openapi: 3.1.0 info: title: WorqHat AI API Endpoints description: > This API provides access to various AI services offered by WorqHat. It includes endpoints for user authentication, Databases and AI access. Users can authenticate themselves, access AI services, and manage their databases. version: 2.1.2 termsOfService: 'https://www.worqhat.com/terms-of-service' contact: name: WorqHat Support email: support@worqhat.com url: https://www.worqhat.com/contact-us license: name: Apache 2.0 url: 'https://www.apache.org/licenses/LICENSE-2.0.html' externalDocs: description: 'Read more at https://docs.worqhat.com' url: 'https://docs.worqhat.com' tags: - name: Authentication description: Endpoints for user authentication, including login, logout, and password reset. - name: AI Services description: Endpoints for accessing various AI services, such as image recognition, natural language processing, and machine learning models. - name: AI Dataset Management description: Endpoints for managing custom trained AI models. - name: Database Management description: Endpoints for managing user data, including CRUD operations on user-specific databases and data retrieval. servers: - url: https://api.worqhat.com description: Production server for WorqHat AI API security: - bearerAuth: [] paths: /authentication: post: summary: Authenticate a user description: > This endpoint is used to authenticate a user by providing their API Key. It verifies the provided API Key and returns the user's details upon successful authentication. operationId: authenticateUser tags: - Authentication security: - bearerAuth: [] responses: '200': description: User authenticated successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the authentication. userEmail: type: string description: The email address of the authenticated user. userDisplayName: type: string description: The display name of the authenticated user. orgName: type: string description: The organization name associated with the authenticated user. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. example: status: "success" userEmail: "user@example.com" userDisplayName: "John Doe" orgName: "example_org" processing_time: 2311 processing_id: "cd185dd4-fcfb-4b15-93de-db9eded23ade" '400': description: Bad Request content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/images/generate/v2: post: summary: Generate an image using AI description: > This endpoint is used to generate an image using AI. It accepts a JSON object containing the image generation parameters and returns the generated image. The ImageCon V2 model is our Fastest and basic model for generating images that can handle image sizes of 512x512 and 512x768. operationId: generateImageV2 tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: prompt: type: array description: The prompt and descriptions to be used for generating the image. items: type: string image_style: type: string description: > The style of the image to be generated. You can choose between `Abstract`, `Landscape`, `Portrait`, `Still Life`, `Animal`, `Anime`, `Architecture`, etc. output_type: type: string description: > The type of output to be generated. You can choose between `url` and `blob` . `URL` will return a cloud-hosted Temporary URL for the generated image, you need to handle the image download on your end. `blob` will return the image as a base64 encoded string. enum: - url - blob orientation: type: string description: > The orientation of the image to be generated. You can choose between `square` , `portrait`, and `landscape`. `square` will generate a square image of dimensions 512x512. `portrait` will generate a portrait image of dimensions 512x768. `landscape` will generate a landscape image of dimensions 768x512. enum: - square - portrait - landscape example: prompt: ["Create an image of an AI cat typing on a keyboard"] image_style: "realistic" output_type: "url" orientation: "square" responses: '200': description: Image generated successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the image generation. image: type: string description: The generated image. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" image: "https://storage.googleapis.com/1fe0a9ac-617a-42e4-a376-37808b98fc99-worqhat/image-gen/MFl2oNxrMLYKvWbwoDkbQPpScWD3-1697226444718.png?GoogleAccessId=cloud-storage-upload%40worqhat-dev.iam.gserviceaccount.com&Expires=1697226626&Signature=DHlOeWd4QladLc6hsdoqp9lTbvMXs06B6hOkQPviFubszuLfahXXRv9aj%2FPTTlytlTClXHX0zGFr3Tsq9S%2Fs3hFjqBsy7lho%2BfuRFhPG4FrQoV2lxrZmB47X6nWc7TG6hbgLkyT3CvAOfwccmWHH1cbBiEDSI0iEKvx7kwUsgIrYu1ko9Szkul29fjVQ89WL6jyQQX1G9ejsQTNmXHFNRvhwRHkRfZJ5n3Y1uR7aqAyMZfQ2Me6i7bVb7smc0t5Ed2yk6%2BN1fdrz6zhbkc%2Fuh13vWhrT8EWMuCYKhsrzPakO%2B%2B229nlt5Y4D9zyFqevAmj43Vl76INIq29gcs39oQg%3D%3D" processing_time: 2311 processing_id: "cd185dd4-fcfb-4b15-93de-db9eded23ade" processing_count: 1 '400': description: Bad Request content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/images/generate/v3: post: summary: Generate an image using AI description: > This endpoint is used to generate an image using AI. It accepts a JSON object containing the image generation parameters and returns the generated image. The ImageCon V2 model is our Fastest and basic model for generating images that can handle image sizes of `1024x1024` and `1344x1024`. operationId: generateImageV3 tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: prompt: type: array description: The prompt and descriptions to be used for generating the image. items: type: string image_style: type: string description: > The style of the image to be generated. You can choose between `Abstract`, `Landscape`, `Portrait`, `Still Life`, `Animal`, `Anime`, `Architecture`, etc. output_type: type: string description: > The type of output to be generated. You can choose between `url` and `blob` . `URL` will return a cloud-hosted Temporary URL for the generated image, you need to handle the image download on your end. `blob` will return the image as a base64 encoded string. enum: - url - blob orientation: type: string description: > The orientation of the image to be generated. You can choose between `square` , `portrait`, and `landscape`. `square` will generate a square image of dimensions 1024x1024. `portrait` will generate a portrait image of dimensions 1024x1344. `landscape` will generate a landscape image of dimensions 1344x1024. enum: - square - portrait - landscape example: prompt: ["Create an image of an AI cat typing on a keyboard"] image_style: "realistic" output_type: "url" orientation: "square" responses: '200': description: Image generated successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the image generation. image: type: string description: The generated image. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" image: "https://storage.googleapis.com/1fe0a9ac-617a-42e4-a376-37808b98fc99-worqhat/image-gen/MFl2oNxrMLYKvWbwoDkbQPpScWD3-1697226444718.png?GoogleAccessId=cloud-storage-upload%40worqhat-dev.iam.gserviceaccount.com&Expires=1697226626&Signature=DHlOeWd4QladLc6hsdoqp9lTbvMXs06B6hOkQPviFubszuLfahXXRv9aj%2FPTTlytlTClXHX0zGFr3Tsq9S%2Fs3hFjqBsy7lho%2BfuRFhPG4FrQoV2lxrZmB47X6nWc7TG6hbgLkyT3CvAOfwccmWHH1cbBiEDSI0iEKvx7kwUsgIrYu1ko9Szkul29fjVQ89WL6jyQQX1G9ejsQTNmXHFNRvhwRHkRfZJ5n3Y1uR7aqAyMZfQ2Me6i7bVb7smc0t5Ed2yk6%2BN1fdrz6zhbkc%2Fuh13vWhrT8EWMuCYKhsrzPakO%2B%2B229nlt5Y4D9zyFqevAmj43Vl76INIq29gcs39oQg%3D%3D" processing_time: 2311 processing_id: "cd185dd4-fcfb-4b15-93de-db9eded23ade" processing_count: 1 '400': description: Bad Request content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/images/modify/v2: post: summary: Modify existing image using ImageCon V2 description: > This endpoint is used to modify an existing image using AI. It accepts a Form Data containing the image modification parameters and returns the modified image. operationId: modifyImageV2 tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: multi-part/form-data: schema: type: object properties: existing_image: type: string format: binary description: > The image to be modified or edited. Neither `height` nor `width` of the image should be less than `128px`. Only one of the sides of the image should be greater than or equal to `512px`. (Eg: `512x512`, `512x768`, `768x512`). Maximum dimensions supported is `512x896` output_type: type: string description: > The type of output to be generated. You can choose between `url` and `blob` . `URL` will return a cloud-hosted Temporary URL for the generated image, you need to handle the image download on your end. `blob` will return the image as a base64 encoded string. enum: - url - blob modification: type: string description: > The modification to be applied to the image. You can add in the modification parameters as a string based description. similarity: type: number description: > The similarity to be applied to the image. It is a number between 0 and 100. The higher the number, the more similar the image will be to the original. example: existing_image: "/path/to/image.jpg" output_type: "url" modification: "Add a cat to the image" similarity: 50 responses: '200': description: Image generated successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the image generation. image: type: string description: The generated image. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" image: "https://storage.googleapis.com/1fe0a9ac-617a-42e4-a376-37808b98fc99-worqhat/image-gen/MFl2oNxrMLYKvWbwoDkbQPpScWD3-1697226444718.png?GoogleAccessId=cloud-storage-upload%40worqhat-dev.iam.gserviceaccount.com&Expires=1697226626&Signature=DHlOeWd4QladLc6hsdoqp9lTbvMXs06B6hOkQPviFubszuLfahXXRv9aj%2FPTTlytlTClXHX0zGFr3Tsq9S%2Fs3hFjqBsy7lho%2BfuRFhPG4FrQoV2lxrZmB47X6nWc7TG6hbgLkyT3CvAOfwccmWHH1cbBiEDSI0iEKvx7kwUsgIrYu1ko9Szkul29fjVQ89WL6jyQQX1G9ejsQTNmXHFNRvhwRHkRfZJ5n3Y1uR7aqAyMZfQ2Me6i7bVb7smc0t5Ed2yk6%2BN1fdrz6zhbkc%2Fuh13vWhrT8EWMuCYKhsrzPakO%2B%2B229nlt5Y4D9zyFqevAmj43Vl76INIq29gcs39oQg%3D%3D" processing_time: 2311 processing_id: "cd185dd4-fcfb-4b15-93de-db9eded23ade" processing_count: 2 '400': description: > Bad Request. This mostly happens because of invalid image sizes. Neither `height` nor `width` of the image should be less than 128px. Only one of the sides of the image should be greater than or equal to 512px. (Eg: 512x512, 512x768, 768x512) Maximum dimensions supported is 512x896. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/images/upscale/v3: post: summary: Upscale an image using ImageCon V3 description: > This endpoint is used to upscale an existing image using AI. It can take scale inputs of upto a combination of 4194304px. It accepts a Form Data containing the image modification parameters and returns the upscaled image. operationId: upscaleImageV3 tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: multi-part/form-data: schema: type: object properties: existing_image: type: string format: binary description: The image to be modified or edited. Keep in mind that the File Object dimensions should not exceed `1024x1024`. Also, the resulting image dimensions will not exceed `2048x2048`. output_type: type: string description: > The type of output to be generated. You can choose between `url` and `blob` . `URL` will return a cloud-hosted Temporary URL for the generated image, you need to handle the image download on your end. `blob` will return the image as a base64 encoded string. enum: - url - blob scale: type: number description: > The scale to be applied to the image. It is a number between 1 and maximum of 5. The higher the number, the more the image will be upscaled. example: existing_image: "/path/to/image.jpg" output_type: "url" scale: 2 responses: '200': description: Image generated successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the image generation. image: type: string description: The generated image. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" image: "https://storage.googleapis.com/1fe0a9ac-617a-42e4-a376-37808b98fc99-worqhat/image-gen/MFl2oNxrMLYKvWbwoDkbQPpScWD3-1697226444718.png?GoogleAccessId=cloud-storage-upload%40worqhat-dev.iam.gserviceaccount.com&Expires=1697226626&Signature=DHlOeWd4QladLc6hsdoqp9lTbvMXs06B6hOkQPviFubszuLfahXXRv9aj%2FPTTlytlTClXHX0zGFr3Tsq9S%2Fs3hFjqBsy7lho%2BfuRFhPG4FrQoV2lxrZmB47X6nWc7TG6hbgLkyT3CvAOfwccmWHH1cbBiEDSI0iEKvx7kwUsgIrYu1ko9Szkul29fjVQ89WL6jyQQX1G9ejsQTNmXHFNRvhwRHkRfZJ5n3Y1uR7aqAyMZfQ2Me6i7bVb7smc0t5Ed2yk6%2BN1fdrz6zhbkc%2Fuh13vWhrT8EWMuCYKhsrzPakO%2B%2B229nlt5Y4D9zyFqevAmj43Vl76INIq29gcs39oQg%3D%3D" processing_time: 2311 processing_id: "cd185dd4-fcfb-4b15-93de-db9eded23ade" processing_count: 2 '400': description: > Bad Request. This mostly happens because of invalid image sizes. Valid dimensions are `1024x1024`, `1152x896`, `1216x832`, `1344x768`, `1536x640`, `640x1536`, `768x1344`, `832x1216`, `896x1152`. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/images/modify/v3: post: summary: Modify existing image using ImageCon V3 description: > This endpoint is used to modify an existing image using AI. It accepts a Form Data containing the image modification parameters and returns the modified image. operationId: modifyImageV3 tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: multi-part/form-data: schema: type: object properties: existing_image: type: string format: binary description: The image to be modified or edited. Valid dimensions are `1024x1024`, `1152x896`, `1216x832`, `1344x768`, `1536x640`, `640x1536`, `768x1344`, `832x1216`, `896x1152`. output_type: type: string description: > The type of output to be generated. You can choose between `url` and `blob` . `URL` will return a cloud-hosted Temporary URL for the generated image, you need to handle the image download on your end. `blob` will return the image as a base64 encoded string. enum: - url - blob modification: type: string description: > The modification to be applied to the image. You can add in the modification parameters as a string based description. similarity: type: number description: > The similarity to be applied to the image. It is a number between 0 and 100. The higher the number, the more similar the image will be to the original. example: existing_image: "/path/to/image.jpg" output_type: "url" modification: "Add a cat to the image" similarity: 50 responses: '200': description: Image generated successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the image generation. image: type: string description: The generated image. