{"slug": "langchain-rust-build-llm-apps-with-ollama-local-models-in-pure-rust-no-python", "title": "langchain-rust: Build LLM apps with Ollama + local models in pure Rust — no Python needed", "summary": "A developer has released langchain-rust, a pure Rust framework for building LLM applications with local models via Ollama, eliminating the need for Python. The framework includes first-class Ollama support, nine vector store backends, BM25 keyword search, hybrid retrieval, GraphRAG, CorrectiveRAG, and a code interpreter, all packaged as a single binary.", "body_md": "If you're running local models through Ollama and tired of Python's overhead, check out [langchain-rust](https://github.com/atliliw/langchainrust).\n\nIt's a full LLM framework in pure Rust that works great with local models:\n\n-\n**Ollama support** — first-class integration with tool calling, vision, and streaming\n-\n**9 vector store backends** — InMemory, SQLite, Qdrant, ChromaDB, Redis, PGVector, MongoDB, Pinecone, FileVectorStore\n-\n**BM25 keyword search** — with Chinese/English tokenization, no external dependency\n-\n**Hybrid retrieval** — BM25 + Vector with RRF fusion for better recall\n-\n**GraphRAG** — Knowledge graph construction + community detection, all local\n-\n**CorrectiveRAG** — Self-correcting retrieval with hallucination detection\n-\n**Code Interpreter** — LocalSandbox (subprocess), E2B cloud, or WASM sandbox\n-\n**LocalEmbeddings** — Run embeddings without calling an API\n\nPlus: LangGraph workflows, MCP client/server, 7 memory types, guardrails, and 12+ built-in tools.\n\nSingle binary, no virtualenv, no pip conflicts. Just `cargo add langchainrust`\n\nand go.\n\nGitHub: [https://github.com/atliliw/langchainrust](https://github.com/atliliw/langchainrust)\n\nDocs: [https://docs.rs/langchainrust](https://docs.rs/langchainrust)", "url": "https://wpnews.pro/news/langchain-rust-build-llm-apps-with-ollama-local-models-in-pure-rust-no-python", "canonical_source": "https://dev.to/lili_at_32369546c2947bd24/langchain-rust-build-llm-apps-with-ollama-local-models-in-pure-rust-no-python-needed-52jl", "published_at": "2026-08-03 09:24:01+00:00", "updated_at": "2026-08-03 09:42:03.396904+00:00", "lang": "en", "topics": ["large-language-models", "developer-tools", "ai-infrastructure"], "entities": ["langchain-rust", "Ollama", "Qdrant", "ChromaDB", "Redis", "PGVector", "MongoDB", "Pinecone"], "alternates": {"html": "https://wpnews.pro/news/langchain-rust-build-llm-apps-with-ollama-local-models-in-pure-rust-no-python", "markdown": "https://wpnews.pro/news/langchain-rust-build-llm-apps-with-ollama-local-models-in-pure-rust-no-python.md", "text": "https://wpnews.pro/news/langchain-rust-build-llm-apps-with-ollama-local-models-in-pure-rust-no-python.txt", "jsonld": "https://wpnews.pro/news/langchain-rust-build-llm-apps-with-ollama-local-models-in-pure-rust-no-python.jsonld"}}