Method of importation.
Options:
'img\_class\_folder': import as an image classification problem with folder names as image class labels
'img\_csv': import as an image regression or classification problem
with image paths listed in a colmn of a csv and target variables on other column(s)
(required with file\_type : zip)
Path to images from zip file's root
(required with file\_type: zip)
Method of importing target labels or variables
Options:
'binary': The inputter will return binary labels indicating the class membership of each sample
'categorical': The inputter will return one-hot encoded labels, where each class is represented by a binary vector with a single 1 and 0s elsewhere
'sparse': Instead of one-hot encoded labels for a multi-classifcation problem, the inputter will return integer labels for each class
'input': The inputter will return the input images as both the input and output.
'raw': The inputter will return the raw data gotten for the y\_column
Image size in pixels (Length, Width)
(required with file\_type: zip)
Path to CSV from zip file's root
(required with file\_type: zip and method: img\_csv)
Column name of column containing the list of image file names (images within folders aren't allowed)
(required with file\_type: zip and method: img\_csv)
Column names of columns containing target variable(s). Leave empty to include all other columns
(required with file\_type: zip and method: img\_csv)
type of dataset being processed with loaded weights.load\_name required
set's wether or not to drop duplicates during loading modeload\_name required
One-Hot Encoding: Converts categories into binary columns.
Label Encoding: Assigns numbers to categories.
Binary Encoding: Represents categories as binary codes.
Target Encoding: Replaces categories with target stats.
String to Hash Encoding: Hashes strings to numbers.
Extract Numbers Encoding: Converts text numbers to digits.
| | remainder\* | String | applied method to none specified columns; `drop` drops the unspecified columns for encoding, `passthrough` ignores unspecified columns | | index\* | int | column index to apply encoding technique | | save\_name | String | name to save processing models with. | | load\_name | String | name to load processing models with. Used to switch to loading mode | {% tabs %} {% tab title="200: OK Data Encode Successful" %} ```javascript { "status": "true", "message": { "id": 3, "project": 1, "block_id": 3, "parent_id": 2, "dataset_url": "", "x_value_url": "", "y_value_url": "" } } ``` {% endtab %} {% endtabs %} {% tabs %} {% tab title="Python" %} ``` // Some code ``` {% endtab %} {% tab title="Node" %} ``` // Some code ``` {% endtab %} {% endtabs %} # Data Split (DP\_4) This functionality splits data into two subsets: a training set and a test set. The training set is used to train a model, while the test set is used to evaluate its performance. This process of separating data into two sets is a crucial step in the process of developing and evaluating machine learning models. It ensures that the model is able to generalize well to new, unseen data, and it also allows for a more accurate assessment of the model's performance. This functionality of splitting data into training and test sets is widely used in the field of machine learning and data science. ## Sample Request This request uses the mean strategy to fill in missing values in the second column to the end with the mean values of the X variable. ```javascript { "project_id": 1, "parent_id": 3, "block_id": 4, "function_code": "DP_4", "args": { "test_size": 0.3, "random_state": 0 } } ``` ## Splitting Data ## Splits data `POST` `https://autogon.ai/api/v1/engine/start` Splitting data into training and test data. #### Request Body | Name | Type | Description | | ------------------------------------------------ | --------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | project\_id\* | int | current project ID | | parent\_id\* | int | parent block ID | | block\_id\* | int | current block ID | | function\_code\* | String | block's function code | | args | object | block arguments | | test\_size | float/int | If `float`, should be between 0.0 and 1.0 and represent the proportion of the dataset to include in the test split. If `int`, represents the absolute number of test samples. If None, the value is set to the complement of the train size. | | random\_state | int | Controls the shuffling applied to the data before applying the split. | {% tabs %} {% tab title="200: OK