ollama-ex

A nifty little library for working with Ollama in Elixir.

Stars: 127

Visit

Ollama is a powerful tool for running large language models locally or on your own infrastructure. It provides a full implementation of the Ollama API, support for streaming requests, and tool use capability. Users can interact with Ollama in Elixir to generate completions, chat messages, and perform streaming requests. The tool also supports function calling on compatible models, allowing users to define tools with clear descriptions and arguments. Ollama is designed to facilitate natural language processing tasks and enhance user interactions with language models.

README:

Ollama

Ollama is a powerful tool for running large language models locally or on your own infrastructure. This library provides an interface for working with Ollama in Elixir.

🦙 Full implementation of the Ollama API
🧰 Tool use (function calling)
🧱 Structured outputs
🛜 Streaming requests
- Stream to an Enumerable
- Or stream messages to any Elixir process

Installation

The package can be installed by adding ollama to your list of dependencies in mix.exs.

def deps do
  [
    {:ollama, "~> 0.8"}
  ]
end

Quickstart

For more examples, refer to the Ollama documentation.

1. Generate a completion

client = Ollama.init()

Ollama.completion(client, [
  model: "llama2",
  prompt: "Why is the sky blue?",
])
# {:ok, %{"response" => "The sky is blue because it is the color of the sky.", ...}}

2. Generate the next message in a chat

Ollama.chat(client, [
  model: "llama2",
  messages: [
    %{role: "system", content: "You are a helpful assistant."},
    %{role: "user", content: "Why is the sky blue?"},
    %{role: "assistant", content: "Due to rayleigh scattering."},
    %{role: "user", content: "How is that different than mie scattering?"},
  ]
])
# {:ok, %{"message" => %{
#   "role" => "assistant",
#   "content" => "Mie scattering affects all wavelengths similarly, while Rayleigh favors shorter ones."
# }, ...}}

3. Generate structured data

The :format option can be used with both completion/2 and chat/2.

Ollama.completion(client, [
  model: "llama3.1",
  prompt: "Tell me about Canada",
  format: %{
    type: "object",
    properties: %{
      name: %{type: "string"},
      capital: %{type: "string"},
      languages: %{type: "array", items: %{type: "string"}},
    },
    required: ["name", "capital", "languages"]
  }
])
# {:ok, %{"response" => "{ \"name\": \"Canada\" ,\"capital\": \"Ottawa\" ,\"languages\": [\"English\", \"French\"] }", ...}}

Streaming

Streaming is supported on certain endpoints by setting the :stream option to true or a t:pid/0.

When :stream is set to true, a lazy t:Enumerable.t/0 is returned, which can be used with any Stream functions.

{:ok, stream} = Ollama.completion(client, [
  model: "llama2",
  prompt: "Why is the sky blue?",
  stream: true,
])

stream
|> Stream.each(& Process.send(pid, &1, [])
|> Stream.run()
# :ok

This approach above builds the t:Enumerable.t/0 by calling receive, which may cause issues in GenServer callbacks. As an alternative, you can set the :stream option to a t:pid/0. This returns a t:Task.t/0 that sends messages to the specified process.

The following example demonstrates a streaming request in a LiveView event, sending each streaming message back to the same LiveView process:

defmodule MyApp.ChatLive do
  use Phoenix.LiveView

  # When the client invokes the "prompt" event, create a streaming request and
  # asynchronously send messages back to self.
  def handle_event("prompt", %{"message" => prompt}, socket) do
    {:ok, task} = Ollama.completion(Ollama.init(), [
      model: "llama2",
      prompt: prompt,
      stream: self(),
    ])

    {:noreply, assign(socket, current_request: task)}
  end

  # The streaming request sends messages back to the LiveView process.
  def handle_info({_request_pid, {:data, _data}} = message, socket) do
    pid = socket.assigns.current_request.pid
    case message do
      {^pid, {:data, %{"done" => false} = data}} ->
        # handle each streaming chunk

      {^pid, {:data, %{"done" => true} = data}} ->
        # handle the final streaming chunk

      {_pid, _data} ->
        # this message was not expected!
    end
  end

  # Tidy up when the request is finished
  def handle_info({ref, {:ok, %Req.Response{status: 200}}}, socket) do
    Process.demonitor(ref, [:flush])
    {:noreply, assign(socket, current_request: nil)}
  end
end

Regardless of the streaming approach used, each streaming message is a plain t:map/0. For the message schema, refer to the Ollama API docs.

Function calling

Ollama 0.3 and later versions support tool use and function calling on compatible models. Note that Ollama currently doesn't support tool use with streaming requests, so avoid setting :stream to true.

