Overview
Agent Platform supports 30+ curated open-source models and allows importing any text generation model from Hugging Face. Models are deployed on Kore-hosted infrastructure with optional optimization for improved performance. Model Sources:Open-source models do not support tool calling and cannot be used with Agentic Apps. Use external commercial models for agentic workflows.
View Models & Deployments
- View Models: Go to Models → Open-source models and click a model to view its deployments.
- Deployments List: Each model can have multiple deployments. Select a deployment to access its settings.
Deploy a Platform-Hosted Model
- Go to Models → Open-source models → Deploy a model
- Select Platform-hosted and choose a model from the dropdown
- Add a Description and Tags, then click Next
- Select an optimization technique (optional)
- Configure deployment parameters
- Select Hardware for deployment
- Review and accept terms, then click Deploy
Deploy from Hugging Face
Import and deploy any compatible model from Hugging Face.Models must be compatible with Transformers library version ≤4.43.1.
- Go to Models → Open-source models → Deploy a model
- Select Hugging Face
- Enter Deployment name and Description
- Select your Hugging Face connection (or use public mode)
- Enter the Hugging Face model name
- Configure deployment parameters
- Select Hardware and click Deploy
Import a Local Model
Upload model files from your local machine for deployment.Import a Base Model
- Go to Models → Open-source models → Import model
- Select the Base Model tab
- Upload your model file (.zip format)
- Click Import
Import an Adapter Model
Adapter models require a compatible base model.- Go to Models → Open-source models → Import model
- Select the Adapter Model tab
- Choose a Base model from the Platform-hosted list
- Upload your adapter model file (.zip format)
- Click Import
Import Status
After import, the model appears in the Open-source models list and can be deployed like any other model.
Optimization Techniques
Optimize Platform-hosted models before deployment for improved performance.CTranslate2
Efficient inference for translation and NLP tasks with optimized kernels. Advantages: CPU and GPU support, int8 quantization, multi-threading, PyTorch/TensorFlow compatibility.vLLM
High-performance inference for very large language models. Advantages: Advanced memory management, model/data parallelism, mixed-precision, AWQ quantization.When to Choose
Deployment Parameters
Configure these parameters when deploying a model:Inference Parameters
Scaling Parameters
Hardware
Select GPU hardware based on model size and performance requirements.Manage Deployed Models
After deployment, access model settings via the three-dot menu or by clicking the deployment.Model Endpoint
View the generated API endpoint in three formats (cURL, Python, Node.js). Use this to invoke your model externally. Structured Output: Kore-hosted models support JSON schema responses via theresponse_format parameter (v2/chat/completions endpoint only). See Supported Models for Structured Output.
Deployment History
Track all deployment versions with:- Deployment name and timestamp
- Duration and status
- Who deployed and when
- Un-deployment details (if applicable)
API Keys
Generate API keys for external access to your deployed model.- Go to API Keys tab
- Click Create a new API key
- Enter a name and click Generate key
- Copy the key (shown only once)
Configurations
Timeout precedence: Tool > Node timeout > Model timeout.
Re-deploy a Model
To update parameters or hardware after initial deployment:- Select the deployed model
- Click Deploy model
- Modify settings as needed
- Click Deploy
Limitations
- Open-source models do not support tool calling
- Cannot be used with Agentic Apps or Agents
- Hugging Face models require Transformers ≤4.43.1
- Structured output requires v2/chat/completions endpoint and vLLM/no optimization