Feature Scaling Successful" %} ```javascript { "status": "true", "message": { "id": 4, "project": 1, "block_id": 4, "parent_id": 3, "dataset_url": "", "x_value_url": "", "y_value_url": "", "x_train_url": "", "y_train_url": "", "x_test_url": "", "y_test_url": "" } } ``` {% endtab %} {% endtabs %} {% tabs %} {% tab title="Python" %} ``` // Some code ``` {% endtab %} {% tab title="Node" %} ``` // Some code ``` {% endtab %} {% endtabs %} # Feature Scaling (DP\_5) This functionality normalizes the range of values for different features in the dataset This process is very important because many machine learning algorithms use the Euclidean distance between two points in their computations, and if the ranges of the features are vastly different, then the algorithm will be sensitive to the feature with the larger range, and may produce unexpected results. ## Sample Request This request scales the feature sets defined in the range of columns for training and testing. ```javascript { "project_id": 1, "parent_id": 4, "block_id": 5, "function_code": "DP_5", "args": { "dataset": true, "xtrain": true, "xtest": true, "x": true, "ytrain": true, "ytest": true, "y": true, "scaler": "maxabs", "boundariestoscale": ":, 2:", "save_name": "testweights", "load_name": "testweights" } } ``` ## Missing Data ## Encode categorical values `POST` `https://autogon.ai/api/v1/engine/start` Encodes categorical data on specific columns with specified boundaries #### Request Body | Name | Type | Description | | ------------------------------------------------ | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | project\_id\* | int | current project ID | | parent\_id\* | int | parent block ID | | block\_id\* | int | current block ID | | function\_code\* | String | block's function code | | encode\* | boolean | specify if variable is encoded | | args | object | block arguments | | remainder\* | | applied method to none specified columns; `drop` drops the unspecified columns for encoding, `passthrough` ignores unspecified columns | | index\* | int | column index to apply encoding technique | | scaler | String |Type of scaler to use:'minmax' : transforms data to a 0-1 range.
'standard' : transforms data to have zero mean and unit variance.
'robust' : scaling technique that is less sensitive to outliers in the data.
'maxabs' : scaling technique that scales the data by dividing each feature by its maximum absolute value, preserving the sign of the values while normalizing them.
specifies wether the image array should be scaled between 0-1
Default: true
{
"project_id": 41,
"block_id": 10,
"parent_id": 9,
"function_code": "DP_PCA",
"args": {
"n_components": 3,
"dataset": false,
"xtrain": true,
"xtest": true,
"x": true,
"ytrain": false,
"ytest": false,
"y": false
}
}
int, float or 'mle'
Number of components to keep. If n\_components is not set, all components are kept
Defaults to 'null'
Type of vectorizer to apply:
tfidf : Converts text data into numerical features based on term frequency-inverse document frequency, capturing word importance in documents and across the corpus.
count: Transforms text data into numerical features by counting the occurrences of words
hashing: Uses a hashing trick to map words into fixed-size feature vectors
const project_id = 1
const parent_id = 7
const block_id = 8
decisionTreeRegression= await client.decision_tree_regression(project_id, parent_id, block_id, {
model_name: "SimpleModel",
random_state: 0
});
const project_id = 1
const parent_id = 7
const block_id = 8
kernelSvm = await client.kernel_svm(project_id, parent_id, block_id, {
model_name: "ClassicModel",
kernel: "rbf",
random_state: 0
});
const project_id = 1
const parent_id = 7
const block_id = 8
kernelSvmPredict = await client.kernel_svm_predict(project_id, parent_id, block_id, {
model_name: "ClassicModel",
test_data: ""
});
const project_id = 1
const parent_id = 7
const block_id = 8
decisionTreeClassificationPredict = await client.decision_tree_classification_predict(project_id, parent_id, block_id, {
model_name: "ClassicModel",
test_data: ""
});
const project_id = 1
const parent_id = 7
const block_id = 8
kmeansClustering = await client.xgboost_predict(project_id, parent_id, block_id, {
model_name: "XGBoost",
test_data: ""
});
const project_id = 1
const parent_id = 7
const block_id = 8
decisionTreeRegression = await client.isolation_forest(project_id, parent_id, block_id, {
model_name: "IsolateForest"
});
// Some code
The upsampling factors for rows and columns.
