> ## Documentation Index > Fetch the complete documentation index at: https://docs.useparagon.com/llms.txt > Use this file to discover all available pages before exploring further. # Read Segment Context > Read the text before and after a passage returned by search. Use this endpoint when a search result looks relevant and you need more of the surrounding text. Pass the `pointer` from a search result passage. Use `direction` to choose which side to read: `around` (default), `before`, or `after`. Use `maxTokens` to limit the size of the response. It defaults to 2000 and cannot exceed 32000. At least one chunk is always returned, even if that chunk alone is larger than `maxTokens`. The response includes `prev` and `next` pointers for the neighboring chunks, or `null` at the start or end of the document. Pass either one back to this endpoint to keep reading in that direction. If the pointer doesn't exist or the user doesn't have access to it, the request returns a `404` with the error code `RESOURCE_NOT_FOUND`. Run a new search to get a fresh pointer. ```javascript theme={null} const response = await fetch( `https://agentos.useparagon.com/api/context/projects/${projectId}/segments/${pointer}/context?direction=around&maxTokens=2000&identity=${encodeURIComponent("user@example.com")}`, { headers: { Authorization: `Bearer ${paragonUserToken}` }, }, ); ``` ## OpenAPI ````yaml agent-os/openapi/context.json GET /api/context/projects/{projectId}/segments/{pointer}/context openapi: 3.1.0 info: title: Agent OS Context API version: 1.0.0 description: Search your users' synced content and read the text around a search result. servers: - url: https://agentos.useparagon.com description: Production US Cloud - url: https://agentos.eu.paragon.so description: Production EU Cloud security: - bearerAuth: [] paths: /api/context/projects/{projectId}/segments/{pointer}/context: get: summary: Read Segment Context operationId: readSegmentContext parameters: - $ref: '#/components/parameters/ProjectId' - name: pointer in: path required: true schema: type: string description: The pointer from a passage in a search result. - name: direction in: query description: >- Which side of the pointer to read: around it, before it, or after it. schema: type: string enum: - around - before - after default: around - name: maxTokens in: query description: >- The maximum number of tokens to return. At least one chunk is always returned, even if it is larger than this limit. schema: type: integer minimum: 1 maximum: 32000 default: 2000 - name: identity in: query schema: type: string maxLength: 1024 description: >- The account whose access applies, used on every source. Unlike search, this endpoint accepts a single string only. - name: email in: query description: Deprecated. Use identity instead. schema: type: string maxLength: 1024 deprecated: true responses: '200': description: The text around the pointer. content: application/json: schema: $ref: '#/components/schemas/SegmentContextResponse' example: id: 6f1c0b2e-1a2b-4c3d-8e9f-0a1b2c3d4e5f.rec_1 text: |- # Q2 roadmap The Q2 roadmap covers launch dates. prev: null next: chk_next tokenBudget: returnedTokens: 18 tokenizer: o200k_base '400': $ref: '#/components/responses/Error' '401': $ref: '#/components/responses/Error' '403': $ref: '#/components/responses/Error' '404': $ref: '#/components/responses/Error' components: parameters: ProjectId: name: projectId in: path required: true schema: type: string format: uuid description: >- Your Paragon Project ID. Must match the Project ID in your Paragon User Token. schemas: SegmentContextResponse: type: object required: - id - text - prev - next - tokenBudget - tokenizer properties: id: type: string description: Unique ID for the record, in the format {syncId}.{recordId}. text: type: string description: The text around the pointer. prev: oneOf: - type: string - type: 'null' description: >- Pointer to the chunk before this text, or null if this is the start of the record. next: oneOf: - type: string - type: 'null' description: >- Pointer to the chunk after this text, or null if this is the end of the record. tokenBudget: type: object required: - returnedTokens description: How much text was returned. properties: returnedTokens: type: integer description: The number of tokens in text. tokenizer: type: string enum: - o200k_base description: The tokenizer used to count tokens. ErrorEnvelope: type: object required: - error properties: error: type: object required: - code - message - hint - retryable - requestId properties: code: type: string description: >- A stable error code you can handle in your code, such as REQUEST_INVALID. message: type: string description: A human-readable description of what went wrong. hint: type: string description: Suggested next step to resolve the error. retryable: type: boolean description: Whether retrying the same request may succeed. retryAfterMs: type: integer description: >- How long to wait before retrying, in milliseconds. Only present when retryable is true. requestId: type: string description: Include this ID when contacting Paragon support about a request. details: type: array description: >- Present on validation errors. Lists the fields that failed validation. items: type: object required: - field - issue properties: field: type: string description: The field that failed validation. issue: type: string description: What was wrong with the field. responses: Error: description: The request failed. See the error object for details. content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT description: >- Your [Paragon User Token](/getting-started/installing-the-connect-sdk#setup) (JWT), which you can generate using your project's signing keys. ````