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" image: "https://storage.googleapis.com/1fe0a9ac-617a-42e4-a376-37808b98fc99-worqhat/image-gen/MFl2oNxrMLYKvWbwoDkbQPpScWD3-1697226444718.png?GoogleAccessId=cloud-storage-upload%40worqhat-dev.iam.gserviceaccount.com&Expires=1697226626&Signature=DHlOeWd4QladLc6hsdoqp9lTbvMXs06B6hOkQPviFubszuLfahXXRv9aj%2FPTTlytlTClXHX0zGFr3Tsq9S%2Fs3hFjqBsy7lho%2BfuRFhPG4FrQoV2lxrZmB47X6nWc7TG6hbgLkyT3CvAOfwccmWHH1cbBiEDSI0iEKvx7kwUsgIrYu1ko9Szkul29fjVQ89WL6jyQQX1G9ejsQTNmXHFNRvhwRHkRfZJ5n3Y1uR7aqAyMZfQ2Me6i7bVb7smc0t5Ed2yk6%2BN1fdrz6zhbkc%2Fuh13vWhrT8EWMuCYKhsrzPakO%2B%2B229nlt5Y4D9zyFqevAmj43Vl76INIq29gcs39oQg%3D%3D" processing_time: 2311 processing_id: "cd185dd4-fcfb-4b15-93de-db9eded23ade" processing_count: 2 '400': description: > Bad Request. This mostly happens because of invalid image sizes. Valid dimensions are `1024x1024`, `1152x896`, `1216x832`, `1344x768`, `1536x640`, `640x1536`, `768x1344`, `832x1216`, `896x1152`. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/moderation: post: summary: Moderate Text Content using AI description: > This endpoint is used to moderate text content using AI. It accepts a JSON object containing the text moderation parameters and returns the the moderation results. operationId: moderateText tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: text_content: type: string description: The text to be moderated. example: text_content: "This is a sample text to be moderated." responses: '200': description: Text moderated successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. moderation: type: object properties: sexual: type: string hate: type: string harassment: type: string self-harm: type: string sexual/minors: type: string hate/threatening: type: string violence/graphic: type: string self-harm/intent: type: string self-harm/instructions: type: string harassment/threatening: type: string violence: type: string description: The moderation results. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" moderation: sexual: "0.016973" hate: "0.001243" harassment: "0.012784" self-harm: "0.000040" sexual/minors: "0.000049" hate/threatening: "0.000002" violence/graphic: "0.000016" self-harm/intent: "0.000059" self-harm/instructions: "0.000007" harassment/threatening: "0.000002" violence: "0.000333" processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 3 '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/images/v2/image-text-detection: post: summary: Detect and identify text in an image using AI description: > This endpoint is used to modify an existing image using AI. It accepts a Form Data containing the image modification parameters and returns the modified image. operationId: detectTextInImageV2 tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: multi-part/form-data: schema: type: object properties: image: type: string format: binary description: The image to be sent as input. output_type: type: string description: > The type of output to be generated. You can choose between `json` and `text`. `json` will return the text detection results as a JSON object with the scan words marked and positional information. `text` will return the text detection results as a plain text string. enum: - json - text example: image: "/path/to/image.jpg" output_type: "json" responses: 200: description: OK content: application/json: schema: type: object properties: code: type: integer description: The HTTP status code. status: type: string description: Status indicating the success of the response. In case you have an error for `multipart/form-data` requests, try removing the `Content-Type` header. data: type: string description: The response data. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: code: 200 status: 'success' data: 'WorqHat Introduction to WorqHat AI Custom Models Studio' processing_time: 4554 processing_id: '7a07501f-a611-4c19-b5f9-b62e429c54f8' processing_count: 1 '400': description: > Bad Request. This mostly happens because of invalid image sizes. Neither `height` nor `width` of the image should be less than 128px. Only one of the sides of the image should be greater than or equal to 512px. (Eg: 512x512, 512x768, 768x512) Maximum dimensions supported is 512x896. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/images/v2/image-analysis: post: summary: Analyze an image using AI description: > Analyse an Image using AI. This endpoint helps to identify the different objects in the image, classify them and assign them under different aliases. It also analyses the Colour combinations of the different objects, describes the activities and the dominant colours in the image. operationId: analyzeImageV2 tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: multi-part/form-data: schema: type: object properties: images: type: array items: type: string format: binary description: The images to be sent as input. You can pass a maximum of 10 images. output_type: type: string description: > The type of output to be generated. You can choose between `json` and `text`. `json` will return the text detection results as a JSON object with the scan words marked and positional information. `text` will return the text detection results as a plain text string with a proper description of the image and what it contains. enum: - json - text question: type: string description: > The question to be answered by the AI or any specific command you would like the Model to take into consideration while analysing the image. This is an optional parameter. If not provided, the AI will only send a description of the image and what it contains. training_data: type: string description: > The training data to be used for the AI. This is an optional parameter. If not provided, the AI will use the default training data. It is only applicable for Image Analysis process with Text as `output_type`. stream_data: type: boolean description: > Whether to stream the data as it is being generated. If set to true, the response will be streamed as the data is being generated. This is useful when you want to generate a lot of content and want to save the data as it is being generated. You need to handle Server Sent Events for this use case. default: false example: images: ["/path/to/image.jpg", "/path/to/image.jpg"] output_type: "text" question: "What is the name of the person in the image?" training_data: "You are a support for a Blind person. Please describe the image in detail." stream_data: false responses: 200: description: OK content: application/json: schema: type: object properties: code: type: integer description: The HTTP status code. status: type: string description: Status indicating the success of the response. data: type: object properties: analysed_data: type: array items: type: array description: Analyzed data. quality: type: object properties: brightness: type: number description: Brightness value. contrast: type: number description: Contrast value. sharpness: type: number description: Sharpness value. description: Quality information. foreground: type: object properties: dominant_colors: type: array items: type: string description: Dominant colors in the foreground. quality: type: array description: Foreground information. background: type: object properties: dominant_colors: type: array items: type: string description: Dominant colors in the background. quality: type: array description: Background information. primary_colours: type: array items: type: array description: Primary colors. description: The response data. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. example: code: 200 status: 'success' data: analysed_data: [ [ Object ], [ Object ], [ Object ], [ Object ], [ Object ], [ Object ], [ Object ], [ Object ], [ Object ], [ Object ], [ Object ], [ Object ], [ Object ], [ Object ] ] quality: brightness: 74.43968200683594 contrast: 85.29368591308594 sharpness: 44.84498977661133 foreground: dominant_colors: [ Array ] quality: [ Object ] background: dominant_colors: [ Array ] quality: [ Object ] primary_colours: [ [ Object ], [ Object ], [ Object ], [ Object ], [ Object ], [ Object ], [ Object ], [ Object ], [ Object ], [ Object ] ] processing_time: 3193 processing_id: '9a7cc5d3-735a-4299-8d84-1fbaab309ba4' processing_count: 1 '400': description: > Bad Request. This mostly happens because of invalid image sizes. Neither `height` nor `width` of the image should be less than 128px. Only one of the sides of the image should be greater than or equal to 512px. (Eg: 512x512, 512x768, 768x512) Maximum dimensions supported is 512x896. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/images/v2/face-detection: post: summary: Identify Faces and Characteristics in an Image description: > This endpoint is used to identify faces and characteristics in an image. It accepts a Form Data containing the image and returns the the face detection results. operationId: detectFacesInImageV2 tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: multi-part/form-data: schema: type: object properties: image: type: string format: binary description: The image to be sent as input. example: image: "/path/to/image.jpg" responses: '200': description: Successful response content: application/json: schema: type: object properties: code: type: integer example: 200 status: type: string example: success data: type: object properties: analysed_data: type: array items: type: object properties: age_range: type: object properties: high: type: integer example: 26 low: type: integer example: 18 beard: type: object properties: confidence: type: number example: 73.7099380493164 value: type: boolean example: false bounding_box: type: object properties: height: type: number example: 0.22712668776512146 left: type: number example: 0.3961663544178009 top: type: number example: 0.2599637806415558 width: type: number example: 0.22138258814811707 confidence: type: number example: 99.99722290039062 emotions: type: array items: type: object processing_time: type: integer example: 2189 processing_id: type: string example: b577b18e-1313-47d4-a709-ed3bb219ea52 processing_count: type: integer example: 1 '400': description: > Bad Request. This mostly happens because of invalid image sizes. Neither `height` nor `width` of the image should be less than 128px. Only one of the sides of the image should be greater than or equal to 512px. (Eg: 512x512, 512x768, 768x512) Maximum dimensions supported is 512x896. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/images/v2/image-moderation: post: summary: Moderate an Image using AI description: > This endpoint is used to moderate an image using AI. It accepts a Form Data containing the image and returns the the moderation results. operationId: moderateImageV2 tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: multi-part/form-data: schema: type: object properties: image: type: string format: binary description: The image to be sent as input. example: image: "/path/to/image.jpg" responses: '200': description: Successful response content: application/json: schema: type: object properties: code: type: integer example: 200 status: type: string example: success data: type: object properties: analysed_data: type: array items: type: object properties: Confidence: type: number example: 92.51395416259766 Name: type: string example: Revealing Clothes ParentName: type: string example: Suggestive processing_time: type: integer example: 1268 processing_id: type: string example: 492e385b-f1ec-412a-904e-3f55fd36fd86 processing_count: type: integer example: 1 '400': description: > Bad Request. This mostly happens because of invalid image sizes. Neither `height` nor `width` of the image should be less than 128px. Only one of the sides of the image should be greater than or equal to 512px. (Eg: 512x512, 512x768, 768x512) Maximum dimensions supported is 512x896. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/images/v2/facial-comparison: post: summary: Compare two faces using AI description: > This endpoint is used to compare two faces using AI. It returns the matching percentage for all the images that match. It accepts a Form Data containing the two images and returns the the facial comparison results. operationId: compareFacesV2 tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: multi-part/form-data: schema: type: object properties: source_image: type: string format: binary description: The image to be sent as input. target_image: type: string format: binary description: The image to be sent as input. example: source_image: "/path/to/image.jpg" target_image: "/path/to/image.jpg" responses: '200': description: Successful response content: application/json: schema: type: object properties: code: type: integer example: 200 status: type: string example: success data: type: object properties: analysed_data: type: array items: type: object properties: Confidence: type: number example: 92.51395416259766 processing_time: type: integer example: 1268 processing_id: type: string example: 492e385b-f1ec-412a-904e-3f55fd36fd86 processing_count: type: integer example: 1 '400': description: > Bad Request. This mostly happens because of invalid image sizes. Neither `height` nor `width` of the image should be less than 128px. Only one of the sides of the image should be greater than or equal to 512px. (Eg: 512x512, 512x768, 768x512) Maximum dimensions supported is 512x896. