> ## Documentation Index > Fetch the complete documentation index at: https://docs.gbase.ai/llms.txt > Use this file to discover all available pages before exploring further. # Ask Question > When you upload a file through the file upload interface, you can use this interface to ask questions about the content of the file you upload, and this interface will return the retrieved answer. ## OpenAPI ````yaml https://api.gbase.ai/openapi-redoc.json post /v1/question/{ai_id} openapi: 3.1.0 info: title: GBase description: > # Introduce This API document can help you understand GBase more deeply. You can train your own AI directly through the interface of this document. ## Authentication Home page: [https://gbase.ai](https://gbase.ai) Huggingface: [https://huggingface.co/gptbase](https://huggingface.co/gptbase) The GBase API uses API keys for authentication. Visit your API Keys page to retrieve the API key you'll use in your requests. Remember that your API key is a secret! Do not share it with others or expose it in any client-side code (browsers, apps). Production requests must be routed through your own backend server where your API key can be securely loaded from an environment variable or key management service. All API requests should include your API key in an Authorization HTTP header as follows: Parameter name: Authorization Value: Bearer [YOUR_API_KEY](https://admin.gbase.ai/keys) ``` Authorization: Bearer YOUR_API_KEY ``` ## Use steps 1.Fill in your API keys. 2.You can create an AI by using either the API interface or the administrative backend. Once created, the AI will generate an ID which will be required for the subsequent steps. 3.Use the generated ID to call the file upload interface. 4.After uploading the file, you can use the question interface to inquire about it. version: 0.0.1 servers: - url: https://api.gbase.ai security: [] paths: /v1/question/{ai_id}: post: tags: - Question summary: Ask Question description: >- When you upload a file through the file upload interface, you can use this interface to ask questions about the content of the file you upload, and this interface will return the retrieved answer. operationId: ask_question_v1_question__ai_id__post parameters: - required: true schema: type: string title: Ai Id name: ai_id in: path requestBody: content: application/json: schema: $ref: '#/components/schemas/QuestionIn' required: true responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/QuestionOut' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - Auth0HTTPBearer: [] - HTTPBearer: [] components: schemas: QuestionIn: properties: question: type: string title: Question session_id: type: string maxLength: 100 title: Session Id description: |- Session ID It is recommended to use uuid message_id: type: string format: uuid title: Message Id anonymous_username: type: string title: Anonymous Username default: '' use_faq: type: boolean title: Use Faq default: true max_tokens: type: integer title: Max Tokens default: 3000 stream: type: boolean title: Stream default: true stream_obj: type: boolean title: Stream Obj default: false format: allOf: - $ref: '#/components/schemas/StreamingMessageDataFormat' default: PLAIN_TEXT with_source: type: boolean title: With Source default: false with_images: type: boolean title: With Images debug_with_messages: type: boolean title: Debug With Messages description: >- Debug only, use `debug_with_messages: true, stream: false` to get prompt messages default: false recommend_faq_id: type: string format: uuid title: Recommend Faq Id created_by: type: string title: Created By default: '' page_info: type: object title: Page Info is_test: type: boolean title: Is Test default: false metadata: items: $ref: '#/components/schemas/QuestionMetadata' type: array title: Metadata default: [] prompt_custom_goal: type: string maxLength: 200 title: Prompt Custom Goal description: custom goal for prompt default: '' dynamic_background: anyOf: - type: string - items: {} type: array title: Dynamic Background description: >- JSON string or dict for dynamic background information, used to add to agent meta prompt default: '' language: type: string title: Language agent_mode: type: string title: Agent Mode model: type: string title: Model user_identifier: type: string title: User Identifier tool_response: type: boolean title: Tool Response default: false image_contents: items: type: object type: array title: Image Contents description: >- 多模态图片内容列表，格式: [{'url': 'data:image/png;base64,...', 'detail': 'auto'}] type: object required: - question - session_id title: QuestionIn QuestionOut: properties: answer: anyOf: - type: string - type: object - items: {} type: array title: Answer messages: items: {} type: array title: Messages tool_calls: items: {} type: array title: Tool Calls type: object title: QuestionOut HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError StreamingMessageDataFormat: type: string enum: - PLAIN_TEXT - JSON_AST - OPENAI_AST title: StreamingMessageDataFormat description: An enumeration. QuestionMetadata: properties: key: type: string title: Key value: type: string title: Value type: type: string title: Type type: object required: - key title: QuestionMetadata 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 securitySchemes: HTTPBearer: type: http scheme: bearer ````