# llamafile Published articles for llamafile. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Structured Output with LangChain and Llamafile DevFeed: [Structured Output with LangChain and Llamafile]() Original publisher: [Read original article]() Author: brakmic Published: 2025-06-22T16:50:12Z Content type: tutorial Language: en Sources: [Harris Brakmic - Coding]() Topics: [LangChain](), [llamafile](), [JSON](), [llama.cpp](), [Parser](), [Pydantic]() Tags: [ai](), [code](), [coding](), [cpp](), [how-to](), [import](), [json](), [langchain](), [llama-cpp](), [llamafile](), [llm](), [local](), [local-llm](), [models](), [properties](), [python](), [structured-output]() ### AI overview A tutorial on using LangChain with Llamafile to produce structured JSON output from a local large language model. It uses JsonOutputParser, PromptTemplate, and a Pydantic model because Llamafile does not provide a with_structured_output method. ### Source excerpt Learn how to extend Llamafile with LangChain's JsonParser to produce clean, structured JSON output ## 4M Models Scanned: Protect AI + Hugging Face 6 Months In DevFeed: [4M Models Scanned: Protect AI + Hugging Face 6 Months In]() Original publisher: [Read original article]() Author: Sean Morgan Published: 2025-04-14T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [hugging face](), [Machine Learning, Security Attacks](), [Threat Research](), [Security](), [threat detection](), [Zero Trust](), [obfuscation](), [vulnerability](), [payload](), [Script](), [llamafile](), [Tensorflow]() Tags: [ai-ml](), [hub](), [hugging-face](), [keras](), [llamafile](), [obfuscation](), [partnerships](), [payload](), [security](), [tensorflow](), [threat-detection](), [vulnerability](), [zero-trust]() ### AI overview Hugging Face and Protect AI report six months of collaboration on Guardian, a scanning system that improves security checks for models hosted on the Hugging Face Hub. Guardian added four detection modules, expanded format and obfuscation coverage, identified a Keras vulnerability, and provides inline alerts and vulnerability reports. The system uses a zero trust approach that treats arbitrary code execution as unsafe, including code hidden through obfuscation. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Llamafile v0.8.14: a new UI, performance gains, and more DevFeed: [Llamafile v0.8.14: a new UI, performance gains, and more]() Original publisher: [Read original article]() Author: Stephen Hood Published: 2024-10-16T13:32:30Z Content type: release Language: en Sources: [Mozilla Hacks - the Web developer blog]() Topics: [Local AI](), [Language models](), [releases](), [Retrieval Augmented Generation (RAG)]() Tags: [ai](), [api](), [command-line](), [featured-article](), [hardware](), [llamafile](), [llms](), [open-source](), [performance](), [release](), [retrieval-augmented-generation-rag](), [ui]() ### AI overview Llamafile 0.8.14 adds a terminal chat interface, performance improvements, and expanded model support for running open LLMs locally. ### Source excerpt Discover the latest release of Llamafile 0.8.14, an open-source AI tool by Mozilla Builders. With a new command-line chat interface, enhanced performance, and support for powerful models, Llamafile makes it easy to run large language models (LLMs) on your own hardware. Learn more about the updates and how to get involved with this cutting-edge project. The post Llamafile v0.8.14: a new UI, performance gains, and more appeared first on Mozilla Hacks - the Web developer blog. ## Mozilla Llamafile in Supabase Edge Functions DevFeed: [Mozilla Llamafile in Supabase Edge Functions]() Original publisher: [Read original article]() Author: Thor Schaeff Published: 2024-08-21T07:00:00Z Content type: tutorial Language: en Sources: [Supabase Blog]() Topics: [llamafile](), [Supabase](), [AI Inference](), [API](), [Large Language Model](), [Command-line interface](), [Docker](), [OpenAI](), [fly.io](), [Open Source]() Tags: [ai-inference](), [api](), [cli](), [docker](), [fly-io](), [llamafile](), [llms](), [open-source](), [openai](), [vs-code]() ### AI overview This tutorial explains how to run Mozilla Llamafile as an OpenAI API-compatible inference server with Supabase Edge Functions. It covers calling Llamafile through the functions-js interface or the OpenAI Deno SDK, serving functions locally with the Supabase CLI and Docker, and deploying Llamafile and Supabase Edge Functions. ### Source excerpt Use Mozilla Llamafile OpenAI API compatible server in Supabase Edge Functions. ## Sponsoring sqlite-vec to enable more powerful Local AI applications DevFeed: [Sponsoring sqlite-vec to enable more powerful Local AI applications]() Original publisher: [Read original article]() Author: Stephen Hood Published: 2024-06-25T15:25:58Z Content type: news Language: en Sources: [Mozilla Hacks - the Web developer blog]() Topics: [Local AI]() Tags: [ai](), [artificial-intelligence](), [discord](), [featured-article](), [firefox](), [llamafile](), [local-ai](), [mozilla](), [on-device](), [open-source](), [rag](), [sqlite](), [vector]() ### AI overview Mozilla is sponsoring sqlite-vec through its Builders program to bring vector search to SQLite for local AI applications. The project is presented as enabling on-device uses such as retrieval-augmented generation and semantic search. ### Source excerpt Today we're proud to announce the next Mozilla Builders project: sqlite-vec. Led by independent developer Alex Garcia, this project brings vector search functionality to the beloved SQLite embedded database. Alex has been working on this problem for a while, and we think his latest approach will have a great impact by providing application developers with a powerful new tool for building Local AI applications. The post Sponsoring sqlite-vec to enable more powerful Local AI applications appeared first on Mozilla Hacks - the Web developer blog. ## Llamafile's progress, four months in DevFeed: [Llamafile's progress, four months in]() Original publisher: [Read original article]() Author: Stephen Hood Published: 2024-04-25T15:34:08Z Content type: article Language: en Sources: [Mozilla Hacks - the Web developer blog]() Topics: [Language models](), [SDKs]() Tags: [ai](), [cuda](), [developer-tools](), [discord](), [featured-article](), [firefox](), [gpu](), [hugging-face](), [inference](), [language-models](), [llama-cpp](), [llamafile](), [open-source](), [openai](), [raspberrypi]() ### AI overview Mozilla's update on llamafile describes v0.8 support for recent open models, CPU-inference performance work, and tinyBLAS GPU acceleration for NVIDIA and AMD hardware without requiring CUDA installation on Windows. ### Source excerpt When Mozilla's Innovation group first launched the llamafile project late last year, we were thrilled by the immediate positive response from open source AI developers. It's become one of Mozilla's top three most-favorited repositories on GitHub, attracting a number of contributors, some excellent PRs, and a growing community on our Discord server. The post Llamafile's progress, four months in appeared first on Mozilla Hacks - the Web developer blog.