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/speech-text: post: summary: Convert Speech to Text using AI description: > This endpoint is used to convert speech to text using AI. It accepts a Form Data containing the audio file and returns the the speech to text conversion results. operationId: speechToText tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: multi-part/form-data: schema: type: object properties: audio: type: string format: binary description: The audio file to be sent as input. The audio file can be of any format. example: audio: "/path/to/audio.mp3" responses: '200': description: Successful response content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the Audio Conversion Process. In case you have an error for `multipart/form-data` requests, try removing the `Content-Type` header. data: type: object properties: text: type: string description: The Extracted Text from the Audio. speaker_labels: type: array properties: speaker: type: string description: The speaker label. text: type: string description: The text associated with the speaker. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" data: text: "This is a sample text to be converted to speech." speaker_labels: [ { speaker: "A", text: "This is a sample text to be converted to speech." } ] processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 12 '400': description: > Bad Request. This mostly happens because of invalid image sizes. Neither `height` nor `width` of the image should be less than 128px. Only one of the sides of the image should be greater than or equal to 512px. (Eg: 512x512, 512x768, 768x512) Maximum dimensions supported is 512x896. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/v2/web-extract: post: summary: Extract text from a web page using AI. description: > This endpoint is used to extract text from a web page using AI. It can take into account all the features such as metadata, inline code, codeblocks, image & html references and other links as well. operationId: extractTextFromWebPageV2 tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: url_path: type: string description: The URL of the web page to be extracted. headline: type: boolean description: Whether to extract the headline of the web page. default: true inline_code: type: boolean description: Whether to extract the inline code of the web page. default: true code_blocks: type: boolean description: Whether to extract the codeblocks of the web page. default: true references: type: boolean description: > Whether to extract the references of images and other external links in the web page. default: true tables: type: boolean description: Whether to extract the tables in the web page. default: true example: url_path: "https://www.worqhat.com" headline: true inline_code: true code_blocks: true references: true tables: true responses: '200': description: Successful response content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the Audio Conversion Process. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. data: type: object properties: text_content: type: string description: The extracted text content from the web page. tags: type: array description: The extracted tags from the web page. items: type: object properties: name: type: string description: The name of the tag. value: type: string description: The value associated with the tag. data: type: object description: Additional data associated with the tag. example: status: "success" data: text_content: | WorqHat 🎉 Our Conversational Language Model WorqBot is now live for Beta use! Try out Now.🤖 Resources APIs Connect your app to WorqHat Documentations Learn how to use our products Changelogs Check what's new Careers Find your dream role Community Connect with other developers, designers, and entrepreneurs Security Our Security Principles and Practices Blog Interviews, tutorials, Updates and more Status Outage updates and announcements Green Initiatives Partnerships to make the World Greener Contact Us Enterprise WorqHat Playground Join Waitlist Careers - Documentation - Changelog - Blogs - Security Subscribe to our newsletter Stay up to date with the latest news and updates from WorqHat. Join us! - LinkedIn > - Instagram - Facebook - Twitter - GitHub © 2023. Winlysis Pvt. Ltd., India All rights reserved. - Terms & Conditions - Privacy Policy - Statu tags: - name: language value: en data: { } - name: thumbnail value: "/resources/WorqHat TM Logo.png" data: { } - name: current_date value: "2023-01-01" data: { } - name: title span: - "0" - "7" span_text: WorqHat value: WorqHat data: { } - name: link span: - "45" - "52" span_text: WorqBot value: "//playground.worqhat.app/worqbot" data: { } - name: image span: - "94" - "94" value: "/resources/WorqHat TM Logo.png" data: alt: WorqHat Logo - name: control span: - "94" - "105" span_text: " Resources " value: " Resources " data: { } - name: subheading span: - "12016" - "12042" span_text: "Future-proof your business" value: "Future-proof your business" data: { } - name: link span: - "12224" - "12238" span_text: "Join Waitlist " value: "https://join.worqhat.com/waitlist" data: { } - name: image span: - "12295" - "12295" value: "/resources/integrations/logo-dropbox-40.svg" data: alt: Dropbox Icon processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 12 '400': description: > Bad Request. This mostly happens because of invalid image sizes. Neither `height` nor `width` of the image should be less than 128px. Only one of the sides of the image should be greater than or equal to 512px. (Eg: 512x512, 512x768, 768x512) Maximum dimensions supported is 512x896. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/v2/pdf-extract: post: summary: Extract text from a PDF using AI. description: > This endpoint is used to extract text from a PDF using AI. Scanning simultaneously across all pages and with the capability to understand human handwriting, this endpoint can extract text from any PDF. operationId: extractTextFromPDFV2 tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: multi-part/form-data: schema: type: object properties: file: type: string format: binary description: The PDF file to be sent as input. example: file: "/path/to/pdf.pdf" responses: '200': description: Successful response content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the PDF Extraction Process. In case you have an error for `multipart/form-data` requests, try removing the `Content-Type` header. data: type: string description: The converted text. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" data: "This is a sample text to be converted." processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 12 '400': description: > Bad Request. This mostly happens because of invalid image sizes. Neither `height` nor `width` of the image should be less than 128px. Only one of the sides of the image should be greater than or equal to 512px. (Eg: 512x512, 512x768, 768x512) Maximum dimensions supported is 512x896. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/list-datasets: get: summary: Retrieves the list of pre-trained datasets description: > This endpoint fetches all the datasets that you have trained along with the dataset IDs and the training status. operationId: listDatasets tags: - AI Dataset Management security: - bearerAuth: [ ] responses: '200': description: Successful response content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the Audio Conversion Process. data: type: array items: type: object properties: dataset_id: type: string example: dataset123 description: The ID of the dataset. dataset_name: type: string example: Dataset 1 description: The name of the dataset. dataset_description: type: string example: This is dataset 1 description: The description of the dataset. training_for: type: string example: Search Models description: The purpose of the dataset. It is usually either for ``Search Models`` or ``Generative Models``. type: type: string example: Self description: The type of the dataset when trained. It holds values as ``Self`` for datasets available to the User and ``Org`` for datasets available to the members of the Organization. dataset_timestamp: type: object properties: _seconds: type: integer example: 1624954636 description: The timestamp of the dataset creation in seconds. _clock_hash: type: integer example: 1634954636579 description: The clock hash of the dataset. Used for making sure all the Machine Learning are in sync with the dataset. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" data: - dataset_id: "dataset123" dataset_name: "Dataset 1" dataset_description: "This is dataset 1" training_for: "Search Models" type: "Self" dataset_timestamp: _seconds: 1624954636 _clock_hash: 1634954636579 processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 12 '400': description: > Bad Request. This mostly happens because of invalid image sizes. Neither `height` nor `width` of the image should be less than 128px. Only one of the sides of the image should be greater than or equal to 512px. (Eg: 512x512, 512x768, 768x512) Maximum dimensions supported is 512x896. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/delete-datasets/{datasetId}: delete: summary: Deletes a pretrained AI Model Dataset description: > This endpoint deletes a pretrained AI Model Dataset. This is a permanent action and cannot be undone. operationId: deleteDataset tags: - AI Dataset Management security: - bearerAuth: [ ] parameters: - in: path name: datasetId description: ID of the dataset to be deleted required: true schema: type: string responses: '200': description: Successful response content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the Audio Conversion Process. data: type: string description: The deletion status of the dataset. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" data: "This is a sample text to be converted." processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 12 '400': description: > Bad Request. This mostly happens because of invalid image sizes. Neither `height` nor `width` of the image should be less than 128px. Only one of the sides of the image should be greater than or equal to 512px. (Eg: 512x512, 512x768, 768x512) Maximum dimensions supported is 512x896. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/content/v2: post: summary: AiCon V2 (Stable) description: > Content Generation AI focused only on Business Content Generation Purpose. Trained on top of actual business and financial data with added data security and privacy. operationId: generateContentV2 tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: question: type: string description: The Text or Command to be processed. preserve_history: type: boolean description: > Whether to preserve the conversation history of the user. If set to true, the conversation history will be preserved and the conversation history will be accepted as `conversation_history` in the request body. conversation_history: type: array description: > The conversation history of the user as an array of objects. Each object should have a `question` and `answer` property as the key and value respectively. items: type: object properties: conversation: type: string description: The conversation between the user and the AI as a key value pair. randomness: type: integer description: > The randomness factor to be used while generating the content. The higher the randomness, the more creative the content will be. The value should be between 0 and 1. `0` means it will be absolutely to the point and stops hallucinations. `1` means it will be completely creative and creates a content surrounding your questions a lot. default: 0.5 training_data: type: string description: > The training data to be used while generating the content. This can be used to pass in smaller content based on how you want the model to behave, and specific behavioural or restrictive traits you want to add. This is optional. stream_data: type: boolean description: > Whether to stream the data as it is being generated. If set to true, the response will be streamed as the data is being generated. This is useful when you want to generate a lot of content and want to save the data as it is being generated. You need to handle Server Sent Events for this use case. default: false response_type: type: string description: > The type of output to be generated. You can choose between `json` and `text`. `json` will return the text detection results as a JSON object that is parseable. `text` will return the text results as a plain text string. enum: - json - text default: text example: question: "What is the capital of India?" preserve_history: true randomness: 0.5 stream_data: false conversation_history: [ { "What is the capital of India?": "New Delhi" }, { "What is the capital of USA?": "Washington DC" }] training_data: 'You are alex and you are one of the best Tour Guides.' response_type: text responses: '200': description: Text Content Generated Successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. content: type: string description: The text content generated. