{"slug": "serializing-llm-pipelines", "title": "Serializing LLM Pipelines", "summary": "Haystack introduces serialization for LLM pipelines, enabling conversion to a format that can be saved, loaded, and transmitted across networks. The feature supports components like TransformersChatGenerator and ChatPromptBuilder, with documentation available on the Haystack website.", "body_md": "`TransformersChatGenerator`\n\n`ChatPromptBuilder`\n\n**📚 Useful Documentation:**\n[Serialization](https://docs.haystack.deepset.ai/docs/serialization)\n\nSerialization means converting a pipeline to a format that you can save on your disk and load later. It’s especially useful because a serialized pipeline can be saved on disk or a database, get sent over a network and more.", "url": "https://wpnews.pro/news/serializing-llm-pipelines", "canonical_source": "https://haystack.deepset.ai/tutorials/29_serializing_pipelines/", "published_at": "2026-06-15 00:00:00+00:00", "updated_at": "2026-06-24 12:19:02.331288+00:00", "lang": "en", "topics": ["large-language-models", "developer-tools"], "entities": ["Haystack", "TransformersChatGenerator", "ChatPromptBuilder"], "alternates": {"html": "https://wpnews.pro/news/serializing-llm-pipelines", "markdown": "https://wpnews.pro/news/serializing-llm-pipelines.md", "text": "https://wpnews.pro/news/serializing-llm-pipelines.txt", "jsonld": "https://wpnews.pro/news/serializing-llm-pipelines.jsonld"}}