> ## Documentation Index > Fetch the complete documentation index at: https://docs.stockinsights.ai/llms.txt > Use this file to discover all available pages before exploring further. # Filings Embeddings Search > The Filings Embeddings Search API retrieves the nearest chunks of text (based on semantic similarity) from our database for specified filings (earnings transcripts and 10-Ks) for any given user query/prompt in natural langauge. Users can utilize this functionality for various purposes, such as building an AI-search engine, AI-tagging, etc., using the associated text from these filings. ## OpenAPI ````yaml openapi-us post /api/us/v0/documents/embeddings-search openapi: 3.0.0 info: title: stockinsights.ai APIs description: All the APIs of stockinsights.ai version: 1.0.0 servers: - url: https://stockinsights-ai-us-main-f5fd25a.zuplo.app security: - bearerAuth: [] paths: /api/us/v0/documents/embeddings-search: post: summary: Filings Embeddings Search description: >- The Filings Embeddings Search API retrieves the nearest chunks of text (based on semantic similarity) from our database for specified filings (earnings transcripts and 10-Ks) for any given user query/prompt in natural langauge. Users can utilize this functionality for various purposes, such as building an AI-search engine, AI-tagging, etc., using the associated text from these filings. operationId: documentEmbeddingSearch requestBody: required: true content: application/json: schema: type: object required: - query properties: query: type: string description: >- The user query in natural language for which similar chunks of filings text is retrieved using OpenAI embeddings. top_k: type: integer default: 10 maximum: 100 description: >- Number of top matching chunks to return in the response. This parameter is optional and defaults to 20 if not specified. Maximum value is 50 filters: type: object description: >- Filters to narrow the search scope. For example, the search can be limited to few CIKs only. Without filters, search will be performed across all the filings properties: types: type: array items: type: string enum: - earnings-transcript - 10-K description: >- The type of filings to include in the search. Choose from 'earnings-transcript', '10-K'. ciks: type: array items: type: string example: '0001045810' maxItems: 100 description: >- CIKs (Central Index Keys) of companies. Multiple CIKs can be provided separated by commas. Each CIK should be a 10-digit number (include leading zeros if necessary). Get CIKs from [Company Details](https://drive.google.com/file/d/1XQh20CTDEn_uFhRArOQm9jkVesnSkSTI/view). sectors: type: array items: type: string maxItems: 5 description: >- Sector classification of the companies. Multiple values can be provided separated by commas. Get valid sector values from [Company Details](https://drive.google.com/file/d/1XQh20CTDEn_uFhRArOQm9jkVesnSkSTI/view). industries: type: array items: type: string maxItems: 5 description: >- Industry classification of the companies. Multiple values can be provided separated by commas. Check valid industry values from [Company Details](https://drive.google.com/file/d/1XQh20CTDEn_uFhRArOQm9jkVesnSkSTI/view) years: type: array items: type: string pattern: ^[0-9]{4}$ description: >- Fiscal year values in the format YYYY (e.g., 2024, 2023). Multiple values can be provided separated by commas. Use this parameter to filter data by specific years. quarters: type: array items: type: string enum: - Q1 - Q2 - Q3 - Q4 example: Q4 description: >- Fiscal quarter values in the format Q1, Q2, Q3, Q4. Multiple values can be provided separated by commas. Use this parameter to filter by specific quarters. responses: '200': description: >- Successful response. Contains the list of chunks for given query vector content: application/json: schema: type: object properties: status: type: string description: Status code data: type: array items: $ref: '#/components/schemas/DocumentChunkWithScore' examples: example1: value: status: success data: - text: >- It's Second, we laid the foundation to be a three-chip data center scale computing company with GPUs, DPUs and CPUs. Third, AI is the most powerful technology force of our time. We partner with cloud and consumer Internet companies to scale out and commercialize AI-powered services. And we're democratizing AI for every enterprise and every industry. metadata: chunk_num: '18' document: type: earnings-transcript published_date: '2021-05-27T01:40:47.000Z' year: '2022' quarter: Q1 link: >- https://stockinsights.ai/us/filings/earnings-transcript/64428b8954ef6b435cdc137c/content company: company_name: Nvidia Corp ticker: NVDA cik: '0001045810' similarity_score: 0.9295221567153931 - text: >- And we containerize them into our stack. We call it NVIDIA AI Enterprise. And the way we go to market with it is that think of that NVIDIA AI Enterprise now as a run time like an operating system, it's an operating system for artificial intelligence. metadata: chunk_num: '16' document: type: earnings-transcript published_date: '2024-02-22T10:58:00.000Z' year: '2024' quarter: Q4 link: >- https://stockinsights.ai/us/filings/earnings-transcript/65d811ca8ac10234b0fbd253/content company: id: epPs1xy7IL company_name: Nvidia Corp ticker: NVDA cik: '0001045810' similarity_score: 0.9289319515228271 '400': description: Invalid request content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: DocumentChunkWithScore: allOf: - $ref: '#/components/schemas/DocumentChunk' - type: object properties: similarity_score: type: number description: Similarity score Error: type: object properties: errors: type: array items: type: object properties: status: type: string description: Error status title: type: string description: Error description DocumentChunk: type: object properties: text: type: string description: The chunk's text metadata: type: object properties: chunk_num: type: string description: Identifier of the chunk in the document document: type: object properties: type: type: string description: Filing type published_date: type: string format: date-time description: Filing date year: type: string description: Year of the filing quarter: type: string enum: - Q1 - Q2 - Q3 - Q4 description: Quarter of the filing link: type: string description: URL of the document company: type: object properties: id: type: string description: Internal representation of ID company_name: type: string description: Company Name ticker: type: string description: Internal ticker of the company cik: type: string description: CIK of the company example: '0001045810' securitySchemes: bearerAuth: type: http scheme: bearer ````