Default: \[2, 2].
| {% tabs %} {% tab title="200 Statemanagement object" %} ```json { "status": "true", "message": { "id": 8, "project": 1, "block_id": 8, "parent_id": 7, "dataset_url": "", "x_value_url": "", "y_value_url": "", "x_train_url": "", "y_train_url": "", "x_test_url": "", "y_test_url": "", "output": {} } } ``` {% endtab %} {% endtabs %} ## Sample Request Compile and train the pre-built ANN model, using passed-in Hyper Parameters ```json { "project_id": 1, "parent_id": 8, "block_id": 9, "function_code": "DL_ANN_T", "args": { "model_name": "titanic_model", "add_dim": false, "hyp_params":{ "optimizer": "adam", "loss": "binary_crossentropy", "metrics": ["accuracy"], "batch_size": 12, "epochs": 5, "autoencoder": false } } } ``` ## Training an Artificial Neural Network ## ANN Training `POST` `https://autogon.ai/api/v1` #### Request Body | Name | Type | Description | | ------------------------------------------------ | ------ | -------------------------------------------------------------------------------- | | project\_id\* | int | The `id` of the current project | | hyp\_params\* | object | hyper parameters for model compilation and training | | parent\_id\* | int | The `id` of the previous block | | block\_id\* | int | The `id` of the current block | | function\_code\* | | The function code for current block | | args\* | object | Block arguments | | model\_name\* | String | The name the model would be saved with | | optimizer | String | Optimization function to be used e.g: `"adam"` | | loss\* | String | Loss function to be used e.g: `"binary_crossentropy"` | | metrics | list | Evaluation metrics used to judge the performance of the model | | batch\_size | String | Number of samples that are processed by the model during each training iteration | | epochs\* | String | Number of iterations through the dataset | | add\_dim | bool | Sets whether an extra dimension should be added to `x` train data | | autoencoder | bool | Specifies whether to use x data as y data | {% tabs %} {% tab title="200: OK Statemanagement Object" %} ```json { "status": "true", "message": { "id": 9, "project": 1, "block_id": 9, "parent_id": 8, "dataset_url": "", "x_value_url": "", "y_value_url": "", "x_train_url": "", "y_train_url": "", "x_test_url": "", "y_test_url": "", "output": {} } } ``` {% endtab %} {% endtabs %} ## Sample Request Evaluate the accuracy and losses of a trained artificial neural network. ```json { "project_id": 1, "parent_id": 8, "block_id": 9, "function_code": "DL_ANN_E", "args": { "hyp_params": { "batch_size": 32 } } } ``` ## Evaluating an Artificial Neural Network ## ANN Evaluating `POST` #### Request Body | Name | Type | Description | | ------------------------------------------------ | ------ | ------------------------------------------------------------------- | | project\_id\* | int | The `id` of the current project | | parent\_id\* | int | The `id` of the previous block | | block\_id\* | int | The `id` of the current block | | function\_code\* | String | Function code for the current block | | args\* | object | Block arguments | | hyp\_params\* | object | hyper parameters for model evaluation | | batch\_size | int | Number of samples that are processed by the model during evaluation | {% tabs %} {% tab title="200: OK Statemanagement object" %} ```json { "status": "true", "message": { "id": 9, "project": 1, "block_id": 9, "parent_id": 8, "dataset_url": "", "x_value_url": "", "y_value_url": "", "x_train_url": "", "y_train_url": "", "x_test_url": "", "y_test_url": "", "output": {} } } ``` {% endtab %} {% endtabs %} ## Sample Request Make predictions with the trained ANN model. ```json { "project_id": 1, "parent_id": 8, "block_id": 9, "function_code": "DL_ANN_P", "args": { "test_data": "" } } ``` ## Predicting with an Artificial Neural Network ## ANN Predict `POST` `https://autogon.ai/api/v1/engine/start` #### Request Body | Name | Type | Description | | ------------------------------------------------ | ------ | ------------------------------------------------------------ | | test\_data | String |Input data for prediction
Defaults to x\_test\_url
Input data for prediction
Defaults to x\_test\_url
List of augmentations to apply.
Default: \["all"]
Equivalent to: \["HorizontalFlip", "VerticalFlip", "Crop", "HueSaturation", "BrightnessContrast", "Blur"]
Number of augmented images to generate per image
Default: 3
String constant of model\_type.
