> ## Documentation Index > Fetch the complete documentation index at: https://docs.conare.ai/llms.txt > Use this file to discover all available pages before exploring further. # Search memories > Vector + full-text search over one end user's memory, fused and reranked. No LLM pass — sub-second. Use it when your own agent does the reasoning and just needs relevant raw material; use `POST /api/v1/recall` for a synthesized answer. ## OpenAPI ````yaml /api/openapi.yaml post /api/v1/search openapi: 3.1.0 info: title: Conare API version: 1.2.0 summary: Per-end-user memory for AI applications. description: > The Conare API gives your application a persistent, personalized memory layer. Production applications authenticate as an organization-owned Integration. Every request names an `endUserId`, and that end user's memory lives in its own isolated ConareDB namespace. The physical tenant is an opaque HMAC derived from the Integration and end-user ID; clients cannot select namespaces or address another tenant. On top of storage the API provides hybrid retrieval (vector + BM25, fused and reranked, sub-second), LLM-synthesized **deep recall**, and **proactive suggestions** grounded in a user's memory. Authentication uses a scoped server-side Integration Bearer key (`cint_...`). The secret is shown once and persisted by Conare only as a SHA-256 digest. Keep it in a server-side secret manager; never ship it to the browser. Legacy personal `cmem_...` keys remain accepted during migration. Every response includes `X-Request-Id`. Send a caller-generated safe value (1–128 characters; first alphanumeric, then `A-Za-z0-9._:-`) to correlate one request through the Conare edge and memory plane; otherwise Conare generates one. Errors use a stable `{ statusCode, code, message, requestId, details? }` envelope and never include internal tenant IDs or backend error text. contact: name: Conare url: https://conare.ai email: artem@conare.ai servers: - url: https://api.conare.ai description: Production (dedicated partner-API host) - url: https://conare.ai description: Production (alias — same API, on the main host) security: - bearerAuth: [] tags: - name: Integration description: Credential, configuration, and backend readiness. - name: Memories description: Write and search a single end user's memory. - name: Recall description: LLM-synthesized personalization primitives. - name: Embeddings description: Embed text with Conare's own retrieval embedding model. - name: Connectors description: >- Let end users connect any of ~200 data sources that flow into their memory. - name: Users description: End-user lifecycle (GDPR). paths: /api/v1/search: post: tags: - Memories summary: Search memories description: | Vector + full-text search over one end user's memory, fused and reranked. No LLM pass — sub-second. Use it when your own agent does the reasoning and just needs relevant raw material; use `POST /api/v1/recall` for a synthesized answer. operationId: searchMemory requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/SearchRequest' examples: default: value: endUserId: u_123 query: charter budget boat type limit: 10 responses: '200': description: Ranked matches. content: application/json: schema: $ref: '#/components/schemas/SearchResponse' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '403': $ref: '#/components/responses/Forbidden' '429': $ref: '#/components/responses/RateLimited' components: schemas: SearchRequest: type: object required: - endUserId - query properties: endUserId: $ref: '#/components/schemas/EndUserId' query: type: string minLength: 1 example: charter budget boat type containerTag: allOf: - $ref: '#/components/schemas/ContainerTag' description: | Restrict search to one container. A malformed tag is a `400`, never a silently unscoped read. limit: type: integer description: Max results. example: 10 after: type: integer description: Only memories created after this Unix ms timestamp. before: type: integer description: Only memories created before this Unix ms timestamp. SearchResponse: type: object properties: success: type: boolean results: type: array items: $ref: '#/components/schemas/SearchResult' required: - success - results EndUserId: type: string pattern: ^[A-Za-z0-9@._-]{1,128}$ minLength: 1 maxLength: 128 description: Your stable internal user ID. No colon allowed. example: u_123 ContainerTag: type: string minLength: 1 maxLength: 128 description: | Free-form grouping label attached at save time (e.g. `"profile"`, `"workspace:acme"`). 1-128 characters; must not contain `/` or control characters. example: workspace:acme SearchResult: type: object properties: id: type: string matchedContent: type: string description: The matched text (capped; `originalLength` set when truncated). originalLength: type: integer description: Present only when matchedContent was truncated. container_tag: type: string score: type: number description: Relevance 0-1. created_at: type: integer description: Unix ms. updated_at: type: integer description: Unix ms. metadata: type: - object - 'null' additionalProperties: true Error: type: object properties: statusCode: type: integer code: type: string description: Stable snake_case machine error code. message: type: string requestId: type: string description: Correlates this response through Conare services and logs. details: type: object additionalProperties: true required: - statusCode - code - message - requestId responses: BadRequest: description: Missing or invalid fields (e.g. bad `endUserId`, empty `query`). content: application/json: schema: $ref: '#/components/schemas/Error' Unauthorized: description: Missing or invalid Bearer key. content: application/json: schema: $ref: '#/components/schemas/Error' Forbidden: description: >- The Integration credential does not include the required operation scope. content: application/json: schema: $ref: '#/components/schemas/Error' RateLimited: description: > Rate limit exceeded (reads 300/min, writes 100/min on the current plan), enforced atomically per (account, end user). Rate-window exhaustion carries a `Retry-After` header (seconds); `details` also has `retryAfterSeconds`. headers: X-Request-Id: $ref: '#/components/headers/RequestId' Retry-After: description: Seconds to wait before retrying. schema: type: integer X-RateLimit-Limit: description: The per-minute request cap for this operation. schema: type: integer X-RateLimit-Remaining: description: Requests remaining in the current window. schema: type: integer X-RateLimit-Reset: description: Unix-seconds timestamp when the window resets. schema: type: integer content: application/json: schema: $ref: '#/components/schemas/Error' headers: RequestId: description: Caller-provided or generated request correlation identifier. schema: type: string securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: cint_ description: | A scoped Integration key, prefixed `cint_`. Send as `Authorization: Bearer cint_...` on every request. Server-side only. Legacy personal `cmem_...` keys remain accepted during migration; team/org-scoped `cmem_...` keys are not valid on this API. ````