Mistral AI: Modelli, API e Self-Hosting
«Mistral AI: Modelli, API e Self-Hosting» è un corso online di LLM open source di livello principiante, tenuto da InsightLearn Curated AI su InsightLearn. Il percorso comprende 7 lezioni organizzate in 3 sezioni, per una durata complessiva di 3h 0m. Mistral Small, Large e Nemo: modelli europei ad alte prestazioni con licenza Apache 2.0. API cloud, self-hosting e integrazione in pipeline LLM.
- Docente: InsightLearn Curated AI
- Categoria: LLM open source
- Livello: principiante
- Durata: 3h 0m
- Accesso: gratuito in questa fase di validazione, in cambio di un feedback al termine
- Certificato: certificato di completamento verificabile online
Descrizione del corso
InsightLearn è in fase di sviluppo (work in progress): i contenuti di questa pagina sono pubblicati esclusivamente a fini di verifica e test.
Basato su docs.mistral.ai e mistral-inference GitHub (Apache 2.0). Mistral AI propone modelli efficienti con context window 128K token: Small (edge/cost), Large (reasoning avanzato), Nemo (open, Apache 2.0), Codestral (coding). Copre: Mistral API con Python SDK, function calling, JSON mode, embeddings, self-hosting con Ollama e mistral-inference, confronto Small vs Large per budget, integrazione in LangChain.
Cosa imparerai
- Curated from public resources. Mistral Small, Large e Nemo: modelli europei ad alte prestazioni con licenza Apache 2.0. API cloud, self-hosting e integrazione in pipeline LLM.
Programma del corso
- Python SDK: chat completions, streaming, batch (14 min)
- Function calling e JSON mode strutturato (16 min)
- Mistral Embed: embeddings multilingue per RAG (14 min)
- Self-hosting Mistral Nemo con Ollama e vLLM (16 min)
- Mistral in LangChain: ChatMistral e MistralAIEmbeddings (14 min)
- Small vs Large: budget optimization e fallback strategy (14 min)
- Mistral vs OpenAI vs Anthropic: confronto costi/performance (12 min)
Dalle lezioni
Estratto della trascrizione di «Python SDK: chat completions, streaming, batch»
Open AI just released a huge new update to their API for getting structured outputs. And in this video, I'm going to walk you through everything that you need to know. I will be showing you some code examples, which I will also share with you so you know how you can effectively use this to build your AI systems. Now, for those of you that are new here, my name is Dave Ebelar. I'm the founder of data Lumina, and I've been building custom data and AI solutions for the past five years. And I also create videos like this to help you do the same. Now let's get into it. All right, so the new structured output in…
Estratto della trascrizione di «Function calling e JSON mode strutturato»
In this video, we are diving into a game-changing feature that can take your AI projects to the next level. OpenAI's Structured Output Large-language models are amazing at answering questions. But let's be real, sometimes those responses are a bit all over the place, right? In real-world apps, we can't afford messy unstructured responses. We need them neat, predictable, and perfectly formatted. That's where OpenAI's Structured Output comes in. It ensures that responses you get are in a pr- defined format like JSON, so that you can easily integrate them into your app's UI, workflows, or processes without worrying about inconsistencies. In this video, we'll walk you through how structured output works, how it's achieved using function calling and JSON…
Estratto della trascrizione di «Mistral Embed: embeddings multilingue per RAG»
So your company has 500 gigabytes of documents in their server and you're asked to connect an AI assistant just like ChachiPT to answer questions about these documents and you think to yourself, man, how am I supposed to get this done? From your experience, you know that typical chat applications can't accept more than a dozen files. So you have to use a different method to allow the AI to search, read and understand the entire files. But how? Maybe you think you can create a clever algorithm to search the title of the documents and its contents to rank them by relevance. But you soon realize that that means that every time the user searches, it would need…
Altri corsi di LLM open source
Domande frequenti
Quanto dura il corso Mistral AI: Modelli, API e Self-Hosting?
Il corso dura 3h 0m in totale, con 7 lezioni suddivise in 3 sezioni, da seguire online al proprio ritmo.
Serve esperienza pregressa?
Il corso è di livello principiante e non indica requisiti specifici di ingresso.
Il corso rilascia un certificato?
Sì: al completamento del corso ricevi un certificato di completamento verificabile online.