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" processing_time: 888 content: > "Hello! My name is Alex, and I am your tour guide. I am here to assist you and provide you with information about the places we will be visiting. If you have any questions or need any help during our tour, feel free to ask. I'm here to make your experience enjoyable and memorable. Let's have a great time exploring together" processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/content/v2/{modelId}: post: summary: AiCon V2 Fine Tuned(Stable) description: > Content Generation AI focused only on Business Content Generation Purpose. Trained on top of actual business and financial data with added data security and privacy. operationId: generateContentV2FineTuned tags: - AI Services security: - bearerAuth: [ ] parameters: - name: modelId in: path required: true description: The ID of the model to use. schema: type: string requestBody: required: true content: application/json: schema: type: object properties: question: type: string description: The Text or Command to be processed. preserve_history: type: boolean description: > Whether to preserve the conversation history of the user. If set to true, the conversation history will be preserved and the conversation history will be accepted as `conversation_history` in the request body. conversation_history: type: array description: > The conversation history of the user as an array of objects. Each object should have a `question` and `answer` property as the key and value respectively. items: type: object properties: conversation: type: string description: The conversation between the user and the AI as a key value pair. randomness: type: integer description: > The randomness factor to be used while generating the content. The higher the randomness, the more creative the content will be. The value should be between 0 and 1. `0` means it will be absolutely to the point and stops hallucinations. `1` means it will be completely creative and creates a content surrounding your questions a lot. default: 0.5 training_data: type: string description: > The training data to be used while generating the content. This can be used to pass in smaller content based on how you want the model to behave, and specific behavioural or restrictive traits you want to add. This is optional. stream_data: type: boolean description: > Whether to stream the data as it is being generated. If set to true, the response will be streamed as the data is being generated. This is useful when you want to generate a lot of content and want to save the data as it is being generated. You need to handle Server Sent Events for this use case. default: false response_type: type: string description: > The type of output to be generated. You can choose between `json` and `text`. `json` will return the text detection results as a JSON object that is parseable. `text` will return the text results as a plain text string. enum: - json - text default: text sources: type: boolean description: > Whether to return the sources of the content. If set to true, the sources will be returned. default: false example: question: "What is the capital of India?" preserve_history: true randomness: 0.5 stream_data: false conversation_history: [ { "What is the capital of India?": "New Delhi" }, { "What is the capital of USA?": "Washington DC" }] training_data: 'You are alex and you are one of the best Tour Guides.' response_type: text sources: true responses: '200': description: Text Content Generated Successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. content: type: string description: The text content generated. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" processing_time: 888 content: > "Hello! My name is Alex, and I am your tour guide. I am here to assist you and provide you with information about the places we will be visiting. If you have any questions or need any help during our tour, feel free to ask. I'm here to make your experience enjoyable and memorable. Let's have a great time exploring together" processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/content/v3: post: summary: AiCon V3 (Advanced) description: > Content Generation AI focused only on Business Content Generation Purpose. Trained on top of actual business and financial data with added data security and privacy. This is one of our best and largest models capable of highly creative content and complex situational thinking. operationId: generateContentV3 tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: question: type: string description: The Text or Command to be processed. preserve_history: type: boolean description: > Whether to preserve the conversation history of the user. If set to true, the conversation history will be preserved and the conversation history will be accepted as `conversation_history` in the request body. conversation_history: type: array description: > The conversation history of the user as an array of objects. Each object should have a `question` and `answer` property as the key and value respectively. items: type: object properties: conversation: type: string description: The conversation between the user and the AI as a key value pair. randomness: type: integer description: > The randomness factor to be used while generating the content. The higher the randomness, the more creative the content will be. The value should be between 0 and 1. `0` means it will be absolutely to the point and stops hallucinations. `1` means it will be completely creative and creates a content surrounding your questions a lot. default: 0.5 training_data: type: string description: > The training data to be used while generating the content. This can be used to pass in smaller content based on how you want the model to behave, and specific behavioural or restrictive traits you want to add. This is optional. stream_data: type: boolean description: > Whether to stream the data as it is being generated. If set to true, the response will be streamed as the data is being generated. This is useful when you want to generate a lot of content and want to save the data as it is being generated. You need to handle Server Sent Events for this use case. default: false response_type: type: string description: > The type of output to be generated. You can choose between `json` and `text`. `json` will return the text detection results as a JSON object that is parseable. `text` will return the text results as a plain text string. enum: - json - text default: text example: question: "What is the capital of India?" preserve_history: true randomness: 0.5 stream_data: false conversation_history: [ { "What is the capital of India?": "New Delhi" }, { "What is the capital of USA?": "Washington DC" }] training_data: 'You are alex and you are one of the best Tour Guides.' response_type: text responses: '200': description: Text Content Generated Successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. content: type: string description: The text content generated. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" processing_time: 888 content: > "Hello! My name is Alex, and I am your tour guide. I am here to assist you and provide you with information about the places we will be visiting. If you have any questions or need any help during our tour, feel free to ask. I'm here to make your experience enjoyable and memorable. Let's have a great time exploring together" processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/content/v3/{modelId}: post: summary: AiCon V3 (Advanced) description: > Content Generation AI focused only on Business Content Generation Purpose. Trained on top of actual business and financial data with added data security and privacy. This is one of our best and largest models capable of highly creative content and complex situational thinking. operationId: generateContentV3FineTuned tags: - AI Services security: - bearerAuth: [ ] parameters: - name: modelId in: path required: true description: The ID of the model to use. schema: type: string requestBody: required: true content: application/json: schema: type: object properties: question: type: string description: The Text or Command to be processed. preserve_history: type: boolean description: > Whether to preserve the conversation history of the user. If set to true, the conversation history will be preserved and the conversation history will be accepted as `conversation_history` in the request body. conversation_history: type: array description: > The conversation history of the user as an array of objects. Each object should have a `question` and `answer` property as the key and value respectively. items: type: object properties: conversation: type: string description: The conversation between the user and the AI as a key value pair. randomness: type: integer description: > The randomness factor to be used while generating the content. The higher the randomness, the more creative the content will be. The value should be between 0 and 1. `0` means it will be absolutely to the point and stops hallucinations. `1` means it will be completely creative and creates a content surrounding your questions a lot. default: 0.5 training_data: type: string description: > The training data to be used while generating the content. This can be used to pass in smaller content based on how you want the model to behave, and specific behavioural or restrictive traits you want to add. This is optional. stream_data: type: boolean description: > Whether to stream the data as it is being generated. If set to true, the response will be streamed as the data is being generated. This is useful when you want to generate a lot of content and want to save the data as it is being generated. You need to handle Server Sent Events for this use case. default: false response_type: type: string description: > The type of output to be generated. You can choose between `json` and `text`. `json` will return the text detection results as a JSON object that is parseable. `text` will return the text results as a plain text string. enum: - json - text default: text sources: type: boolean description: > Whether to return the sources of the content. If set to true, the sources will be returned. default: false example: question: "What is the capital of India?" preserve_history: true randomness: 0.5 stream_data: false conversation_history: [ { "What is the capital of India?": "New Delhi" }, { "What is the capital of USA?": "Washington DC" }] training_data: 'You are alex and you are one of the best Tour Guides.' response_type: text sources: true responses: '200': description: Text Content Generated Successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. content: type: string description: The text content generated. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. sources: type: array description: The sources that the AI referred to in order to generate the content, including citations. example: status: "success" processing_time: 888 content: > "Hello! My name is Alex, and I am your tour guide. I am here to assist you and provide you with information about the places we will be visiting. If you have any questions or need any help during our tour, feel free to ask. I'm here to make your experience enjoyable and memorable. Let's have a great time exploring together" processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/content/v3/alpha: post: summary: AiCon V3 Alpha description: > AiCon V3 Alpha is an online LLM designed specifically for Business Content Generation. It leverages live access to online data, ensuring the content it generates is not only highly creative and capable of complex situational thinking but also up-to-date. Trained on a foundation of actual business and financial data, with an emphasis on data security and privacy, AiCon V3 Alpha stands out as one of our most advanced models. Importantly, it provides citations for all sources referred to, enhancing transparency and reliability by linking back to the original data it has accessed. operationId: generateContentV3Alpha tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: question: type: string description: The Text or Command to be processed. preserve_history: type: boolean description: > Whether to preserve the conversation history of the user. If set to true, the conversation history will be preserved and the conversation history will be accepted as `conversation_history` in the request body. conversation_history: type: array description: > The conversation history of the user as an array of objects. Each object should have a `question` and `answer` property as the key and value respectively. items: type: object properties: conversation: type: string description: The conversation between the user and the AI as a key value pair. randomness: type: integer description: > The randomness factor to be used while generating the content. The higher the randomness, the more creative the content will be. The value should be between 0 and 1. `0` means it will be absolutely to the point and stops hallucinations. `1` means it will be completely creative and creates a content surrounding your questions a lot. default: 0.5 training_data: type: string description: > The training data to be used while generating the content. This can be used to pass in smaller content based on how you want the model to behave, and specific behavioural or restrictive traits you want to add. This is optional. stream_data: type: boolean description: > Whether to stream the data as it is being generated. If set to true, the response will be streamed as the data is being generated. This is useful when you want to generate a lot of content and want to save the data as it is being generated. You need to handle Server Sent Events for this use case. default: false response_type: type: string description: > The type of output to be generated. You can choose between `json` and `text`. `json` will return the text detection results as a JSON object that is parseable. `text` will return the text results as a plain text string. enum: - json - text default: text example: question: "What is the capital of India?" preserve_history: true randomness: 0.5 stream_data: false conversation_history: [ { "What is the capital of India?": "New Delhi" }, { "What is the capital of USA?": "Washington DC" }] training_data: 'You are alex and you are one of the best Tour Guides.' response_type: text responses: '200': description: Text Content Generated Successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. content: type: string description: The text content generated. