Language Models (LLM)

Guides

Deploy and use Large Language Models for chat, generation, and RAG applications.

What You’ll Build

Deploy LLMs for various tasks:

Chat - Conversational AI interfaces
Generation - Text completion and content creation
RAG - Retrieval-Augmented Generation with your documents

Prerequisites

A SeeMe.ai account (sign up)
(Optional) Documents for RAG applications
(Optional) Python environment with seeme SDK installed

Available Models

SeeMe.ai supports various LLM backends:

Ollama integration for local models
vLLM for high-performance inference
Custom model deployment

Use Cases

Chat Interface Text Generation RAG (Documents)

Quick Start

from seeme import Client
from seeme.ollama import OllamaClient

client = Client()

## Using Ollama integration
ollama = OllamaClient(client)
response = ollama.chat(
    model="llama2",
    messages=[
        {"role": "user", "content": "Explain machine learning in simple terms"}
    ]
)
print(response.message.content)