Using tools typically involves at least two round-trip requests to the model. Begin by defining one or more tools using a schema similar to ChatGPT's. Provide clear and concise descriptions for the tool and each argument.

stock_price_tool = %{
  type: "function",
  function: %{
    name: "get_stock_price",
    description: "Fetches the live stock price for the given ticker.",
    parameters: %{
      type: "object",
      properties: %{
        ticker: %{
          type: "string",
          description: "The ticker symbol of a specific stock."
        }
      },
      required: ["ticker"]
    }
  }
}

The first round-trip involves sending a prompt in a chat with the tool definitions. The model should respond with a message containing a list of tool calls.

Ollama.chat(client, [
  model: "mistral-nemo",
  messages: [
    %{role: "user", content: "What is the current stock price for Apple?"}
  ],
  tools: [stock_price_tool],
])
# {:ok, %{"message" => %{
#   "role" => "assistant",
#   "content" => "",
#   "tool_calls" => [
#     %{"function" => %{
#       "name" => "get_stock_price",
#       "arguments" => %{"ticker" => "AAPL"}
#     }}
#   ]
# }, ...}}

Your implementation must intercept these tool calls and execute a corresponding function in your codebase with the specified arguments. The next round-trip involves passing the function's result back to the model as a message with a :role of "tool".

Ollama.chat(client, [
  model: "mistral-nemo",
  messages: [
    %{role: "user", content: "What is the current stock price for Apple?"},
    %{role: "assistant", content: "", tool_calls: [%{"function" => %{"name" => "get_stock_price", "arguments" => %{"ticker" => "AAPL"}}}]},
    %{role: "tool", content: "$217.96"},
  ],
  tools: [stock_price_tool],
])
# {:ok, %{"message" => %{
#   "role" => "assistant",
#   "content" => "The current stock price for Apple (AAPL) is approximately $217.96.",
# }, ...}}

After receiving the function tool's value, the model will respond to the user's original prompt, incorporating the function result into its response.

License

This package is open source and released under the Apache-2 License.

For Tasks:

Click tags to check more tools for each tasks

generate completion chat interaction perform streaming define tools execute functions

For Jobs:

data scientist machine learning engineer ai researcher software developer linguist

Alternative AI tools for ollama-ex

Similar Open Source Tools

ollama-ex

github

: 127

ruby-openai

Use the OpenAI API with Ruby! 🤖🩵 Stream text with GPT-4, transcribe and translate audio with Whisper, or create images with DALL·E... Hire me | 🎮 Ruby AI Builders Discord | 🐦 Twitter | 🧠 Anthropic Gem | 🚂 Midjourney Gem ## Table of Contents * Ruby OpenAI * Table of Contents * Installation * Bundler * Gem install * Usage * Quickstart * With Config * Custom timeout or base URI * Extra Headers per Client * Logging * Errors * Faraday middleware * Azure * Ollama * Counting Tokens * Models * Examples * Chat * Streaming Chat * Vision * JSON Mode * Functions * Edits * Embeddings * Batches * Files * Finetunes * Assistants * Threads and Messages * Runs * Runs involving function tools * Image Generation * DALL·E 2 * DALL·E 3 * Image Edit * Image Variations * Moderations * Whisper * Translate * Transcribe * Speech * Errors * Development * Release * Contributing * License * Code of Conduct

github

: 3.0k

lmstudio.js

lmstudio.js is a pre-release alpha client SDK for LM Studio, allowing users to use local LLMs in JS/TS/Node. It is currently undergoing rapid development with breaking changes expected. Users can follow LM Studio's announcements on Twitter and Discord. The SDK provides API usage for loading models, predicting text, setting up the local LLM server, and more. It supports features like custom loading progress tracking, model unloading, structured output prediction, and cancellation of predictions. Users can interact with LM Studio through the CLI tool 'lms' and perform tasks like text completion, conversation, and getting prediction statistics.

github

: 663

promptic

Promptic is a tool designed for LLM app development, providing a productive and pythonic way to build LLM applications. It leverages LiteLLM, allowing flexibility to switch LLM providers easily. Promptic focuses on building features by providing type-safe structured outputs, easy-to-build agents, streaming support, automatic prompt caching, and built-in conversation memory.

github

: 223

ling

Ling is a workflow framework supporting streaming of structured content from large language models. It enables quick responses to content streams, reducing waiting times. Ling parses JSON data streams character by character in real-time, outputting content in jsonuri format. It facilitates immediate front-end processing by converting content during streaming input. The framework supports data stream output via JSONL protocol, correction of token errors in JSON output, complex asynchronous workflows, status messages during streaming output, and Server-Sent Events.