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. sources: type: array description: The sources that the AI referred to in order to generate the content, including citations. items: type: object properties: title: type: string description: The title of the source. url: type: string description: The URL of the source. description: type: string description: A brief description of the source. favicon: type: string description: The favicon URL of the source's website. example: status: "success" processing_time: 888 content: > "Hello! My name is Alex, and I am your tour guide. I am here to assist you and provide you with information about the places we will be visiting. If you have any questions or need any help during our tour, feel free to ask. I'm here to make your experience enjoyable and memorable. Let's have a great time exploring together" processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 sources: [ { title: "Wikipedia", url: "https://en.wikipedia.org/wiki/India", description: "Wikipedia is a free online encyclopedia, created and edited by volunteers around the world and hosted by the Wikimedia Foundation.", favicon: "https://en.wikipedia.org/static/favicon/wikipedia.ico" } ] '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/collections/create: post: summary: Create Database Collection description: > Create a Database Collection for your Organization. Each collection stores your data in the form of Documents which are structures of JSON Objects. You can run complex Queries on all the data that is present in a Collection. operationId: createDatabaseCollection tags: - Database Management security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: collection: type: string description: The Name of the Collection or the Group where you want to store all your data. collectionSchema: type: object description: > The Schema of the Collection. This is used to validate the data that is being stored in the Collection. **_This is optional_**. You can pass in the variables on how you want to structure the data as. We currently support Data Types such as `string`, `number`, `float`, `boolean`, `date`, `timestamp`, `json`, `map`, `array`, `geopoint`, `uuid`, `ip`. collectionSortBy: type: string description: > The Field by which you want to sort the data in the Collection. **_This is optional_**. By default we will sort it by the Document Creation Time of the data that you add. example: collection: "Users" collectionSchema: name: "string" age: "number" weight: "float" is_active: "boolean" date_of_birth: "date" timestamp: "timestamp" address: "json" hobbies: "array" location: "geopoint" id: "uuid" ip_address: "ip" collectionSortBy: "name" responses: '200': description: Output from the Database Creation Process content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. database: type: object properties: collection: type: string description: The Name of the Collection or the Group where you want to store all your data. elapsed_time: type: integer description: The time taken to process the request, in milliseconds. example: status: "success" processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 database: collection: "Users" elapsed_time: 800 '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/collections/data/fetch/all: post: summary: Fetch All Data from a Collection description: > Fetch all the data from a Collection. This is useful when you want to fetch all the data from a Collection and perform some operations on it. operationId: fetchAllDataFromCollection tags: - Database Management security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: collection: type: string description: The Name of the Collection or the Group where you want to store all your data. outputType: type: string description: The type of output you want. `json` will return the data as a JSON object that is parseable. `stream` will return the data as a stream of data and `file` will return the data as a parseable CSV file. enum: - "json" - "stream" - "file" example: collection: "Users" outputType: "json" responses: '200': description: Output from the Database Collection Fetch Process content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. data: type: object properties: databaseId: type: string description: The ID of the Database where the data is stored. collection: type: string description: The Name of the Collection or the Group where you want to store all your data. elapsed_time: type: integer description: The time taken to process the request, in milliseconds. data: type: array items: type: object properties: sampleDbContent: type: string description: The data that is stored in the Collection. sampleDbContent2: type: string description: The data that is stored in the Collection. example: status: "success" processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 data: databaseId: "1234567890" collection: "Users" elapsed_time: 800 data: - sampleDbContent: "This is a sample content" sampleDbContent2: "This is a sample content 2" - sampleDbContent: "This is a sample content" sampleDbContent2: "This is a sample content 2" '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/collections/fetch-all: post: summary: Fetch All Collections from a Database description: > Fetch all the Collections from a Database. This is useful when you want to fetch all the Collections from a Database and perform some operations on it. operationId: fetchAllCollections tags: - Database Management security: - bearerAuth: [ ] responses: '200': description: Output from the Database Collection Fetch Process content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. data: type: object properties: databaseId: type: string description: The ID of the Database where the data is stored. elapsed_time: type: integer description: The time taken to process the request, in milliseconds. collections: type: array items: type: object properties: name: type: string description: The Name of the Collection or the Group where you want to store all your data. example: status: "success" processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 data: databaseId: "1234567890" elapsed_time: 800 collections: - name: "Users" - name: "Posts" '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/collections/data/fetch/document: post: summary: Fetch a Document from a Collection description: > Fetch a Document from a Collection. This is useful when you want to fetch a specific Document from a Collection and perform some operations on it. operationId: fetchDocumentFromCollection tags: - Database Management security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: collection: type: string description: The Name of the Collection or the Group where you want to store all your data. documentId: type: string description: The ID of the Document that you want to fetch. example: collection: "Users" documentId: "1234567890" responses: '200': description: Output from the Database Collection Fetch Process content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. data: type: object properties: databaseId: type: string description: The ID of the Database where the data is stored. collection: type: string description: The Name of the Collection or the Group where you want to store all your data. elapsed_time: type: integer description: The time taken to process the request, in milliseconds. data: type: array items: type: object properties: sampleDbContent: type: string description: The data that is stored in the Collection. sampleDbContent2: type: string description: The data that is stored in the Collection. example: status: "success" processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 data: databaseId: "1234567890" collection: "Users" elapsed_time: 800 data: - sampleDbContent: "This is a sample content" sampleDbContent2: "This is a sample content 2" - sampleDbContent: "This is a sample content" sampleDbContent2: "This is a sample content 2" '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/collections/data/fetch/count: post: summary: Fetch the Count of Documents with a Not-Null Field/Key in a Collection description: > Fetch the Count of Documents in a Collection. This is to fetch the number of Documents that have a specific Field/Key that is not null. operationId: fetchCountOfDocumentsInCollection tags: - Database Management security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: collection: type: string description: The Name of the Collection or the Group where you want to store all your data. key: type: string description: The Field/Key that you want to check for. example: collection: "Users" key: "name" responses: '200': description: Output from the Database Collection Fetch Process content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. data: type: object properties: databaseId: type: string description: The ID of the Database where the data is stored. collection: type: string description: The Name of the Collection or the Group where you want to store all your data. elapsed_time: type: integer description: The time taken to process the request, in milliseconds. data: type: string description: The Count of Documents with a Not-Null Field/Key in a Collection example: status: "success" processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 data: databaseId: "1234567890" collection: "Users" elapsed_time: 800 data: 124 '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/collections/data/fetch/unique: post: summary: Fetch the Unique Values of a Field/Key in a Collection (Sortable) description: > Fetch the Unique Values of a Field/Key in a Collection. You can also sort the response in a specific order of `asc` or `desc` on the basis of the Field/Key that you pass in. operationId: fetchUniqueValuesOfFieldInCollection tags: - Database Management security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: collection: type: string description: The Name of the Collection or the Group where you want to store all your data. key: type: string description: The Field/Key that you want to check unique values for. orderBy: type: string description: > The Field/Key that you want to sort the response by. This is optional. By default we will sort it by the Field/Key that you pass in `key`. If you add a `orderBy` Field/Key, we will sort the response by that Field/Key. orderType: type: string enum: [asc, desc] description: > The Order Type that you want to sort the response by. This is optional. By default we will sort it in `asc` order. If you add a `orderType` Field/Key, we will sort the response by that Order Type on the `orderBy` Field/Key. example: collection: "Users" key: "name" orderBy: "age" orderType: "desc" responses: '200': description: Output from the Database Collection Fetch Process content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. data: type: object properties: databaseId: type: string description: The ID of the Database where the data is stored. collection: type: string description: The Name of the Collection or the Group where you want to store all your data. elapsed_time: type: integer description: The time taken to process the request, in milliseconds. data: type: array items: type: object properties: sampleDbContent: type: string description: The data that is stored in the Collection. example: status: "success" processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 data: databaseId: "1234567890" collection: "Users" elapsed_time: 800 data: - sampleDbContent: "This is a sample content" sampleDbContent2: "This is a sample content 2" '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/collections/data/fetch/query: post: summary: Run Simple and Compound Queries on a Collection description: > Run Simple and Compound Queries on a Collection. You can run a simple `WHERE` query or a compound `AND` or `OR` query on a Collection. This is useful when you want to fetch a specific Document from a Collection and perform some operations on it. You can also sort the response in a specific order of `asc` or `desc` on the basis of the Field/Key that you pass in and limit the number of Documents that you want to fetch. operationId: fetchDocumentFromCollectionQuery tags: - Database Management security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: collection: type: string description: The Name of the Collection or the Group where you want to store all your data. queries: type: array description: > The Queries that you want to run on the Collection. You can run a simple `WHERE` query or a compound `AND` or `OR` using the `join` query parameter on a Collection. items: type: object properties: field: type: string description: The Field/Key that you want to run the query on. operator: type: string enum: ["<", "<=", "==", ">", ">=", "!