Supported types:'small', 'medium','large'
confidence\_thresh
| Float | Default: 0.5 | | overlap\_thresh | Float | Default: 0.5 | {% tabs %} {% tab title="200: OK " %} ```json { "https://storage.autogon.ai/45c16e3a-924f-4db0-8db7-0b043598f093.jpg": [ { "lbl_id": 0, "lbl": "LP", "bbx": { "x": 59.0321159362793, "y": 434.32745361328125, "w": 267.5981750488281, "h": 140.85491943359375 }, "conf": 0.9056000113487244 }, { "lbl_id": 0, "lbl": "LP", "bbx": { "x": 543.1251220703125, "y": 363.24102783203125, "w": 179.230224609375, "h": 43.1021728515625 }, "conf": 0.7953004240989685 } ] } ``` {% endtab %} {% endtabs %} ## Motion Detection Provides real time, accurate motion tracking for video streams `POST` `http://api.autogon.ai/services/motion-detection/` #### Headers | Name | Type | Description | | ---------------------------------------------- | ------ | ---------------- | | Content-Type\* | String | application/json | #### Request Body | Name | Type | Description | | --------------------------------------- | ---- | --------------------------- | | video\* | File | video file to detect motion | {% tabs %} {% tab title="200: OK " %} ```json { "fps": 12.0, "annotations": { "5": [ { "bbx": { "x": 0, "y": 568, "w": 576, "h": 276 } } ], "6": [ { "bbx": { "x": 34, "y": 708, "w": 110, "h": 86 } }, { "bbx": { "x": 0, "y": 671, "w": 576, "h": 249 } }, { "bbx": { "x": 0, "y": 663, "w": 120, "h": 15 } } ], } } ``` {% endtab %} {% endtabs %} ## Stable Diffusion (Deprecated) Generate Images from Text `POST` `https://api.autogon.ai/api/v1/services/stable-diffusion/` #### Headers | Name | Type | Description | | ---------------------------------------------- | ---- | ---------------- | | Content-Type\* | | application/json | #### Request Body | Name | Type | Description | | -------------------------------------- | ------ | ------------------------------------------ | | text\* | String | Short description of image to be generated | {% tabs %} {% tab title="200: OK " %} ```json { "status": true, "image": "https://test-image.png" } ``` {% endtab %} {% endtabs %} ## Image Captioning (Deprecated) Analyzes an image and generates captions for images `POST` `https://api.autogon.ai/api/v1/services/image-captioning/` #### Headers | Name | Type | Description | | ---------------------------------------------- | ------ | ------------------- | | Content-Type\* | String | multipart/form-data | #### Request Body | Name | Type | Description | | -------------------------------------------- | ------ | --------------------------------------------------------- | | image\* | File | image to be captioned | | image\_url\* | String | url of the image to be captioned (should be downloadable) | {% tabs %} {% tab title="200: OK " %} ```json { "status": true, "message": "a ball with a yellow ball inside of it " } ``` {% endtab %} {% endtabs %} ## Document Question and Answering (Deprecated) Leverage AI models capable of answering questions based on the content of a given document. `POST` `https://api.autogon.ai/api/v1/services/document-qa/` #### Headers | Name | Type | Description | | ---------------------------------------------- | ------ | ------------------- | | Content-Type\* | String | multipart/form-data | #### Request Body | Name | Type | Description | | ------------------------------------------ | ------ | ----------- | | question\* | String | | | document\_url | String | | | document | File | | {% tabs %} {% tab title="200: OK " %} ```json { "status": True, "message": answer } ``` {% endtab %} {% tab title="400: Bad Request " %} ```json { "status": False, "message": error message } ``` {% endtab %} {% endtabs %} ## Visual Question and Answering (Deprecated) Generate accurate answers about an image based on the visual content of the image `POST` `https://api.autogon.ai/api/v1/services/vilt-vq/` #### Headers | Name | Type | Description | | ---------------------------------------------- | ------ | ------------------- | | Content-Type\* | String | multipart/form-data | #### Request Body | Name | Type | Description | | -------------------------------------- | ------ | ----------- | | text\* | String | | | image | File | | | image\_url | String | | {% tabs %} {% tab title="200: OK " %} ```json { "status": true, "message": "very" } ``` {% endtab %} {% endtabs %} # Natural Language AI Fully managed production environment to create your own natural language applications. All endpoints in this collection except that of Chatbot are protected and require authentication using an `X-AUG-KEY` as the authorization header. To authenticate your