pepperoni21/ollama-rs

Health v2 · maintenance only

Adoption not part of the score

1059 stars · 166 forks observed · 2026-09-03

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Rust client library for interacting with the Ollama API, supporting completion generation, streaming, chat, model management, embeddings, and function/tool calling. It is published on crates.io with nearly 480k downloads and an MIT license.

Use cases

• call local ollama models from rust
• generate llm completions with streaming in rust
• build a chatbot on top of ollama
• generate embeddings for rag in rust
• manage ollama models programmatically
• implement tool/function calling with local llms

When to choose

• you're writing Rust and want a simple typed client for Ollama
• you need streaming, chat, embeddings, or tool calling against a local Ollama server
• you want a lightweight alternative to raw HTTP calls to the Ollama API

When to avoid

• you need to talk to OpenAI, Anthropic, or other non-Ollama LLM APIs
• you're not using Rust
• you need a full inference engine rather than a client for an existing Ollama server

Facets

library · maturity active

http-client llm-inference rag chatbot sdk large-language-models artificial-intelligence developer-tools apis rust cross-platform ollama llm-client async embeddings function-calling streaming

Member repositories

For agents

markdown · JSON · MCP: product_card(name="pepperoni21/ollama-rs")