Overview Use Cases Customer Churn Prediction Time Series Anomaly Detection Event Anomaly Detection Cloud Spend Alerts Personalized Promotions Predictive Modeling Real-Time Forecasting Financial Metrics Forecasting Demand Forecasting Cumulative Forecasting Text extraction and classification NLP Powered Search Sentiment Analysis Finetuned LLM ChatLLM Language Detection Image Classification & Detection Object Detection Clustering Timeseries Clustering Sales and Revenue Forecasting Predictive Lead Scoring Personalized Search Personalized Recommendations Related Items Model Drift and Monitoring Tensorflow with Vector Matching TensorFlow Model with Embeddings Artifacts Deployment And Prediction Custom Python Model Data Ingestion Streaming Feature Store Vector Store AI Agents Named Entity Recognition Guidelines Optimization Connectors Authentication Getting Started with the Python SDK API Documentation Chat Bot API Search How to

Deploy TensorFlow Plug and Play Model with Embeddings

The section focuses on how you can leverage Abacus.AI infrastructure and abstractions to create, manage, and utilize the deployment(s) of the model(s) trained on your infrastructure.

Uploading Artifacts

In the previous section, we have discussed the process of creating the artifacts required for the use case. You could upload the files directly to our platform using the interface as follows:

Artifacts Upload UI - upload from file

Another way to upload the artifacts is to add them from your cloud storage bucket by providing the location and other details as follows: Artifacts Upload UI - upload from bucket

Creating and Managing Deployments

1-Click Deployment

Point to Deployment

Prediction API

Our deployments expose the prediction API that can be used to generate predictions from the model:

curl -X POST "https://abacus.ai/api/predict?deploymentToken=8238f34bb2b04bef89a0699359b6d670&deploymentId=5edfcc400"
-d '{
"distance": "dot",
"num": 20,
"data": ""
}'
-H "Content-Type: application/json"