and generate an LLM-powered answer description: > This endpoint performs a context search using the context processor, joins all matching context chunks into a single string, then sends that joined context along with the user's query to an LLM via OpenRouter (model `poolside/laguna-m.1` pinned to the `poolside/fp4` provider) to produce a natural-language answer grounded in the retrieved context. By default the response only includes the generated `answer`. Pass `?context=true` to also receive the joined context string that was used to ground the answer. operationId: steerUserContext parameters: - in: query name: mode schema: type: string enum: - fast - standard default: standard required: false description: > Controls the search mode: - mode=fast -> prioritizes speed over completeness. - mode=standard -> performs a comprehensive search (default if omitted). - in: query name: context schema: type: boolean default: false required: false description: > When set to `true`, the response includes the joined `context` string used to ground the answer. Defaults to `false` (only `answer`, `model`, and `usage` are returned). requestBody: required: true content: application/json: schema: type: object required: - query - similarity_threshold - minimum_similarity_threshold properties: user_id: type: string description: The ID of the user making the request example: user123 deprecated: true steeringPrompt: type: string description: >- The steering prompt for the query - basically the way in which you want to get your answer as. example: >- Return only the basic details of the person in a structured JSON schema with the fields "name", "status", "location" query: type: string description: >- The search query and question to be answered using retrieved context example: What did the customer ask about pricing for the Scale plan? similarity_threshold: type: number minimum: 0 maximum: 1 description: >- Maximum similarity threshold (must be >= minimum_similarity_threshold) example: 0.8 minimum_similarity_threshold: type: number minimum: 0 maximum: 1 description: Minimum similarity threshold example: 0.5 scope: type: string enum: - internal - external default: internal description: Search scope body_metadata: type: object description: Additional metadata for the search default: {} examples: simple: summary: Basic steer request value: query: What did the customer ask about pricing for the Scale plan? similarity_threshold: 0.8 minimum_similarity_threshold: 0.5 scope: internal withMetadata: summary: Steer request with metadata filters value: query: What did the customer ask about pricing for the Scale plan? similarity_threshold: 0.8 minimum_similarity_threshold: 0.5 scope: internal body_metadata: fileName: support_thread_TCK-1234.txt groupName: - support - pricing lastModifiedAt: '2025-01-10T12:34:56.000Z' responses: '200': description: Successfully retrieved context and generated an answer. content: application/json: schema: type: object required: - answer - model - usage properties: answer: type: string description: The LLM-generated answer based on the retrieved context context: type: string description: > The joined context retrieved from the context processor. Only present when the request was made with `?context=true`. model: type: string description: >- The model used to generate the answer (currently `poolside/laguna-m.1`) example: poolside/laguna-m.1 usage: type: object description: Token usage information from the LLM properties: inputTokens: type: number outputTokens: type: number totalTokens: type: number '400': description: Bad Request - Invalid or missing search parameters content: application/json: schema: type: object properties: response: type: string example: 'Fields missing. Detailed error: {error details}' '401': description: Unauthorized - User not authenticated content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '402': description: Payment Required - User not allowed to perform action content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '403': description: Forbidden - User lacks required scope content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '500': description: Internal Server Error content: application/json: schema: type: object properties: response: type: string example: error security: - bearerAuth: [] components: schemas: ErrorResponse: type: object required: - success - error properties: success: type: boolean example: false message: type: string example: Invalid job id status: type: number example: 400 error: type: object example: Error details required: - code - message properties: code: type: string example: UNAUTHORIZED message: type: string example: User not authenticated details: type: object additionalProperties: true statusText: type: string description: Error message (detailed in debug mode) securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT ````