LLM API

The LLM API handles chat sessions and language model completions. It is the core interface for conversational AI within Lakehousecat, connecting users to the configured provider models (OpenAI, Anthropic, Google, Azure, AWS Bedrock).

Base URL: http://<host>:42015

What you can do

• Create and manage chat sessions
• Run streaming chat completions against any configured provider model
• Search, archive, clone, and share chats
• List available models from all configured providers

Authentication

All endpoints require a Bearer token. Generate your API key in the Lakehousecat UI:

Account Settings → Security → API Keys → Generate API Key

Authorization: Bearer <your-api-key>

Quick Start

List available models

curl -X GET "http://localhost:42015/api/v1/llm/models" \
  -H "Authorization: Bearer <your-api-key>"

import requests

BASE_URL = "http://localhost:42015"
HEADERS = {"Authorization": "Bearer <your-api-key>"}

response = requests.get(f"{BASE_URL}/api/v1/llm/models", headers=HEADERS)
models = response.json()

Create a new chat session

curl -X POST "http://localhost:42015/api/v1/llm/chats/new" \
  -H "Authorization: Bearer <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{"title": "My Chat"}'

response = requests.post(
    f"{BASE_URL}/api/v1/llm/chats/new",
    json={"title": "My Chat"},
    headers=HEADERS,
)
chat = response.json()
chat_id = chat["id"]

Send a chat completion

curl -X POST "http://localhost:42015/api/v1/llm/chat/completions" \
  -H "Authorization: Bearer <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "What is the total revenue this year?"}
    ]
  }'

response = requests.post(
    f"{BASE_URL}/api/v1/llm/chat/completions",
    json={
        "model": "gpt-4o",
        "messages": [
            {"role": "user", "content": "What is the total revenue this year?"}
        ],
    },
    headers=HEADERS,
)
result = response.json()
print(result["choices"][0]["message"]["content"])

List your chats

curl -X GET "http://localhost:42015/api/v1/llm/chats/paginated?page=1&page_size=20" \
  -H "Authorization: Bearer <your-api-key>"

response = requests.get(
    f"{BASE_URL}/api/v1/llm/chats/paginated",
    params={"page": 1, "page_size": 20},
    headers=HEADERS,
)
chats = response.json()

Get models from a specific provider

# Anthropic models
curl -X GET "http://localhost:42015/api/v1/llm/anthropic/models" \
  -H "Authorization: Bearer <your-api-key>"

# OpenAI models
curl -X GET "http://localhost:42015/api/v1/llm/openai/models" \
  -H "Authorization: Bearer <your-api-key>"

# Available provider endpoints
providers = ["anthropic", "openai", "google", "azure", "aws"]
for provider in providers:
    r = requests.get(f"{BASE_URL}/api/v1/llm/{provider}/models", headers=HEADERS)
    print(f"{provider}: {r.json()}")

Endpoint Groups

Resource	Path	Description
Chat Completions	/api/v1/llm/chat/completions	Run model completions
Chats	/api/v1/llm/chats	Session lifecycle management
Models	/api/v1/llm/models	List all accessible models
Provider Models	/api/v1/llm/{provider}/models	List models by provider

UI Equivalent

Chat sessions managed via this API correspond to the Sessions workspace in the Lakehousecat UI. Any chat created or modified via API is immediately visible in the UI session list.