requests, include an `X-AUG-KEY` header in the following format: ```json X-AUG-KEY: YOUR_API_KEY ``` Replace `YOUR_API_KEY` with your unique API Key created on the [Autogon Console](https://console.autogon.ai/) # Text Classification (Deprecated) This classifies texts based on positivity and negativity with scores for each class. The Text Classification API is a robust tool designed to analyze and classify textual data based on positivity and negativity. This API assigns scores to each class, indicating the degree of positivity or negativity present in the provided text. #### Pricing Requests made to the Text Classification API are billed. Prices are based on the number of characters sent to the service to be classified. The pricing for API requests is as follows: * **Per Request Cost**: 3 units base cost per request. `POST` `https://api.autogon.ai/api/v1/services/text-classification/` #### Headers | Name | Type | Description | | ---------------------------------------------- | ------ | ---------------- | | Content-Type\* | String | application/json | #### Request Body | Name | Type | Description | | -------------------------------------- | ------ | --------------------- | | text\* | String | Text to be classified | {% tabs %} {% tab title="200: OK " %} ```json [ { "label": "POSITIVE", "score": 0.465040385723114 }, { "label": "NEGATIVE", "score": 0.534959614276886 } ] ``` {% endtab %} {% endtabs %} # Text Summary (Deprecated) Summarize natural language with pre-trained text engines. The Text Summary API is a powerful tool designed to generate concise summaries from natural language text. This API utilizes pre-trained text summarization engines to extract essential information and condense lengthy passages into shorter, coherent summaries. The API allows developers to specify the minimum and maximum length of the generated summaries. #### Pricing Requests made to the Text Summary API are billed. Prices are based on the number of characters sent to the service to be summarized. The pricing for API requests is as follows: * **Per Request Cost**: 3 units base cost per request. `POST` `https://api.autogon.ai/api/v1/services/text-summary/` #### Headers | Name | Type | Description | | ---------------------------------------------- | ------ | ---------------- | | Content-Type\* | String | application/json | #### Request Body | Name | Type | Description | | -------------------------------------- | ------- | ------------------------------------------------------------- | | text\* | String | The text to be summarized | | max\_length | Integer | Specifies the maximum length of the summary. Defaults to 130. | | min\_length | Integer | Specifies the minimum length of the summary. Defaults to 30. | {% tabs %} {% tab title="200: OK " %} ```json ``` {% endtab %} {% endtabs %} # Ask Your Data Query your data using natural language. Leverage on artificial intelligence to help you work with your data, ranging from tasks such as data cleansing, data analytics, to data visualization, and more. #### Pricing Requests made to the Ask Your Data API are billed. The pricing for API requests is as follows: * **Per Request Cost**: 3 units base cost per request. `POST` `https://api.autogon.ai/api/v1/services/ask-your-data/` The Ask Your Data API empowers developers to directly query their datasets using natural language without having to use SQL or any programming language. It is recommended you use the [upload](https://docs.autogon.ai/autogon-qore/natural-language-ai/pages/UGxplb3QjCSpqvgd4xY4#uploads-a-dataset.) endpoint with your dataset to generate a dataset URL. #### Headers | Name | Type | Description | | ---------------------------------------------- | ------ | ---------------- | | Content-Type\* | String | application/json | #### Request Body | Name | Type | Description | | ---------------------------------------- | ------ | --------------------------------------------------------- | | data\* | String | URL to dataset to be queried | | prompt\* | String | Query text (Ex: Give me a chart of the first two columns) | {% tabs %} {% tab title="200: OK Signed URL to queried content" %} ```json { "status": true, "data": "" } ``` {% endtab %} {% endtabs %} # Generate Synthetic Data This API is designed to generate synthetic datasets. The Synthetic Data Generation API is a versatile tool designed to create synthetic datasets based on user-defined prompts and specifications regarding the number of rows required. This API allows developers to generate artificial datasets that mimic real-world data while meeting specific