> ## Documentation Index > Fetch the complete documentation index at: https://docs.zeroentropy.dev/llms.txt > Use this file to discover all available pages before exploring further. # Top Snippets > Get the top K snippets that match the given query. You may choose between coarse and precise snippets. Precise snippets will average ~200 characters, while coarse snippets will average ~2000 characters. The default is coarse snippets. Use the `precise_responses` parameter to adjust. ## OpenAPI ````yaml post /queries/top-snippets openapi: 3.1.0 info: title: ZeroEntropy API description: This API provides access to ZeroEntropy's SoTA retrieval pipeline. Enjoy! version: 0.1.0 servers: - url: https://api.zeroentropy.dev/v1 description: ZeroEntropy API - url: https://eu-api.zeroentropy.dev/v1 description: ZeroEntropy API (EU datacenters) security: [] paths: /queries/top-snippets: post: tags: - Queries summary: Top Snippets description: >- Get the top K snippets that match the given query. You may choose between coarse and precise snippets. Precise snippets will average ~200 characters, while coarse snippets will average ~2000 characters. The default is coarse snippets. Use the `precise_responses` parameter to adjust. operationId: top_snippets_queries_top_snippets_post requestBody: content: application/json: schema: $ref: '#/components/schemas/TopSnippetsRequest' required: true responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/TopSnippetsResponse' '400': description: Bad Request content: application/json: example: detail: Description of Error '404': description: Not Found content: application/json: example: detail: Description of Error '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - HTTPBearer: [] components: schemas: TopSnippetsRequest: properties: collection_name: type: string title: Collection Name description: The name of the collection. query: type: string title: Query description: >- The natural language query to search with. This cannot exceed 4096 characters (A single UTF-8 codepoint, is considered to be 1 character). k: type: integer title: K description: >- The number of snippets to return. If there are not enough snippets matching your filters, then fewer may be returned. This number must be between 1 and 128, inclusive. reranker: anyOf: - type: string - type: 'null' title: Reranker description: >- The reranker to use after initial retrieval. The default is `null`. You can find available model ids, along with more information, at [/models/rerank](/api-reference/models/rerank). filter: anyOf: - $ref: '#/components/schemas/StrJson' - type: 'null' description: >- The query filter to apply. Please read [Metadata Filtering](/metadata-filtering) for more information. If not provided, then all documents will be searched. precise_responses: type: boolean title: Precise Responses description: >- Enable precise responses. Precise responses will have higher latency, but provide much more precise snippets. When `precise_responses` is set to `true`, the responses will average 200 characters. If set to `false`, the responses will average 2000 characters. The default is `false`. default: false include_document_metadata: type: boolean title: Include Document Metadata description: >- If true, the `document_results` returns will additionally contain document metadata. This is false by default, as returning metadata can add overhead if the amount of data to return is large. default: false type: object required: - collection_name - query - k title: TopSnippetsRequest TopSnippetsResponse: properties: results: items: $ref: '#/components/schemas/SnippetResponse' type: array title: Results description: >- The array of snippets returned by this endpoint. Each snippet result refers to a particular document path, and index range. Note that all documents, regardless of filetype, are converted into `UTF-8`-encoded strings. The `start_index` and `end_index` of a snippet refer to the range of characters in that string, that have been matched by this snippet. document_results: items: $ref: '#/components/schemas/DocumentRetrievalResponse' type: array title: Document Results description: >- The array of associated document information. Note how each snippet has an associated document path. After deduplicating the document paths, this array will contain document info for each document path that is referenced by at least one snippet result. type: object required: - results - document_results title: TopSnippetsResponse HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError StrJson: anyOf: - type: string - items: type: string type: array - items: $ref: '#/components/schemas/StrJson' type: array - additionalProperties: $ref: '#/components/schemas/StrJson' type: object SnippetResponse: properties: path: type: string title: Path description: The path of the document that this snippet comes from. start_index: type: integer title: Start Index description: The start index of this snippet. end_index: type: integer title: End Index description: The end index of this snippet. page_span: prefixItems: - type: integer - type: integer type: array items: type: integer maxItems: 2 minItems: 2 title: Page Span description: >- The range of page indices spanned by this snippet, as a 2-tuple of integers. Inclusive on the first page_index and exclusive on the second page_index. content: type: string title: Content description: The full string content of this snippet. score: type: number title: Score description: The relevancy score assigned to this snippet. type: object required: - path - start_index - end_index - page_span - content - score title: SnippetResponse description: >- This is a Snippet. A snippet refers to a particular document path, and index range. Note that all documents, regardless of filetype, are converted into `UTF-8`-encoded strings. The `start_index` and `end_index` refer to the range of characters in that string, that have been matched by this snippet. DocumentRetrievalResponse: properties: path: type: string title: Path description: The path of the document. score: type: number title: Score description: The relevancy score assigned to this document. metadata: anyOf: - $ref: '#/components/schemas/DocumentMetadataJson' - type: 'null' description: >- The metadata for that document. Will be `None` if `include_metadata` is `False`. file_url: type: string title: File Url description: >- A URL to the document data, which can be used to download the raw document content or to display the document in frontend applications. NOTE: If a `/documents/update-document` call returned a new document id, then this url will be invalidated and must be retrieved again. type: object required: - path - score - metadata - file_url title: DocumentRetrievalResponse ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError DocumentMetadataJson: additionalProperties: anyOf: - type: string - items: type: string type: array type: object securitySchemes: HTTPBearer: type: http description: >- The `Authorization` header must be provided in the format `Bearer `. You can get your API Key at the [Dashboard](https://dashboard.zeroentropy.dev/)! scheme: bearer ````