=", "less than", "less than or equal to", "equal to", "greater than", "greater than or equal to", "not equal to"] description: > The Operator that you want to run the query with. This is optional. By default we will run the query with the `==` operator. If you add a `operator` Field/Key, we will run the query with that Operator. value: type: string description: > The Value that you want to run the query with. This is optional. By default we will run the query with the `==` operator. If you add a `value` Field/Key, we will run the query with that Value. compounding: type: string enum: ["and", "or"] description: > The Compounding Operator that you want to run the query with. This is optional. By default we will run the query with the `and` operator if you pass multiple queries. If you add a `compounding` parameter, we will run the query with that Compounding Operator. orderBy: type: string description: > The Field/Key that you want to sort the response by. This is optional. By default we will sort it by the Field/Key that you pass in as default orderBy value when collection was created. If you add a `orderBy` Field/Key, we will sort the response by that Field/Key. orderType: type: string enum: [asc, desc] description: > The Order Type that you want to sort the response by. This is optional. By default we will sort it in `asc` order. If you add a `orderType` Field/Key, we will sort the response by that Order Type on the `orderBy` Field/Key. limit: type: integer description: > The Limit of the number of Documents that you want to fetch. This is optional. By default we will fetch all the Documents that match the query. If you add a `limit` Field/Key, we will limit the response by that number. startAfter: type: string description: > The number of documents to skip. This is optional. By default we will not skip any documents. If you add a `startAfter` value, we will skip the number of documents that you pass in. outputType: type: string description: The type of output you want. `json` will return the data as a JSON object that is parseable. `stream` will return the data as a stream of data and `file` will return the data as a parseable CSV file. enum: - "json" - "stream" - "file" example: collection: "Users" queries: - field: "name" operator: "equal to" value: "Alex" - field: "age" operator: "greater than" value: 18 compounding: "and" orderBy: "age" orderType: "desc" limit: 10 startAfter: 5 outputType: "json" responses: '200': description: Output from the Database Collection Fetch Process content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. data: type: object properties: databaseId: type: string description: The ID of the Database where the data is stored. collection: type: string description: The Name of the Collection or the Group where you want to store all your data. elapsed_time: type: integer description: The time taken to process the request, in milliseconds. data: type: array items: type: object properties: sampleDbContent: type: string description: The data that is stored in the Collection. sampleDbContent2: type: string description: The data that is stored in the Collection. example: status: "success" processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 data: databaseId: "1234567890" collection: "Users" elapsed_time: 800 data: - sampleDbContent: "This is a sample content" sampleDbContent2: "This is a sample content 2" - sampleDbContent: "This is a sample content" sampleDbContent2: "This is a sample content 2" '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/collections/data/fetch/natural-query: post: summary: Run Natural Language Queries on a Collection description: > Run Natural Language Queries on a Collection. Describe the data that you want to fetch from a Collection in a natural language format and we will run the query for you. operationId: fetchDocumentFromCollectionNLQ tags: - Database Management security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: collection: type: string description: The Name of the Collection or the Group where you want to store all your data. query: type: string description: > The Query that you want to run on the Collection. Describe the data that you want to fetch from a Collection in a natural language format and we will run the query for you. outputType: type: string description: The type of output you want. `json` will return the data as a JSON object that is parseable. `stream` will return the data as a stream of data and `file` will return the data as a parseable CSV file. enum: - "json" - "stream" - "file" example: collection: "Users" query: "Fetch all the users with age greater than 18" outputType: "json" responses: '200': description: Output from the Database Collection Fetch Process content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. data: type: object properties: databaseId: type: string description: The ID of the Database where the data is stored. collection: type: string description: The Name of the Collection or the Group where you want to store all your data. elapsed_time: type: integer description: The time taken to process the request, in milliseconds. data: type: array items: type: object properties: sampleDbContent: type: string description: The data that is stored in the Collection. sampleDbContent2: type: string description: The data that is stored in the Collection. example: status: "success" processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 data: databaseId: "1234567890" collection: "Users" elapsed_time: 800 data: - sampleDbContent: "This is a sample content" sampleDbContent2: "This is a sample content 2" - sampleDbContent: "This is a sample content" sampleDbContent2: "This is a sample content 2" '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/collections/data/add: post: summary: Add Documents to a Collection description: > Add Documents to a Collection. You can add your documents to a Collection using this endpoint in the form of Json. operationId: addDocumentToCollection tags: - Database Management security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: collection: type: string description: The Name of the Collection or the Group where you want to store all your data. docId: type: string description: The ID of the Document that you want to add. **_This is optional_**. If you don't pass a Document ID, we will generate a random ID for you. *Make sure this is unique*. You can add `string` data types as the Document ID, we will convert it automatically. data: description: > The Data that you want to store in the Collection. You can add your documents to a Collection using this endpoint in the form of `JSON` objects in NoSQL. type: object properties: sampleDbContent: type: string description: The data that you want to store in the Collection. sampleDbContent2: type: string description: The data that you want to store in the Collection. example: collection: "Users" docId: "1234567890" data: sampleDbContent: "This is a sample content" sampleDbContent2: "This is a sample content 2" responses: '200': description: Output from the Database Collection Addition Process content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. data: type: object properties: databaseId: type: string description: The ID of the Database where the data is stored. collection: type: string description: The Name of the Collection or the Group where you want to store all your data. elapsed_time: type: integer description: The time taken to process the request, in milliseconds. documentId: type: string description: The ID of the Document that you added to the Collection. example: status: "success" processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 data: databaseId: "1234567890" collection: "Users" elapsed_time: 800 documentId: "1234567890" '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/collections/data/update: post: summary: Update Documents in a Collection description: > Update the documents in a collection. You can pass in the values as a Collection and we will update the document. SPECIAL CASE: Nested JSON. If you want to update a nested JSON, there are two ways. You can either replace the entire Nested JSON by passing in the New JSON Value or you can replac any specific key in the Nested JSON by passing it in as a dot-notation key value pair. operationId: updateDocumentInCollection tags: - Database Management security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: collection: type: string description: The Name of the Collection or the Group where you want to store all your data. docId: type: string description: The ID of the Document that you want to update. data: description: > The Data that you want to update in the Collection. You can add your documents to a Collection using this endpoint in the form of Json. To update Nested JSONs, you can either pass in the entire Nested JSON or you can pass in the key value pair in the form of dot-notation to update a specific key in the Nested JSON. type: object properties: sampleDbContent: type: string description: The data that you want to store in the Collection. sampleDbContent2: type: string description: The data that you want to store in the Collection. example: collection: "Users" docId: "1234567890" data: sampleDbContent: "This is a sample content" sampleDbContent2: "This is a sample content 2" responses: '200': description: Output from the Database Collection Addition Process content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. data: type: object properties: databaseId: type: string description: The ID of the Database where the data is stored. collection: type: string description: The Name of the Collection or the Group where you want to store all your data. elapsed_time: type: integer description: The time taken to process the request, in milliseconds. documentId: type: string description: The ID of the Document that you added to the Collection. example: status: "success" processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 data: databaseId: "1234567890" collection: "Users" elapsed_time: 800 documentId: "1234567890" '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/collections/data/delete: post: summary: Delete Documents from a Collection description: > Delete a Specific Document from a Collection. You can pass in the Document ID and we will delete the Document from the Collection. operationId: deleteDocumentFromCollection tags: - Database Management security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: collection: type: string description: The Name of the Collection or the Group where you want to store all your data. docId: type: string description: The ID of the Document that you want to update. example: collection: "Users" docId: "1234567890" responses: '200': description: Output from the Database Collection Addition Process content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. data: type: object properties: databaseId: type: string description: The ID of the Database where the data is stored. collection: type: string description: The Name of the Collection or the Group where you want to store all your data. elapsed_time: type: integer description: The time taken to process the request, in milliseconds. documentId: type: string description: The ID of the Document that you added to the Collection. example: status: "success" processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 data: databaseId: "1234567890" collection: "Users" elapsed_time: 800 documentId: "1234567890" '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/collections/data/increment: post: summary: Increment a Number/Numeric Field/Key in a Document description: > Increment a Number/Numeric Field/Key in a Document. You can pass in the Document ID and the Field/Key that you want to increment and we will increment or decrement the value for you. operationId: incrementNumberInDocument tags: - Database Management security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: collection: type: string description: The Name of the Collection or the Group where you want to store all your data. docId: type: string description: The ID of the Document that you want to update. field: type: string description: The Field/Key that you want to increment or decrement. increment: type: integer description: The value that you want to increment or decrement the Field/Key by. You can pass in a `negative` value to decrement the Field/Key and a `positive` value to increment the Field/Key. example: collection: "Users" docId: "1234567890" field: "age" increment: 1 responses: '200': description: Output from the Database Collection Edits Process content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. data: type: object properties: databaseId: type: string description: The ID of the Database where the data is stored. collection: type: string description: The Name of the Collection or the Group where you want to store all your data. elapsed_time: type: integer description: The time taken to process the request, in milliseconds. documentId: type: string description: The ID of the Document that you added to the Collection. example: status: "success" processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 data: databaseId: "1234567890" collection: "Users" elapsed_time: 800 documentId: "1234567890" '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/collections/data/array/update/add: post: summary: Add an Element to an Array in a Document description: > Add an Element to an Array in a Document. You can pass in the Document ID and the Field/Key that you want to add an element to and we will add the element to the Array for you. If the Array does not exist, we will create a new Array and add the element to it. operationId: addElementToArrayInDocument tags: - Database Management security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: collection: type: string description: The Name of the Collection or the Group where you want to store all your data. docId: type: string description: The ID of the Document that you want to update. field: type: string description: The Field/Key that you want to increment or decrement. arrayUnion: type: - string - boolean - number description: The value that you want to add to the Array. example: collection: "Users" docId: "1234567890" field: "identities" arrayUnion: "sfdcsfc" responses: '200': description: Output from the Database Collection Edits Process content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. data: type: object properties: databaseId: type: string description: The ID of the Database where the data is stored. collection: type: string description: The Name of the Collection or the Group where you want to store all your data. elapsed_time: type: integer description: The time taken to process the request, in milliseconds. documentId: type: string description: The ID of the Document that you added to the Collection. example: status: "success" processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 data: databaseId: "1234567890" collection: "Users" elapsed_time: 800 documentId: "1234567890" '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/collections/data/array/update/remove: post: summary: Remove an Element from an Array in a Document description: > Remove an Element from an Array in a Document. You can pass in the Document ID and the Field/Key that you want to remove an element from and we will remove the element from the Array for you. operationId: removeElementFromArrayInDocument tags: - Database Management security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: collection: type: string description: The Name of the Collection or the Group where you want to store all your data. docId: type: string description: The ID of the Document that you want to update. field: type: string description: The Field/Key that you want to increment or decrement. arrayRemove: type: - string - boolean - number description: The value that you want to add to the Array. example: collection: "Users" docId: "1234567890" field: "identities" arrayRemove: "sfdcsfc" responses: '200': description: Output from the Database Collection Edits Process