github

: 64

parakeet

Parakeet is a Go library for creating GenAI apps with Ollama. It enables the creation of generative AI applications that can generate text-based content. The library provides tools for simple completion, completion with context, chat completion, and more. It also supports function calling with tools and Wasm plugins. Parakeet allows users to interact with language models and create AI-powered applications easily.

github

: 96

DeRTa

DeRTa (Refuse Whenever You Feel Unsafe) is a tool designed to improve safety in Large Language Models (LLMs) by training them to refuse compliance at any response juncture. The tool incorporates methods such as MLE with Harmful Response Prefix and Reinforced Transition Optimization (RTO) to address refusal positional bias and strengthen the model's capability to transition from potential harm to safety refusal. DeRTa provides training data, model weights, and evaluation scripts for LLMs, enabling users to enhance safety in language generation tasks.

github

: 59

ogpt.nvim

OGPT.nvim is a Neovim plugin that enables users to interact with various language models (LLMs) such as Ollama, OpenAI, TextGenUI, and more. Users can engage in interactive question-and-answer sessions, have persona-based conversations, and execute customizable actions like grammar correction, translation, keyword generation, docstring creation, test addition, code optimization, summarization, bug fixing, code explanation, and code readability analysis. The plugin allows users to define custom actions using a JSON file or plugin configurations.

github

: 166

aiavatarkit

AIAvatarKit is a tool for building AI-based conversational avatars quickly. It supports various platforms like VRChat and cluster, along with real-world devices. The tool is extensible, allowing unlimited capabilities based on user needs. It requires VOICEVOX API, Google or Azure Speech Services API keys, and Python 3.10. Users can start conversations out of the box and enjoy seamless interactions with the avatars.

github

: 413

crush

Crush is a versatile tool designed to enhance coding workflows in your terminal. It offers support for multiple LLMs, allows for flexible switching between models, and enables session-based work management. Crush is extensible through MCPs and works across various operating systems. It can be installed using package managers like Homebrew and NPM, or downloaded directly. Crush supports various APIs like Anthropic, OpenAI, Groq, and Google Gemini, and allows for customization through environment variables. The tool can be configured locally or globally, and supports LSPs for additional context. Crush also provides options for ignoring files, allowing tools, and configuring local models. It respects `.gitignore` files and offers logging capabilities for troubleshooting and debugging.

github

: 19.8k

firecrawl

Firecrawl is an API service that takes a URL, crawls it, and converts it into clean markdown. It crawls all accessible subpages and provides clean markdown for each, without requiring a sitemap. The API is easy to use and can be self-hosted. It also integrates with Langchain and Llama Index. The Python SDK makes it easy to crawl and scrape websites in Python code.

github

: 34.1k

parrot.nvim

Parrot.nvim is a Neovim plugin that prioritizes a seamless out-of-the-box experience for text generation. It simplifies functionality and focuses solely on text generation, excluding integration of DALLE and Whisper. It supports persistent conversations as markdown files, custom hooks for inline text editing, multiple providers like Anthropic API, perplexity.ai API, OpenAI API, Mistral API, and local/offline serving via ollama. It allows custom agent definitions, flexible API credential support, and repository-specific instructions with a `.parrot.md` file. It does not have autocompletion or hidden requests in the background to analyze files.

github

: 558

firecrawl

Firecrawl is an API service that empowers AI applications with clean data from any website. It features advanced scraping, crawling, and data extraction capabilities. The repository is still in development, integrating custom modules into the mono repo. Users can run it locally but it's not fully ready for self-hosted deployment yet. Firecrawl offers powerful capabilities like scraping, crawling, mapping, searching, and extracting structured data from single pages, multiple pages, or entire websites with AI. It supports various formats, actions, and batch scraping. The tool is designed to handle proxies, anti-bot mechanisms, dynamic content, media parsing, change tracking, and more. Firecrawl is available as an open-source project under the AGPL-3.0 license, with additional features offered in the cloud version.

github

: 81.9k

vim-ai

vim-ai is a plugin that adds Artificial Intelligence (AI) capabilities to Vim and Neovim. It allows users to generate code, edit text, and have interactive conversations with GPT models powered by OpenAI's API. The plugin uses OpenAI's API to generate responses, requiring users to set up an account and obtain an API key. It supports various commands for text generation, editing, and chat interactions, providing a seamless integration of AI features into the Vim text editor environment.

github

: 878

openmacro

Openmacro is a multimodal personal agent that allows users to run code locally. It acts as a personal agent capable of completing and automating tasks autonomously via self-prompting. The tool provides a CLI natural-language interface for completing and automating tasks, analyzing and plotting data, browsing the web, and manipulating files. Currently, it supports API keys for models powered by SambaNova, with plans to add support for other hosts like OpenAI and Anthropic in future versions.

