local_llm 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: d8cbf63f243ec6c48c454711b97be37b1672dbe38ecd016744c6f5fc44fa5203
+  data.tar.gz: c054e2e4f177c3241936d718de8ab6b04b05e198c40ed8e97651309338b1a281
+SHA512:
+  metadata.gz: cc1fe4e1e27d394b83596854cf795696e37f8224c34288acb754bff33c1d67771f4bee6fef59ed492a4989dd07c083fda29102f072157c3e75e8ebd5cff62882
+  data.tar.gz: a17c1605fc1283a713c1fd697004bf5f3aece8415b4a43021af3db8ac2055fdd3cd8fc26983b6b04ba95ac413011fa9b87adf240f0d06f8fb2b151b88510ab08

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2025 MD Abdul Barek
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -0,0 +1,153 @@
+# local_llm
+
+**`local_llm`** is a lightweight Ruby gem that lets you talk to **locally installed LLMs via Ollama** — with **zero cloud dependency**, full **developer control**, and **configurable defaults**, including **real-time streaming support**.
+
+It supports:
+- Any Ollama model (LLaMA, Mistral, CodeLLaMA, Qwen, Phi, Gemma, etc.)
+- Developer-configurable default models
+- Developer-configurable Ollama API endpoint
+- Developer-configurable **streaming or non-streaming**
+- One-shot Q&A and multi-turn chat
+- Works in plain Ruby & Rails
+- 100% local & private
+
+---
+
+## 🚀 Features
+
+- Use **any locally installed Ollama model**
+- Change **default models at runtime**
+- Enable or disable **real-time streaming**
+- Works with:
+  - `llama2`
+  - `mistral`
+  - `codellama`
+  - `qwen`
+  - `phi`
+  - Anything supported by Ollama
+- No API keys needed
+- No cloud calls
+- Full privacy
+- Works completely offline
+
+---
+
+## 📦 Installation
+
+### Install Ollama
+
+Download from:
+
+https://ollama.com
+
+Then start it:
+
+```bash
+ollama serve
+```
+
+### How to Install New LLMs
+```
+ollama pull llama2:13b
+ollama pull mistral:7b-instruct
+ollama pull codellama:13b-instruct
+ollama pull qwen2:7b
+```
+
+### Verify Installed Models
+```
+ollama list
+```
+
+### Configuration
+```
+LocalLlm.configure do |c|
+  c.base_url = "http://localhost:11434"
+  c.default_general_model = "llama2:13b"
+  c.default_fast_model    = "mistral:7b-instruct"
+  c.default_code_model    = "codellama:13b-instruct"
+  c.default_stream = false   # true = stream by default, false = return full text
+end
+```
+
+### Basic Usage (Non-Streaming)
+```
+LocalLlm.ask("llama2:13b", "What is HIPAA?")
+LocalLlm.ask("qwen2:7b", "Explain transformers in simple terms.")
+
+LocalLlm.general("What is a Denial of Service attack?")
+LocalLlm.fast("Summarize this paragraph in 3 bullet points.")
+LocalLlm.code("Write a Ruby method that returns factorial of n.")
+```
+
+### Streaming Usage (Live Output)
+```
+LocalLlm.configure do |c|
+  c.default_stream = true
+end
+
+LocalLlm.fast("Explain HIPAA in very simple words.") do |chunk|
+  print chunk
+end
+```
+
+### Per-Call Streaming Override
+```
+LocalLlm.fast("Explain LLMs in one paragraph.", stream: true) do |chunk|
+  print chunk
+end
+
+full_text = LocalLlm.fast("Explain DoS attacks briefly.", stream: false)
+puts full_text
+```
+
+### Full Chat API (Multi-Turn)
+```
+LocalLlm.chat("llama2:13b", [
+  { "role" => "system", "content" => "You are a helpful assistant." },
+  { "role" => "user",   "content" => "Explain LSTM." }
+])
+```
+
+### List Installed Ollama Models from Ruby
+```
+LocalLlm.models
+```
+
+### Switching to Qwen (or Any New Model)
+```
+ollama pull qwen2:7b
+```
+
+```
+LocalLlm.ask("qwen2:7b", "Explain HIPAA in simple terms.")
+```
+
+### Make Qwen the Default
+```
+LocalLlm.configure do |c|
+  c.default_general_model = "qwen2:7b"
+end
+
+LocalLlm.general("Explain transformers.")
+```
+
+### 🔌 Remote Ollama / Docker Support
+```
+LocalLlm.configure do |c|
+  c.base_url = "http://192.168.1.100:11434"
+end
+```
+
+### Troubleshooting
+##### Ollama Not Running
+```
+ollama serve
+```
+
+### Privacy & Security
+ - 100% local inference
+ - No cloud calls
+ - No API keys
+ - No data leaves your machine
+ - Safe for HIPAA, SOC2, and regulated workflows