criteria provided by the user. #### Pricing Requests made to the Synthetic Data Generation API are billed. The pricing for API requests is as follows: * **Per Request Cost**: 3 units base cost per request. `POST` `https://api.autogon.ai/api/v1/services/generate-data/` This API endpoint takes two json parameters the "prompt", and number of rows as the "rows" parameter respectively #### Headers | Name | Type | Description | | ---------------------------------------------- | ------ | ---------------- | | Content-Type\* | String | application/json | #### Request Body | Name | Type | Description | | ---------------------------------------- | ------ | ------------------------------------------------------------------------------------------------------------------------------------------- | | prompt\* | String | User-defined prompts specifying the structure and characteristics of the dataset. (Ex. "insurance dataset with the columns (name, amount)") | | rows\* | String | Number of rows needed in the generated dataset. | {% tabs %} {% tab title="200: OK Success status and message containing the dataset url" %} ```json { "status": true, "message": "www.generated_dataset_url" } ``` {% endtab %} {% endtabs %} # Speech To Text Convert speech into text using an API powered by the best of AI technologies. The Speech To Text (STT) API is a robust tool designed to convert spoken language into written text. This API empowers developers to integrate speech recognition capabilities into their applications, enabling users to interact with spoken language for various purposes. #### Pricing Requests made to the Speech To Text (STT) API are billed. Prices are based on the number of characters sent to the service to be synthesized into audio. The pricing for API requests is as follows: * **Per Request Cost**: 3 units base cost per request. `POST` `https://api.autogon.ai/api/v1/services/speech-to-text/` #### Headers | Name | Type | Description | | ---------------------------------------------- | ------ | ---------------- | | Content-Type\* | String | application/json | #### Request Body | Name | Type | Description | | --------------------------------------- | ------ | ------------------------------------------------------------ | | audio\* | File | Audio to be processed and converted to text | | language\_code | String | Specifies the language spoken in the audio, defaults to "en" | {% tabs %} {% tab title="200: OK " %} ```json { "success":true, "data":{ "results":[ { "alternatives":[ { "transcript":"example audio transcription by Autogon AI", "confidence":0.922834, "words":[] }], "resultEndTime":"19.110s", "languageCode":"en-gb", "channelTag":0 }], "totalBilledTime":"20s", "requestId":"7571580858796951372" } } ``` {% endtab %} {% endtabs %} # Text To Speech Convert text into natural-sounding speech using an API powered by the best of AI technologies. The Text To Speech (TTS) API is a powerful tool designed to convert text-based input into natural-sounding speech. This API enables developers to integrate speech synthesis capabilities into their applications, providing users with an auditory experience for various use cases. Text-to-Speech converts text or [Speech Synthesis Markup Language (SSML)](https://en.wikipedia.org/wiki/Speech_Synthesis_Markup_Language) input into audio data like MP3. #### Pricing Requests made to the Text To Speech (TTS) API are billed. Prices are based on the number of characters sent to the service to be synthesized into audio. The pricing for API requests is as follows: * **Per Request Cost**: 3 units base cost per request. `POST` `https://api.autogon.ai/api/v1/services/text-to-speech/` #### Headers | Name | Type | Description | | ---------------------------------------------- | ------ | ---------------- | | Content-Type\* | String | application/json | #### Request Body | Name | Type | Description | | -------------------------------------- | ------ | ----------------------------------------------------------------------------------- | | text\* | String | Text to be processed and converted to audio | | language\_code | String | Specifies the language used for speech synthesis, defaults to "en" which is English | {% tabs %} {% tab title="200: OK " %} ```json { "success": true, "data": { "audio": "http://cloud.autogonai.s3.amazonaws.com/tts-f45a5db2-481b-442f-bb92-d16d0b3d7f72.wav" } } ``` {% endtab %} {% endtabs %} # Sentiment Analyzer (Deprecated) Sentiment Analysis inspects the given text and identifies the prevailing emotional opinion within the text, especially to determine a writer's