content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. data: type: object properties: databaseId: type: string description: The ID of the Database where the data is stored. collection: type: string description: The Name of the Collection or the Group where you want to store all your data. elapsed_time: type: integer description: The time taken to process the request, in milliseconds. documentId: type: string description: The ID of the Document that you added to the Collection. example: status: "success" processing_time: 888 processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 data: databaseId: "1234567890" collection: "Users" elapsed_time: 800 documentId: "1234567890" '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/datasets/train-datasets: post: summary: Train Custom Datasets for Search and LLM (Language Model) description: > Train Custom Datasets for Search and LLM (Language Model). You can train your own custom datasets for Search and LLM (Language Model) using this endpoint. You can pass in the Dataset Name, the Dataset Type and the Dataset File and we will train the dataset for you. operationId: trainDatasets tags: - AI Dataset Management security: - bearerAuth: [ ] requestBody: required: true content: multi-part/form-data: schema: type: object properties: datasetId: type: string description: The ID of the Dataset that you want to train. This is optional. If you don't pass a Dataset ID, we will generate a random ID for you. *Make sure this is unique*. You can pass in a old id if you want to add in more data to your existing Trained Dataset. dataset_name: type: string description: The Name of the Dataset that you want to train. dataset_type: type: string description: The Type of the Training Dataset after Saving. It can be either `self` or `org`. enum: - self - org json_data: type: string description: The JSON Data that you want to train. You can pass in the JSON Data in the form of a stringified JSON. training_file: type: string format: binary description: The Training File that you want to train. You can pass in the Training File in the form of a CSV or a PDF file. example: datasetId: "1234567890" dataset_name: "Sample Dataset" dataset_type: "self" json_data: "{'data': 'This is a sample data'}" training_file: "sample.csv" responses: '200': description: Successful response content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the Dataset Creation Process. data: type: object properties: dataset_id: type: string description: The ID of the created dataset. dataset_name: type: string description: The name of the created dataset. dataset_description: type: string description: The description of the created dataset. training_for: type: string description: The type of training for the dataset. status: type: string description: The status of the dataset. dataset_timestamp: type: object properties: _seconds: type: integer description: The seconds component of the dataset timestamp. _clock_hash: type: integer description: The clock hash component of the dataset timestamp. description: The information about the created dataset. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" data: dataset_id: "0109c3db-5968-4704-b99e-84d1b8201319" dataset_name: "sampled ataset" dataset_description: "" training_for: "Self" status: "Training" dataset_timestamp: _seconds: 1697742460 _clock_hash: 762483 processing_time: 5359 processing_id: "9cb58eda-8ff3-417c-a5d0-1b427471a3d4" processing_count: 132 '400': description: > Bad Request. This mostly happens because of invalid image sizes. Neither `height` nor `width` of the image should be less than 128px. Only one of the sides of the image should be greater than or equal to 512px. (Eg: 512x512, 512x768, 768x512) Maximum dimensions supported is 512x896. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/search/v2: post: summary: Run a Text AI Based Search on Trained Datasets description: > Run a Text AI Based Search on Trained Datasets. You can run a Text AI Based Search on Trained Datasets using this endpoint. You can pass in the Dataset ID and the Search Query and we will run the search for you. operationId: searchV2 tags: - AI Dataset Management security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: question: type: string description: The Search Query that you want to search for. training_data: type: string description: The ID of the Trained Dataset that you want to search in. example: question: "What is the capital of India?" training_data: "1234567890" responses: '200': description: Successful response content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the request. result: type: array items: type: object properties: sId: type: string description: The ID of the item. type: type: string description: The type of the item. name: type: string description: The name of the item. ppu: type: number description: The price per unit of the item. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. example: status: "success" result: - sId: "07743dc2-2c1f-4b15-919e-7f7aae66586c" type: "donut" name: "Old Fashioned" ppu: 0.55 processing_time: 873 processing_id: "9b174f6d-df21-460d-b81a-72ff3d9b9852" processing_count: 2 '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/search/v3/{datasetId}: post: summary: Run a Context and Meaning Based Search on Trained Datasets description: > Run a Context and Meaning Based Search on Trained Datasets. You can run a Context and Meaning Based Search on Trained Datasets using this endpoint. You can pass in the Dataset ID and the Search Query and we will run the search for you. This is mostly used in cases where you want to build a recommendation engine or suggest people based on meaning and emotional ideas. operationId: searchV3 tags: - AI Dataset Management security: - bearerAuth: [ ] parameters: - name: datasetId in: path required: true description: The ID of the dataset to search. schema: type: string requestBody: required: true content: application/json: schema: type: object properties: question: type: string description: The Search Query that you want to search for. search_count: type: integer description: The number of results that you want to return. example: question: "What is the capital of India?" search_count: 10 responses: '200': description: Successful response content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the request. result: type: array items: type: object properties: results: type: object properties: sId: type: string description: The ID of the item. type: type: string description: The type of the item. name: type: string description: The name of the item. ppu: type: string description: The price per unit of the item. description: The detailed information about the item. distance: type: number description: The distance of the item. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. example: status: "success" result: - results: sId: "07743dc2-2c1f-4b15-919e-7f7aae66586c" type: "donut" name: "Old Fashioned" ppu: "0.55" distance: 0.1902 - results: sId: "59183537-9324-44fd-a1e9-023f6acefc52" type: "donut" name: "Cake" ppu: "0.55" distance: 0.2543 - results: sId: "b29b523e-f5c3-4402-8080-9f3416837a00" type: "donut" name: "Raised" ppu: "0.55" distance: 0.268 processing_time: 3323 processing_id: "4e553b00-1898-4337-8003-291cab2f8a2b" processing_count: 4 '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/images/modify/v3/sketch-image: post: summary: Convert a Sketch Image to a Real Image description: > Convert a Sketch Image to a Real Image using this endpoint. You can pass in the Sketch Image and we will convert it to a Real Image for you. This is mostly used in cases where you want to convert a Sketch Image to a Real Image. This is mostly used in cases where you want to build a recommendation engine or suggest people based on meaning and emotional ideas. operationId: sketchImage tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: multi-part/form-data: schema: type: object properties: existing_image: type: string format: binary description: The image to be modified or edited. Max image size in 1024px`. output_type: type: string description: > The type of output to be generated. You can choose between `url` and `blob` . `URL` will return a cloud-hosted Temporary URL for the generated image, you need to handle the image download on your end. `blob` will return the image as a base64 encoded string. enum: - url - blob description: type: string description: > The description of the modification to be applied to the image. You can add in the modification parameters as a string based description. example: existing_image: "/path/to/image.jpg" output_type: "url" description: "Add a cat to the image" responses: '200': description: Image generated successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the image generation. image: type: string description: The generated image. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" image: "https://storage.googleapis.com/1fe0a9ac-617a-42e4-a376-37808b98fc99-worqhat/image-gen/MFl2oNxrMLYKvWbwoDkbQPpScWD3-1697226444718.png?GoogleAccessId=cloud-storage-upload%40worqhat-dev.iam.gserviceaccount.com&Expires=1697226626&Signature=DHlOeWd4QladLc6hsdoqp9lTbvMXs06B6hOkQPviFubszuLfahXXRv9aj%2FPTTlytlTClXHX0zGFr3Tsq9S%2Fs3hFjqBsy7lho%2BfuRFhPG4FrQoV2lxrZmB47X6nWc7TG6hbgLkyT3CvAOfwccmWHH1cbBiEDSI0iEKvx7kwUsgIrYu1ko9Szkul29fjVQ89WL6jyQQX1G9ejsQTNmXHFNRvhwRHkRfZJ5n3Y1uR7aqAyMZfQ2Me6i7bVb7smc0t5Ed2yk6%2BN1fdrz6zhbkc%2Fuh13vWhrT8EWMuCYKhsrzPakO%2B%2B229nlt5Y4D9zyFqevAmj43Vl76INIq29gcs39oQg%3D%3D" processing_time: 2311 processing_id: "cd185dd4-fcfb-4b15-93de-db9eded23ade" processing_count: 2 '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/images/modify/v3/extend-image: post: summary: Extend an Image's Composition description: > Extend an image's composition using this endpoint. You can pass in an existing image, and we will enhance or extend its composition based on the provided description. This feature is particularly useful for creative projects, design work, or when you need to add more context or elements to an existing image. operationId: extendImage tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: multi-part/form-data: schema: type: object properties: existing_image: type: string format: binary description: The image to be modified or edited.`. output_type: type: string description: > The type of output to be generated. You can choose between `url` and `blob` . `URL` will return a cloud-hosted Temporary URL for the generated image, you need to handle the image download on your end. `blob` will return the image as a base64 encoded string. enum: - url - blob leftExtend: type: integer format: int32 description: Percentage to extend the image on the left side. If the percentage value results in a number that is greater than `512px`, it will default to `512px`. rightExtend: type: integer format: int32 description: Percentage to extend the image on the right side. If the percentage value results in a number that is greater than `512px`, it will default to `512px`. topExtend: type: integer format: int32 description: Percentage to extend the image on the top. If the percentage value results in a number that is greater than `512px`, it will default to `512px`. bottomExtend: type: integer format: int32 description: Percentage to extend the image on the bottom. If the percentage value results in a number that is greater than `512px`, it will default to `512px`. description: type: string description: > The description of the modification to be applied to the image. You can add in the modification parameters as a string based description. example: existing_image: "/path/to/image.jpg" output_type: "url" leftExtend: 10 rightExtend: 10 topExtend: 5 bottomExtend: 5 description: "Extend the image's composition by adding more sky at the top and extending the landscape on the sides." responses: '200': description: Image generated successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the image generation. image: type: string description: The generated image. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" image: "https://storage.googleapis.com/1fe0a9ac-617a-42e4-a376-37808b98fc99-worqhat/image-gen/MFl2oNxrMLYKvWbwoDkbQPpScWD3-1697226444718.png?GoogleAccessId=cloud-storage-upload%40worqhat-dev.iam.gserviceaccount.com&Expires=1697226626&Signature=DHlOeWd4QladLc6hsdoqp9lTbvMXs06B6hOkQPviFubszuLfahXXRv9aj%2FPTTlytlTClXHX0zGFr3Tsq9S%2Fs3hFjqBsy7lho%2BfuRFhPG4FrQoV2lxrZmB47X6nWc7TG6hbgLkyT3CvAOfwccmWHH1cbBiEDSI0iEKvx7kwUsgIrYu1ko9Szkul29fjVQ89WL6jyQQX1G9ejsQTNmXHFNRvhwRHkRfZJ5n3Y1uR7aqAyMZfQ2Me6i7bVb7smc0t5Ed2yk6%2BN1fdrz6zhbkc%2Fuh13vWhrT8EWMuCYKhsrzPakO%2B%2B229nlt5Y4D9zyFqevAmj43Vl76INIq29gcs39oQg%3D%3D" processing_time: 2311 processing_id: "cd185dd4-fcfb-4b15-93de-db9eded23ade" processing_count: 2 '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/images/modify/v3/remove-text: post: summary: Remove Text from an Image description: > Remove text from an image using this endpoint. You can pass in an existing image, and we will process it to remove any textual content. This feature is particularly useful for creating images without distracting text, enhancing visual content for presentations, or any other application where a clean, text-free image is desired. operationId: removeText tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: multi-part/form-data: schema: type: object properties: existing_image: type: string format: binary description: The image to be modified or edited. output_type: type: string description: > The type of output to be generated. You can choose between `url` and `blob` . `URL` will return a cloud-hosted Temporary URL for the generated image, you need to handle the image download on your end. `blob` will return the image as a base64 encoded string. enum: - url - blob example: existing_image: "/path/to/image.jpg" output_type: "url" responses: '200': description: Image generated successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the image generation. image: type: string description: The generated image. