Package com.tnsai.llm.providers

Class DatabricksClient

java.lang.Object

com.tnsai.llm.providers.AbstractLLMClient

com.tnsai.llm.providers.AbstractOpenAICompatibleClient

com.tnsai.llm.providers.DatabricksClient

All Implemented Interfaces:

com.tnsai.llm.LLMClient

public class DatabricksClient
extends AbstractOpenAICompatibleClient

Databricks Mosaic AI Model Serving LLM client.

Databricks hosts foundation models (DBRX, Llama, Mixtral, plus customer-fine-tuned models) behind workspace-scoped serving endpoints. The Foundation Model API exposes an OpenAI-compatible chat-completions surface — same wire format as GroqClient / XAIGrokClient / YiClient.

Workspace-scoped URL. Unlike the multi-tenant cloud providers (xAI, Yi, Hunyuan), Databricks endpoints live on a per-customer hostname: https://{workspace}.cloud.databricks.com/serving-endpoints. There is no universally-correct default — every caller must supply their workspace URL via the DATABRICKS_BASE_URL env var or the constructor's baseUrl argument.

Supported models (built-in catalog at time of writing):

• databricks-meta-llama-3-3-70b-instruct — frontier Llama 3.3
• databricks-meta-llama-3-1-405b-instruct — largest Llama 3.1
• databricks-dbrx-instruct — Databricks's own DBRX
• databricks-mixtral-8x7b-instruct — Mixtral MoE

Customers can also point this client at their own fine-tuned endpoints by passing the endpoint name as the model argument — Databricks resolves it relative to the workspace.

Configuration via environment variables:

• DATABRICKS_API_KEY — Required. Either a Personal Access Token (PAT) or a service-principal OAuth token. v1 supports both as opaque bearer tokens; native service-principal OAuth flows can land as a follow-up.
• DATABRICKS_BASE_URL — Required. The full workspace-scoped URL up to and including /serving-endpoints.

See Also:

• Databricks Foundation Model APIs

Constructor Summary

Constructors

Constructor	Description
DatabricksClient(String model)
DatabricksClient(String model, float temperature)
DatabricksClient(String model, float temperature, Float topP, Integer maxTokens)
DatabricksClient(String model, float temperature, Integer maxTokens)
DatabricksClient(String baseUrl, String model, float temperature, Float topP, Integer maxTokens, String apiKey)
DatabricksClient(String baseUrl, String model, float temperature, Integer maxTokens, String apiKey)

Method Summary

Methods inherited from class com.tnsai.llm.providers.AbstractOpenAICompatibleClient

chat, streamChat

Methods inherited from class com.tnsai.llm.providers.AbstractLLMClient

getBaseUrl, getCallTimeoutMs, getMaxTokens, getModel, getTemperature, getTopP

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface com.tnsai.llm.LLMClient

chat, chat, chat, chat, chat, getCapabilities, getProviderName, listModels, streamChat, streamChat, streamChatWithHandler, streamChatWithHandler, streamChatWithSpec, streamChatWithSpec

Constructor Details

DatabricksClient

public DatabricksClient(String model)

DatabricksClient

public DatabricksClient(String model,
 float temperature)

DatabricksClient

public DatabricksClient(String model,
 float temperature,
 Integer maxTokens)

DatabricksClient

public DatabricksClient(String model,
 float temperature,
 Float topP,
 Integer maxTokens)

DatabricksClient

public DatabricksClient(String baseUrl,
 String model,
 float temperature,
 Integer maxTokens,
 String apiKey)

DatabricksClient

public DatabricksClient(String baseUrl,
 String model,
 float temperature,
 Float topP,
 Integer maxTokens,
 String apiKey)