lex-ollama

Ollama integration for LegionIO. Connects LegionIO to a local Ollama LLM server for text generation, chat completions, embeddings, and model management.

gem install lex-ollama

• generate - Generate a text completion (POST /api/generate)
• generate_stream - Stream a text completion with per-chunk callbacks

• chat - Generate a chat completion with message history and tool support (POST /api/chat)
• chat_stream - Stream a chat completion with per-chunk callbacks

• create_model - Create a model from another model, GGUF, or safetensors (POST /api/create)
• list_models - List locally available models (GET /api/tags)
• show_model - Show model details, template, parameters, license (POST /api/show)
• copy_model - Copy a model to a new name (POST /api/copy)
• delete_model - Delete a model and its data (DELETE /api/delete)
• pull_model - Download a model from the Ollama library (POST /api/pull)
• push_model - Upload a model to the Ollama library (POST /api/push)
• list_running - List models currently loaded in memory (GET /api/ps)

• embed - Generate embeddings from a model (POST /api/embed)

• check_blob - Check if a blob exists on the server (HEAD /api/blobs/:digest)
• push_blob - Upload a binary blob to the server (POST /api/blobs/:digest)

• server_version - Retrieve the Ollama server version (GET /api/version)

client = Legion::Extensions::Ollama::Client.new
# or with custom host
client = Legion::Extensions::Ollama::Client.new(host: 'http://remote:11434')

# Chat
result = client.chat(model: 'llama3.2', messages: [{ role: 'user', content: 'Hello!' }])

# Generate
result = client.generate(model: 'llama3.2', prompt: 'Why is the sky blue?')

# Embeddings
result = client.embed(model: 'all-minilm', input: 'Some text to embed')

# List models
result = client.list_models

# Streaming generate
client.generate_stream(model: 'llama3.2', prompt: 'Tell me a story') do |event|
  case event[:type]
  when :delta then print event[:text]
  when :done  then puts "\nDone!"
  end
end

# Streaming chat
client.chat_stream(model: 'llama3.2', messages: [{ role: 'user', content: 'Hello!' }]) do |event|
  print event[:text] if event[:type] == :delta
end

All API calls include automatic retry with exponential backoff on connection failures and timeouts.

Generate and chat responses include standardized usage: data:

result = client.generate(model: 'llama3.2', prompt: 'Hello')
result[:usage]  # => { input_tokens: 1, output_tokens: 5, total_duration: ..., ... }

• Ruby >= 3.4
• LegionIO framework
• Ollama running locally or on a remote host

MIT