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" image: "https://storage.googleapis.com/1fe0a9ac-617a-42e4-a376-37808b98fc99-worqhat/image-gen/MFl2oNxrMLYKvWbwoDkbQPpScWD3-1697226444718.png?GoogleAccessId=cloud-storage-upload%40worqhat-dev.iam.gserviceaccount.com&Expires=1697226626&Signature=DHlOeWd4QladLc6hsdoqp9lTbvMXs06B6hOkQPviFubszuLfahXXRv9aj%2FPTTlytlTClXHX0zGFr3Tsq9S%2Fs3hFjqBsy7lho%2BfuRFhPG4FrQoV2lxrZmB47X6nWc7TG6hbgLkyT3CvAOfwccmWHH1cbBiEDSI0iEKvx7kwUsgIrYu1ko9Szkul29fjVQ89WL6jyQQX1G9ejsQTNmXHFNRvhwRHkRfZJ5n3Y1uR7aqAyMZfQ2Me6i7bVb7smc0t5Ed2yk6%2BN1fdrz6zhbkc%2Fuh13vWhrT8EWMuCYKhsrzPakO%2B%2B229nlt5Y4D9zyFqevAmj43Vl76INIq29gcs39oQg%3D%3D" processing_time: 2311 processing_id: "cd185dd4-fcfb-4b15-93de-db9eded23ade" processing_count: 2 '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/images/modify/v3/remove-background: post: summary: Remove Background from an Image description: > Remove the background from an image using this endpoint. You can pass in an existing image, and we will process it to remove the background. This feature is particularly useful for creating product images for e-commerce, profile pictures without distracting backgrounds, or any other application where a clean, background-free image is desired. operationId: removeBg tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: multi-part/form-data: schema: type: object properties: existing_image: type: string format: binary description: The image to be modified or edited. output_type: type: string description: > The type of output to be generated. You can choose between `url` and `blob` . `URL` will return a cloud-hosted Temporary URL for the generated image, you need to handle the image download on your end. `blob` will return the image as a base64 encoded string. enum: - url - blob example: existing_image: "/path/to/image.jpg" output_type: "url" responses: '200': description: Image generated successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the image generation. image: type: string description: The generated image. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" image: "https://storage.googleapis.com/1fe0a9ac-617a-42e4-a376-37808b98fc99-worqhat/image-gen/MFl2oNxrMLYKvWbwoDkbQPpScWD3-1697226444718.png?GoogleAccessId=cloud-storage-upload%40worqhat-dev.iam.gserviceaccount.com&Expires=1697226626&Signature=DHlOeWd4QladLc6hsdoqp9lTbvMXs06B6hOkQPviFubszuLfahXXRv9aj%2FPTTlytlTClXHX0zGFr3Tsq9S%2Fs3hFjqBsy7lho%2BfuRFhPG4FrQoV2lxrZmB47X6nWc7TG6hbgLkyT3CvAOfwccmWHH1cbBiEDSI0iEKvx7kwUsgIrYu1ko9Szkul29fjVQ89WL6jyQQX1G9ejsQTNmXHFNRvhwRHkRfZJ5n3Y1uR7aqAyMZfQ2Me6i7bVb7smc0t5Ed2yk6%2BN1fdrz6zhbkc%2Fuh13vWhrT8EWMuCYKhsrzPakO%2B%2B229nlt5Y4D9zyFqevAmj43Vl76INIq29gcs39oQg%3D%3D" processing_time: 2311 processing_id: "cd185dd4-fcfb-4b15-93de-db9eded23ade" processing_count: 2 '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/images/modify/v3/replace-background: post: summary: Replace Background from an Image description: > Replace the background from an image using this endpoint. You can pass in an existing image, and we will process it to replace the background. This feature is particularly useful for creating product images for e-commerce, profile pictures without distracting backgrounds, or any other application where a clean, background-free image is desired. operationId: replaceBg tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: multi-part/form-data: schema: type: object properties: existing_image: type: string format: binary description: The image to be modified or edited. output_type: type: string description: > The type of output to be generated. You can choose between `url` and `blob`. `URL` will return a cloud-hosted Temporary URL for the generated image, you need to handle the image download on your end. `blob` will return the image as a base64 encoded string. enum: - url - blob modification: type: string description: > The description of the modification to be applied to the image. This can include instructions or desired outcomes for the image modification process. example: existing_image: "/path/to/image.jpg" output_type: "url" modification: "Create Variation of the Image" responses: '200': description: Image generated successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the image generation. image: type: string description: The generated image. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" image: "https://storage.googleapis.com/1fe0a9ac-617a-42e4-a376-37808b98fc99-worqhat/image-gen/MFl2oNxrMLYKvWbwoDkbQPpScWD3-1697226444718.png?GoogleAccessId=cloud-storage-upload%40worqhat-dev.iam.gserviceaccount.com&Expires=1697226626&Signature=DHlOeWd4QladLc6hsdoqp9lTbvMXs06B6hOkQPviFubszuLfahXXRv9aj%2FPTTlytlTClXHX0zGFr3Tsq9S%2Fs3hFjqBsy7lho%2BfuRFhPG4FrQoV2lxrZmB47X6nWc7TG6hbgLkyT3CvAOfwccmWHH1cbBiEDSI0iEKvx7kwUsgIrYu1ko9Szkul29fjVQ89WL6jyQQX1G9ejsQTNmXHFNRvhwRHkRfZJ5n3Y1uR7aqAyMZfQ2Me6i7bVb7smc0t5Ed2yk6%2BN1fdrz6zhbkc%2Fuh13vWhrT8EWMuCYKhsrzPakO%2B%2B229nlt5Y4D9zyFqevAmj43Vl76INIq29gcs39oQg%3D%3D" processing_time: 2311 processing_id: "cd185dd4-fcfb-4b15-93de-db9eded23ade" processing_count: 2 '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/images/modify/v3/search-replace-image: post: summary: Search and Replace Objects in Image description: > Utilize this endpoint to search for specific objects within an image and replace them with alternative imagery. This powerful feature supports a wide range of applications, from updating product images in e-commerce settings to modifying elements in marketing materials or personal photos, allowing for creative and dynamic image transformations. operationId: searchReplaceObjectsInImage tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: multi-part/form-data: schema: type: object properties: existing_image: type: string format: binary description: The image to be modified or edited. output_type: type: string description: > The type of output to be generated. You can choose between `url` and `blob`. `URL` will return a cloud-hosted Temporary URL for the generated image, you need to handle the image download on your end. `blob` will return the image as a base64 encoded string. enum: - url - blob modification: type: string description: > The description of the modification to be applied to the image. This can include instructions or desired outcomes for the image modification process. search_object: type: string description: > The object or element you want to replace the searched object with. example: existing_image: "/path/to/image.jpg" output_type: "url" modification: "Create Variation of the Image" responses: '200': description: Image generated successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the image generation. image: type: string description: The generated image. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" image: "https://storage.googleapis.com/1fe0a9ac-617a-42e4-a376-37808b98fc99-worqhat/image-gen/MFl2oNxrMLYKvWbwoDkbQPpScWD3-1697226444718.png?GoogleAccessId=cloud-storage-upload%40worqhat-dev.iam.gserviceaccount.com&Expires=1697226626&Signature=DHlOeWd4QladLc6hsdoqp9lTbvMXs06B6hOkQPviFubszuLfahXXRv9aj%2FPTTlytlTClXHX0zGFr3Tsq9S%2Fs3hFjqBsy7lho%2BfuRFhPG4FrQoV2lxrZmB47X6nWc7TG6hbgLkyT3CvAOfwccmWHH1cbBiEDSI0iEKvx7kwUsgIrYu1ko9Szkul29fjVQ89WL6jyQQX1G9ejsQTNmXHFNRvhwRHkRfZJ5n3Y1uR7aqAyMZfQ2Me6i7bVb7smc0t5Ed2yk6%2BN1fdrz6zhbkc%2Fuh13vWhrT8EWMuCYKhsrzPakO%2B%2B229nlt5Y4D9zyFqevAmj43Vl76INIq29gcs39oQg%3D%3D" processing_time: 2311 processing_id: "cd185dd4-fcfb-4b15-93de-db9eded23ade" processing_count: 2 '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' /api/ai/content/v2-large/answering: post: summary: AiCon V2 Large (Based on Custom Trained Datasets) - Question Answering description: > Content Generation AI focused only on Business Content Generation Purpose. Trained on top of actual business and financial data with added data security and privacy. You can also pass in your own custom trained datasets to generate content based on your own data. operationId: aiconV2LargeQuestionAnswering tags: - AI Services security: - bearerAuth: [ ] requestBody: required: true content: application/json: schema: type: object properties: question: type: string description: The Text or Command to be processed. datasetId: type: string description: The ID of the Dataset that you want to use for the Question Answering. preserve_history: type: boolean description: > Whether to preserve the conversation history of the user. If set to true, the conversation history will be preserved and the conversation history will be accepted as `conversation_history` in the request body. conversation_history: type: array description: > The conversation history of the user as an array of objects. Each object should have a `question` and `answer` property as the key and value respectively. items: type: object properties: conversation: type: string description: The conversation between the user and the AI as a key value pair. randomness: type: integer description: > The randomness factor to be used while generating the content. The higher the randomness, the more creative the content will be. The value should be between 0 and 1. `0` means it will be absolutely to the point and stops hallucinations. `1` means it will be completely creative and creates a content surrounding your questions a lot. default: 0.5 instructions: type: string description: > The instructions to be used while generating the content. This can be used to pass in smaller content based on how you want the model to behave, and specific behavioural or restrictive traits you want to add. This is optional. stream_data: type: boolean description: > Whether to stream the data as it is being generated. If set to true, the response will be streamed as the data is being generated. This is useful when you want to generate a lot of content and want to save the data as it is being generated. You need to handle Server Sent Events for this use case. default: false example: question: "What is the capital of India?" datasetId: "1234567890" preserve_history: true randomness: 0.5 stream_data: false conversation_history: [ { "What is the capital of India?": "New Delhi" }, { "What is the capital of USA?": "Washington DC" }] instructions: 'You are alex and you are one of the best Tour Guides.' responses: '200': description: Text Content Generated Successfully content: application/json: schema: type: object properties: status: type: string description: Status indicating the success of the text moderation. content: type: string description: The text content generated. processing_time: type: integer description: The time taken to process the request, in milliseconds. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_count: type: integer description: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes. example: status: "success" processing_time: 888 content: > "Hello! My name is Alex, and I am your tour guide. I am here to assist you and provide you with information about the places we will be visiting. If you have any questions or need any help during our tour, feel free to ask. I'm here to make your experience enjoyable and memorable. Let's have a great time exploring together" processing_id: "4b139bfe-1f71-4345-b539-fa6c1700f166" processing_count: 6554 '400': description: > Bad Request. content: application/json: schema: $ref: '#/components/schemas/Error400Response' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error401Response' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error404Response' '406': description: Not Acceptable content: application/json: schema: $ref: '#/components/schemas/Error406Response' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error500Response' components: securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: 'sk-' schemas: Error400Response: type: object properties: status: type: string description: Status code indicating the error. message: type: string description: A message describing the error. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_time: type: string description: The time taken to process the request, in milliseconds. example: status: "400" message: "Bad Request" processing_id: "123e4567-e89b-12d3-a456-426614174000" processing_time: "343" Error401Response: type: object properties: status: type: string description: Status code indicating the error. message: type: string description: A message describing the error. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_time: type: string description: The time taken to process the request, in milliseconds. example: status: "401" message: "Unauthorized" processing_id: "123e4567-e89b-12d3-a456-426614174000" processing_time: "343" Error406Response: type: object properties: status: type: string description: Status code indicating the error. message: type: string description: A message describing the error. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_time: type: string description: The time taken to process the request, in milliseconds. example: status: "406" message: "Not Acceptable" processing_id: "123e4567-e89b-12d3-a456-426614174000" processing_time: "343" Error404Response: type: object properties: status: type: string description: Status code indicating the error. message: type: string description: A message describing the error. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_time: type: string description: The time taken to process the request, in milliseconds. example: status: "404" message: "Not Found" processing_id: "123e4567-e89b-12d3-a456-426614174000" processing_time: "343" Error500Response: type: object properties: status: type: string description: Status code indicating the error. message: type: string description: A message describing the error. processing_id: type: string description: A universally unique identifier for the request. This can be used to track the request in the logs. processing_time: type: string description: The time taken to process the request, in milliseconds. example: status: "500" message: "Internal Server Error" processing_id: "123e4567-e89b-12d3-a456-426614174000" processing_time: "343"