Resources under the MIT license
Datasets, prompts, models and other resources published under the MIT license, most used first.
Source : https://opensource.org/license/mit
llama.cpp server for a GGUF model
Run any GGUF model with the llama.cpp server: OpenAI-compatible API on port 8080, works without a GPU too.
RAG prompt: check that an answer is supported by the sources
Checks a draft answer sentence by sentence against the retrieved passages and flags unsupported claims, as JSON.
RAG prompt: rewrite a chat question into search queries
Turns the last message of a conversation into a standalone search query plus three variants, before retrieval.
Corpus: AI resource definitions (English)
Definitions of every AI resource type on Contexte Tech, one chunk each with the guide URL: a small English corpus ready for RAG.
Guardrail: mask API keys and passwords
Guardrail that masks API keys, tokens, passwords, private keys and connection strings before a text, file or export is sent to an AI. Rules, 14 test cases…
AI prompt for an Amazon or Shopify product listing
Prompt to write a product listing for Amazon or Shopify in English: title, 5 bullet points and description, from raw product specs.
BGE-M3 embeddings for RAG over long documents
BGE-M3 for RAG over long documents: 1024 dimensions, up to 8,192 tokens, 100+ languages, no prefix needed. MIT license.
JSON schema: classify a support ticket
JSON Schema to classify a support ticket: category, priority, sentiment, one-sentence summary and next action for the support team.
JSON schema: extract a resume
JSON Schema to extract a resume with an LLM: experience, skills, education and certifications. Leaves out age, photo and other protected data.
JSON schema: extract a U.S. invoice
JSON Schema to extract a U.S. invoice with an LLM: vendor, invoice number, dates, line items, subtotal, sales tax and total in USD.
Local automations: n8n and Ollama
docker-compose stack to automate with a local AI: n8n (workflows) and Ollama (model), without sending data to an external API.
Guardrail: mask U.S. personal data (SSN, phone, card)
Guardrail that masks U.S. personal data in AI assistant replies: SSNs, +1 phone numbers, personal emails and card numbers. Rules, 12 tests, code.
Minimal private AI chat: Ollama and Open WebUI
The simplest stack for a private AI chat: Ollama and Open WebUI with docker-compose, interface on port 3000.
Mistral 7B on a 16 GB Mac with Ollama
Ollama Modelfile to run Mistral 7B Instruct locally on a 16 GB Mac: Q4 quantization, 8k context, concise answers in English.
nomic-embed-text embeddings locally with Ollama
nomic-embed-text for a 100% local English RAG with Ollama: 768 dimensions, long texts, search_query: / search_document: prefixes. Apache 2.0.
Private chat on your documents: Ollama, Qdrant, Open WebUI
docker-compose stack for a private chat on your documents: Ollama (model), Qdrant (vector database) and Open WebUI (interface).
Qwen2.5 7B with vLLM on a 24 GB GPU
Serve Qwen2.5 7B Instruct with vLLM on a 24 GB GPU: OpenAI-compatible API, 8k context, a single command.
Red teaming: 12 attacks on a customer service chatbot
12 attacks to replay on a U.S. e-commerce support chatbot: impersonation, data leaks, prompt injection, unauthorized refunds. Expected reply for each.
Red teaming: 10 tests on a U.S. HR assistant
10 tests for an internal HR assistant in the U.S.: employee data, hiring discrimination (EEOC), impersonation, injection, and 2 legitimate questions.