data/Rakefile

@@ -0,0 +1,8 @@
+# frozen_string_literal: true
+
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task default: :spec

data/lib/local_llm/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module LocalLlm
+  VERSION = "0.1.0"
+end

data/lib/local_llm.rb

@@ -0,0 +1,101 @@
+# lib/local_llm.rb
+# frozen_string_literal: true
+
+require_relative "local_llm/version"
+require_relative "local_llm/client"
+
+module LocalLlm
+  # Configuration object
+  class Config
+    attr_accessor :base_url,
+                  :default_general_model,
+                  :default_fast_model,
+                  :default_code_model,
+                  :default_stream
+
+    def initialize
+      @base_url              = "http://localhost:11434" # default Ollama
+      @default_general_model = "llama2:13b"
+      @default_fast_model    = "mistral:7b-instruct"
+      @default_code_model    = "codellama:13b-instruct"
+      @default_stream        = false
+    end
+  end
+
+  # Global config access
+  def self.config
+    @config ||= Config.new
+  end
+
+  # DSL-style configuration:
+  #
+  #   LocalLlm.configure do |c|
+  #     c.base_url              = "http://my-ollama-host:11434"
+  #     c.default_general_model = "phi3:3.8b"
+  #     c.default_fast_model    = "mistral:7b-instruct"
+  #     c.default_code_model    = "codellama:13b-instruct"
+  #   end
+  #
+  def self.configure
+    yield(config)
+  end
+
+  class << self
+    # We build a fresh client each time so changes to config.base_url
+    # are always respected.
+    def client
+      Client.new(base_url: config.base_url)
+    end
+
+    # -------- Core API (any model) --------
+
+    # One-shot Q&A with explicit model name
+    #
+    #   LocalLlm.ask("mistral:7b-instruct", "What is HIPAA?")
+    #
+    def ask(model, prompt, options = {}, &block)
+      # allow per-call stream override, otherwise use config.default_stream
+      stream = options.key?(:stream) ? options.delete(:stream) : config.default_stream
+      client.ask(model: model, prompt: prompt, stream: stream, options: options, &block)
+    end
+
+
+    # Chat API with full messages array (OpenAI-style)
+    #
+    #   LocalLlm.chat("llama2:13b", [
+    #     { "role" => "system", "content" => "You are a helpful assistant." },
+    #     { "role" => "user",   "content" => "Explain LSTM." }
+    #   ])
+    #
+    def chat(model, messages, options = {}, &block)
+      stream = options.key?(:stream) ? options.delete(:stream) : config.default_stream
+      client.chat(model: model, messages: messages, stream: stream, options: options, &block)
+    end
+
+
+    # List models from Ollama (`ollama list`)
+    def models
+      client.models
+    end
+
+    # -------- Convenience helpers using defaults --------
+
+    # Use whatever the developer set as default_general_model
+    def general(prompt, options = {}, &block)
+      ask(config.default_general_model, prompt, options, &block)
+    end
+
+    # Use developer’s default_fast_model
+    def fast(prompt, options = {}, &block)
+      ask(config.default_fast_model, prompt, options, &block)
+    end
+
+    # Use developer’s default_code_model
+    def code(prompt, options = {}, &block)
+      ask(config.default_code_model, prompt, options, &block)
+    end
+  end
+end
+
+# Optional nicer alias if someone prefers LocalLLM
+LocalLLM = LocalLlm unless defined?(LocalLLM)

data/sig/local_llm.rbs

@@ -0,0 +1,4 @@
+module LocalLlm
+  VERSION: String
+  # See the writing guide of rbs: https://github.com/ruby/rbs#guides
+end

metadata

@@ -0,0 +1,55 @@
+--- !ruby/object:Gem::Specification
+name: local_llm
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- MD Abdul Barek
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2025-12-02 00:00:00.000000000 Z
+dependencies: []
+description: local_llm is a lightweight Ruby gem that lets you interact with locally
+  installed Ollama LLMs such as LLaMA, Mistral, CodeLLaMA, Qwen, and more. It supports
+  configurable default models, configurable Ollama API endpoints, real-time streaming
+  or non-streaming responses, and both one-shot and multi-turn chat—while keeping
+  all inference fully local, private, and offline.
+email:
+- barek2k2@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".rspec"
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/local_llm.rb
+- lib/local_llm/version.rb
+- sig/local_llm.rbs
+homepage:
+licenses:
+- MIT
+metadata:
+  allowed_push_host: https://rubygems.org
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 3.0.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.2.22
+signing_key:
+specification_version: 4
+summary: Ruby client for local LLMs via Ollama with streaming support
+test_files: []