github

: 62

bosquet

Bosquet is a tool designed for LLMOps in large language model-based applications. It simplifies building AI applications by managing LLM and tool services, integrating with Selmer templating library for prompt templating, enabling prompt chaining and composition with Pathom graph processing, defining agents and tools for external API interactions, handling LLM memory, and providing features like call response caching. The tool aims to streamline the development process for AI applications that require complex prompt templates, memory management, and interaction with external systems.

github

: 329

For similar tasks

ollama-ex

github

: 127

Ollama

Ollama SDK for .NET is a fully generated C# SDK based on OpenAPI specification using OpenApiGenerator. It supports automatic releases of new preview versions, source generator for defining tools natively through C# interfaces, and all modern .NET features. The SDK provides support for all Ollama API endpoints including chats, embeddings, listing models, pulling and creating new models, and more. It also offers tools for interacting with weather data and providing weather-related information to users.

github

: 134

llm_agents

LLM Agents is a small library designed to build agents controlled by large language models. It aims to provide a better understanding of how such agents work in a concise manner. The library allows agents to be instructed by prompts, use custom-built components as tools, and run in a loop of Thought, Action, Observation. The agents leverage language models to generate Thought and Action, while tools like Python REPL, Google search, and Hacker News search provide Observations. The library requires setting up environment variables for OpenAI API and SERPAPI API keys. Users can create their own agents by importing the library and defining tools accordingly.

github

: 945

kagent

Kagent is a Kubernetes native framework for building AI agents, designed to be easy to understand and use. It provides a flexible and powerful way to build, deploy, and manage AI agents in Kubernetes. The framework consists of agents, tools, and model configurations defined as Kubernetes custom resources, making them easy to manage and modify. Kagent is extensible, flexible, observable, declarative, testable, and has core components like a controller, UI, engine, and CLI.

github

: 1.6k

AgentFly

AgentFly is an extensible framework for building LLM agents with reinforcement learning. It supports multi-turn training by adapting traditional RL methods with token-level masking. It features a decorator-based interface for defining tools and reward functions, enabling seamless extension and ease of use. To support high-throughput training, it implemented asynchronous execution of tool calls and reward computations, and designed a centralized resource management system for scalable environment coordination. A suite of prebuilt tools and environments are provided.

github

: 60

bellman

Bellman is a unified interface to interact with language and embedding models, supporting various vendors like VertexAI/Gemini, OpenAI, Anthropic, VoyageAI, and Ollama. It consists of a library for direct interaction with models and a service 'bellmand' for proxying requests with one API key. Bellman simplifies switching between models, vendors, and common tasks like chat, structured data, tools, and binary input. It addresses the lack of official SDKs for major players and differences in APIs, providing a single proxy for handling different models. The library offers clients for different vendors implementing common interfaces for generating and embedding text, enabling easy interchangeability between models.

github

: 57

mesh

MCP Mesh is an open-source control plane for MCP traffic that provides a unified layer for authentication, routing, and observability. It replaces multiple integrations with a single production endpoint, simplifying configuration management. Built for multi-tenant organizations, it offers workspace/project scoping for policies, credentials, and logs. With core capabilities like MeshContext, AccessControl, and OpenTelemetry, it ensures fine-grained RBAC, full tracing, and metrics for tools and workflows. Users can define tools with input/output validation, access control checks, audit logging, and OpenTelemetry traces. The project structure includes apps for full-stack MCP Mesh, encryption, observability, and more, with deployment options ranging from Docker to Kubernetes. The tech stack includes Bun/Node runtime, TypeScript, Hono API, React, Kysely ORM, and Better Auth for OAuth and API keys.

github

: 331

fal-js

The fal.ai JS client is a robust and user-friendly library for seamless integration of fal serverless functions in Web, Node.js, and React Native applications. Developed in TypeScript, it provides developers with type safety right from the start. The client library is crafted as a lightweight layer atop platform standards like `fetch`, ensuring hassle-free integration into existing codebases and flawless operation across various JavaScript runtimes. The client proxy feature allows secure handling of credentials by using a server proxy for serverless APIs. The repository also includes example Next.js applications for demonstration and integration.

github

: 74

For similar jobs

weave

Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

github

: 1.1k

LLMStack

LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

github

: 1.5k

VisionCraft

The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

github

: 94

kaito

Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

github

: 405

PyRIT

PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

github

: 2.9k

tabby

Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

github

: 32.9k

spear

SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

github

: 224

Magick

Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.

github

: 675