> ## Documentation Index > Fetch the complete documentation index at: https://docs.arrays.org/llms.txt > Use this file to discover all available pages before exploring further. # Search equity research sections and exhibits > [OpenAPI JSON Spec](/docs/output/v1_stocks_research_search_get.json) Full-text search over LLM-generated summaries of sell-side research PDFs. Hits are individual SECTIONS and EXHIBITS (one ranked mix, `kind` discriminates), never whole reports; each hit carries the unit's FULL summary with inline (p.N) page citations plus its report context, and `file_url` opens the source PDF at the hit's page. Summaries are LLM-generated from the source PDF; page references are best-effort. Open `file_url` for original text. **Filters**: `symbol`/`entity` match units that MATERIALLY DISCUSS the company (per-unit tags — a thematic's Tesla section matches symbol=TSLA, its Waymo section doesn't); `entity` reaches unlisted companies (e.g. "Waymo"). `scope`/`sector`/`region` are closed vocabularies (see enums). `per_report` caps how many hits one report may contribute (default 2; 1 ≈ best-hit-per-report ranking). **Sort**: `relevance` (default) or `latest` (same matched set, newest publication first — for "what's the street saying now"). No `total`; page until `data` comes back short. Pagination caveat: when few results match all terms, page 1 may be filled by an any-term fallback pass; later pages use all-term matching only, so a full page 1 can be followed by a short page 2. `entity` matching is exact and case-sensitive. ## OpenAPI ````yaml /api-reference/openapi.json get /v1/stocks/research/search openapi: 3.0.0 info: contact: {} description: >- Welcome to Arrays! Arrays is a unified financial data layer for both financial institutions and retail users, delivering comprehensive market data across crypto and equity markets. Our datasets cover fundamentals, ETFs, options, crypto, and more. Visit [arrays.org](https://arrays.org) to request an API key and start your free trial. You can explore our full API offerings in the documentation below. For any questions regarding APIs or pricing, please contact support@arrays.org. title: Arrays API version: '1.0' servers: - url: https://data-tools.prd.arrays.org/api security: [] paths: /v1/stocks/research/search: get: tags: - Stock summary: Search equity research sections and exhibits description: |- [OpenAPI JSON Spec](/docs/output/v1_stocks_research_search_get.json) Full-text search over LLM-generated summaries of sell-side research PDFs. Hits are individual SECTIONS and EXHIBITS (one ranked mix, `kind` discriminates), never whole reports; each hit carries the unit's FULL summary with inline (p.N) page citations plus its report context, and `file_url` opens the source PDF at the hit's page. Summaries are LLM-generated from the source PDF; page references are best-effort. Open `file_url` for original text. **Filters**: `symbol`/`entity` match units that MATERIALLY DISCUSS the company (per-unit tags — a thematic's Tesla section matches symbol=TSLA, its Waymo section doesn't); `entity` reaches unlisted companies (e.g. "Waymo"). `scope`/`sector`/`region` are closed vocabularies (see enums). `per_report` caps how many hits one report may contribute (default 2; 1 ≈ best-hit-per-report ranking). **Sort**: `relevance` (default) or `latest` (same matched set, newest publication first — for "what's the street saying now"). No `total`; page until `data` comes back short. Pagination caveat: when few results match all terms, page 1 may be filled by an any-term fallback pass; later pages use all-term matching only, so a full page 1 can be followed by a short page 2. `entity` matching is exact and case-sensitive. parameters: - description: Search terms (2-200 chars) in: query name: q required: true schema: type: string - description: >- Units materially discussing this symbol (canonical form, e.g. NVDA, 0700.HK) in: query name: symbol schema: type: string - description: >- Units materially discussing this entity name (reaches unlisted companies) in: query name: entity schema: type: string - description: Report scope in: query name: scope schema: type: string enum: - company - industry - macro - description: Report sector (closed set) in: query name: sector schema: type: string enum: - semiconductors - software - internet - hardware - financials - industrials - autos - aerospace_space - healthcare - consumer - energy - materials - real_assets - multi - none - other - description: Report region (closed set) in: query name: region schema: type: string enum: - us - americas_ex_us - europe - emea_other - japan - greater_china - apac_other - global - description: published_at range start, unix seconds in: query name: start_time schema: type: integer - description: published_at range end, unix seconds in: query name: end_time schema: type: integer - description: relevance (default) or latest in: query name: sort schema: type: string enum: - relevance - latest - description: Max hits per report (default 2, max 5) in: query name: per_report schema: type: integer - description: Max results (default 10, max 50) in: query name: limit schema: type: integer - description: Offset (default 0) in: query name: offset schema: type: integer responses: '200': description: Ranked section/exhibit hits; [] when nothing matched content: application/json: schema: allOf: - $ref: '#/components/schemas/model.APIResponse' - properties: data: items: $ref: '#/components/schemas/model.ResearchUnit' type: array type: object '400': description: Invalid parameters content: application/json: schema: allOf: - $ref: '#/components/schemas/model.APIResponse' - properties: data: $ref: '#/components/schemas/model.APIError' type: object '500': description: Internal server error content: application/json: schema: allOf: - $ref: '#/components/schemas/model.APIResponse' - properties: data: $ref: '#/components/schemas/model.APIError' type: object security: - ApiKeyAuth: [] components: schemas: model.APIResponse: properties: data: {} error: $ref: '#/components/schemas/model.APIError' metadata: {} pagination: {} request_id: type: string success: type: boolean type: object model.ResearchUnit: properties: doc_id: example: 92e1b8986fde4a73 type: string file_url: example: >- https://storage.googleapis.com/arrays-public-assets/equity-research/0b0ac4fa.pdf#page=11 type: string heading: example: Sizing the Consumer Agent Opportunity type: string idx: example: 3 type: integer kind: example: section type: string page_from: example: 11 type: integer page_to: example: 13 type: integer published_at: example: '2026-05-06T00:33:00Z' type: string publisher: example: Goldman Sachs type: string region: example: us type: string scope: example: industry type: string score: example: 14.2 type: number sector: example: semiconductors type: string summary: type: string symbols: items: type: string type: array title: example: Decoding the Agentic Economy type: string type: object model.APIError: properties: code: example: RESOURCE_NOT_FOUND type: string details: items: $ref: '#/components/schemas/model.APIErrorDetail' type: array docs_url: type: string examples: items: type: string type: array hint: type: string message: example: The requested resource was not found. type: string suggestions: items: type: string type: array type: object model.APIErrorDetail: properties: field: type: string got: type: string reason: type: string type: object securitySchemes: ApiKeyAuth: description: 'API Key authentication. Example: "your-api-key-here"' in: header name: X-API-Key type: apiKey ````