attitude as positive, negative, or neutral. #### Pricing Requests made to the Sentiment Analysis API are billed. Prices are based on the number of characters sent to the service to be analyzed. The pricing for API requests is as follows: * **Per Request Cost**: 3 units base cost per request. ## This API analyzes the sentiment of a text `POST` `https://api.autogon.ai/api/v1/services/sentiment-analysis/` #### Headers | Name | Type | Description | | ---------------------------------------------- | ------ | ---------------- | | Content-Type\* | String | application/json | #### Request Body | Name | Type | Description | | -------------------------------------- | ------ | ------------------- | | text\* | String | text to be analyzed | {% tabs %} {% tab title="200: OK " %} ```json { "success": true, "data": { "documentSentiment": { "magnitude": 0.6, "score": -0.6 }, "language": "en", "sentences": [ { "text": { "content": "Bad apple", "beginOffset": -1 }, "sentiment": { "magnitude": 0.6, "score": -0.6 } } ] } } ``` {% endtab %} {% endtabs %} # Conversation with Chatbot Agent The Chatbot Conversation API is a powerful tool designed to enable developers to integrate chatbot functionalities into their applications. This API allows seamless communication between a client application and a custom chatbot service agent, facilitating natural language processing and response generation. #### Get your Chatbot Agent ID A Chatbot Agent ID is gotten from the [Autogon console](https://console.autogon.ai/) after a successful creation of a chatbot agent, [see here](https://youtu.be/LE9T9K__cv8) on how to create a Chatbot Agent. #### Authentication Requests to this API doesn't require an API Key to be included in its headers #### Pricing Requests made to the Chatbot Conversation API are billed. Each message - response cycle incurs a specific charge. The pricing for API requests is as follows: * **Per Request Cost**: 0.05 units per API request `POST` `https://api.autogon.ai/api/v1/services/chatbot/{agent_id}/chat/` Initiates a new conversation session with the chatbot. #### Path Parameters | Name | Type | Description | | ------------------------------------------- | ------ | ------------------------------------------------------------------- | | agent\_id\* | String | Unique identifier for the Agent which responds to the conversation. | #### Headers | Name | Type | Description | | ---------------------------------------------- | ------ | ---------------- | | Content-Type\* | String | application/json | #### Request Body | Name | Type | Description | | ------------------------------------------ | --------------- | ------------------------------------------------ | | question\* | String | message from the user | | session\_id | String(UUID v4) | Identifier for the ongoing conversation session. | {% tabs %} {% tab title="200: OK Successful Conversation " %} ```json { "status": "true", "message": "Chat with agent: {agent_id} successful", "data": { "session_id": "cb6c2000-3231-47f1-b773-6f611bb1ea2f", "question": "hello chatbot", "bot_response": "How can I help you" } } ``` {% endtab %} {% tab title="404: Not Found Incorrect agent\_id" %} ```json { "status": "false", "message": "Agent not found" } ``` {% endtab %} {% endtabs %} ### Sample request {% tabs %} {% tab title="Python (Requests)" %} {% code lineNumbers="true" %} ```python import requests import json url = "https://api.autogon.ai/api/v1/services/chatbot/test-agent-id-907e43cd56e7/chat/" payload = json.dumps({ "session_id": "test-session-id-1497505decbe", "question": "Hello Chatbot" }) headers = { 'Content-Type': 'application/json' } response = requests.request("POST", url, headers=headers, data=payload) print(response.text) ``` {% endcode %} {% endtab %} {% tab title="Node.js" %} {% code lineNumbers="true" %} ```javascript const axios = require('axios'); let data = JSON.stringify({ "session_id": "test-session-id-1497505decbe", "question": "Hello Chatbot" }); let config = { method: 'post', maxBodyLength: Infinity, url: 'https://api.autogon.ai/api/v1/services/chatbot/test-agent-id-907e43cd56e7/chat/', headers: { 'Content-Type': 'application/json' }, data : data }; axios.request(config) .then((response) => { console.log(JSON.stringify(response.data)); }) .catch((error) => { console.log(error); }); ``` {% endcode %} {% endtab %} {% tab title="Curl" %} {% code overflow="wrap" %} ```json curl --location 'https://api.autogon.ai/api/v1/services/chatbot/test-agent-id-907e43cd56e7/chat/' \ --header 'Content-Type: application/json' \ --data '{ "session_id": "test-session-id-1497505decbe", "question": "Hello Chatbot" }' ``` {% endcode %} {% endtab %} {% endtabs %} ### Autogon Response ```json { "status": "true", "message": "Chat with agent: test-agent-id-907e43cd56e7 successful", "data": { "session_id": "test-session-id-1497505decbe", "question": "Hello Chatbot", "bot_response": "How can I help you" } } ``` # Conversational Interaction with GPT-4 Chat with Autogon Chat Completion API using powerful variants of the GPT models. #### Pricing Requests made to the Synthetic Data Generation API are billed. The pricing for API requests is as follows: * **Per Request Cost**: 3 units base cost per request. `POST` `https://autogon.ai/api/v1/services/chat/` #### Path Parameters | Name | Type | Description | | ----------------------------------------- | ------ | --------------------------------------------- | | message\* | string | The messages to generate chat completions for | #### Headers | Name | Type | Description | | ---------------------------------------------- | ------ | ---------------- | | Content-Type\* | String | application/json | {% tabs %} {% tab title="200: OK Sentences, Code blocks or both" %} ```` "To make an HTTP request in Python, you can use the built-in `requests` module. Here is an example:\n\n```python\nimport requests\n\nresponse = requests.get('https://www.example.com')\nprint(response.text)\n```\n\nThis code sends a GET request to `https://www.example.com` and prints the response content. You can also send other types of requests (POST, PUT, DELETE, etc.) by changing the method in the `requests` function. For example:\n\n```python\nimport requests\n\npayload = {'key1': 'value1', 'key2': 'value2'}\nresponse = requests.post('https://www.example.com/post', data=payload)\nprint(response.text)\n```\n\nThis code sends a POST request to `https://www.example.com/post` with a payload of `{'key1': 'value1', 'key2': 'value2'}` and prints the response content." ```` {% endtab %} {% endtabs %} # Essay Marker Generates a detailed metric score for an essay ## Mark an Essay `POST` `https://api.autogon.ai/api/v1/services/essay-marker/` #### Headers | Name | Type | Description | | ---------------------------------------------- | ------ | ---------------- | | Content-Type\* | String | application/json | #### Request Body | Name | Type | Description | | ------------------------------------------------------------- | ------- | ----------------------------------------- | | essay\* | String | Candidate's essay answer | | question\* | String | essay question | | answer | String | Reference answer for evaluation. Optional | | required\_number\_of\_words\* | Integer | Required word count for the essay. | {% tabs %} {% tab title="200: OK Successful request" %} ```json { "response_id": "b54021b9-dba9-4132-aabb-31a48318931b", "data": { "grammatically_correct_score": 95, "meaning_score": 90, "structure_score": 93, "average_score_w4": 93, "known_history_score": 0 } } ``` {% endtab %} {% tab title="400: Bad Request" %} {% code fullWidth="true" %} ```json { "response_id": "b54021b9-dba9-4132-aabb-31a48318931b", "error":"Error occurred while marking the essay" } ``` {% endcode %} {% endtab %} {% endtabs %} # Resume Ranker Ranks a resume if its a best fit for a job description ## Rank Resume `POST` `https://api.autogon.ai/api/v1/services/rank-resume/` #### Headers | Name | Type | Description | | ---------------------------------------------- | ------ | ---------------- | | Content-Type\* | String | application/json | #### Request Body | Name | Type | Description | | -------------------------------------------------- | ------ | --------------- | | job\_description\* | String | job description | | resume\_file\* | File | resume file | {% tabs %} {% tab title="200: OK Successful request" %} ```json { "status": true, "message": "Candidates ranked successfully", "data": "53.67%" } ``` {% endtab %} {% tab title="400: Bad Request" %} {% code fullWidth="true" %} ```json { "error":"Job description is required" } ``` {% endcode %} {% endtab %} {% endtabs %} # Translator Translates a text from one language to another ## Translate `POST` `https://api.autogon.ai/api/v1/services/text-translation/` #### Headers | Name | Type | Description | | ---------------------------------------------- | ------ | ---------------- | | Content-Type\* | String | application/json | #### Request Body| Name | Type | Description |
|---|---|---|
| text* | String | text to translate |
| source_language* | String | language to be translated from |
| target_language* | String | language to be translated to |