Juan Manuel Ciro

Excited to share that we trained rerankers at the cost/performance frontier and are open sourcing them! Contextual AI Reranker v2 🚀 Best performing, most efficient reranker 🤗 Open weights (1B, 2B, 6B) 🫡 Instruction-following (including recency-awareness) 🌐 Multilingual 1/4

Context engineering has become the critical bottleneck for enterprise AI. Your AI agent works perfectly in demos but breaks down with real-world data complexity. Why? I see 6 fundamental challenges that every AI engineer faces: from the "needle in a haystack" problem where models lose critical information buried in long contexts, to the token cost explosion that makes production deployments prohibitively expensive. These are more than just technical hurdles, they're the difference between AI experiments and transformative business impact. Read my full thoughts below.

Introducing: Contextual AI MCP Server (now hosted) After great feedback with our local MCP server, we have added a hosted MCP server inside the platform! This mean every RAG agent is easily accessible via MCP. Added updated info on the hosted MCP server here: github.com/ContextualAI/c…

Tired of guessing if your LLM responses are “good enough?” With @ContextualAI’s LMUnit and CircleCI, you can run natural language unit tests directly in your CI/CD pipeline—turning subjective evals into automated, testable checkpoints. Read on: contextual.ai/blog/lmunit-ci…

The future of CI

$20k/month for an AI agent is an interesting pricing decision. We're in new territory, where potential buyers are almost explicitly being forced to choose between a human vs an AI to do a particular job.. Not sure if this is the right strategy, but certainly interesting times ahead. I think we can all agree on the specialization part though. Glad to see a giant in the industry embrace something we've been saying from the start.

Introducing LMUnit: Natural language unit testing for LLM evaluation How do you really know if your language model is behaving the way you expect? When evaluation is this critical, your best methodology shouldn't just be vibes. With SOTA results on FLASK & BigGenBench and top-10 on RewardBench, LMUnit brings the rigor and familiarity of traditional software engineering unit testing to LLM evaluation. Read on to learn how we built it and try it for free using our API 👇 🔗 🧵 (1/5)

A real honour and career dream that PRISM has won a @NeurIPSConf best paper award! 🌈 One year ago I was sat in a 13,000+ person audience of NeurIPs '23 having just finished data collection. Safe to say I've gone from feeling #stressed to very #blessed 😁

@hannahrosekirk @NeurIPSConf Congrats 🎉🎉

Wahoo PRISM will officially be taking a trip to @NeurIPSConf this year as an oral presentation 🤩 (and my first ever 10/10 in a conference review process 🤯)

@SaraDurango_ @joseluisintilde Totalmente de acuerdo, nos vemos por allá, muchos años sin hablar

@ciropython @joseluisintilde Claaa🔥🔥🔥🫶🏻 Es obvio que no habrá un vocalista como Chester, peeero: 1. Emiliy es una tesa! 2. No se puede reducir una banda a un único integrante 3. Qué brutal poder disfrutar los temones de Linkin Park en vivo!🔥 4. Mike también es vocalista de la banda 5. Qué chimbaa!🔥🫶🏻

@SaraDurango_ @joseluisintilde Vas a ir al concierto?

@joseluisintilde El setlist está brutaaal! Qué necesidad de quejarse por nimiedades! 🥱🥱🥱🙄

@jobergum Would be great a tutorial step by step showing how you created the data and the code for evaluation.

To evaluate your R in RAG, you need only a TSV file with labeled judgments and a simple scraper script.

@AsociacionMi Pequeño aporte

Eros nos necesita por favor, su estado de salud es lamentable y triste, ya debemos $515.000 pesos y tenemos que recaudar lo de su vuelo para tenerlo con nosotros, ahora si es el último 🙈🥺 buscamos 100 corazones que por favor lo ayuden con 10 mil pesos, es urgente pagar su cuenta, a todos infinitas gracias por no dejarnos solos 💙💙💙🥺🥺 Bancolombia Ahorros 35270197653 NIT 901039372 Nequi 3118009018 Ahorro a la mano 13118239988 DaviPlata 3118239988 Paypal vivianieto@yahoo.es Rifa: 📲 (320) 725-5125

@LiLiPuRpLe @FundacionToby Esta perfecto

@FundacionToby Ayyy que padre

Amigos!!! Estrenamos rifa 🐶🖤🥳 Funko pet personalizado para el ganador 👀 $400 el número!!! A partir de que anúncienos al ganador tendrán que esperar mes y medio para recibir el premio, ya que como es personalizado, se trabaja desde cero 😉 También los invitamos a que chequen el bonito trabajo de @art_casesbyluisa (en IG) que nos está apoyando con esta rifa 🐶🖤 - BANCOMER Cuenta: 0117412991 Clabe: 012180001174129915 Tarjeta: 4555113008742068 - SANTANDER Cuenta: 60577008001 Clabe: 014180605770080014 Tarjeta: 5579070082854475

@AsociacionMi Un pequeño aporte

Tenemos más de 600 números 🙁🙁Pasamos a recordarles la rifa, cuesta 30 mil pesos y es un viaje para 2 personas a Guatapé con todo pago, 3 días 2 noches, así nos ayudan en esta titánica labor, a diario rescatamos animalitos graves, con nosotros viven más de 200, haremos jornada de esterilización gratuita y pagaremos algo de la deuda en la clínica veterinaria, para comprar por favor escribir al WhatsApp 📲 3207255125 Infinitas gracias Bancolombia Ahorros 35270197653 NIT 901039372 Nequi 3118009018 Ahorro a la mano 13118239988 DaviPlata 3118239988 Paypal vivianieto@yahoo.es

@nana1gc Un pequeño aporte

BUSCAMOS 276 PERSONAS QUE NOS AYUDEN A PAGAR EL ARRIENDO DEL REFUGIO🙏🏻🥺 276 personas que donen 10.000 pesitos o lo que esté a su alcance, todo se recibe con amor🥹💖 Ha sido MUY duro recoger esta meta y apenas recogimos para pagarle a nuestros trabajadores.

Today we're launching PRISM, a new resource to diversify the voices contributing to alignment. We asked 1500 people around the world for their stated preferences over LLM behaviours, then we observed their contextual preferences in 8000 convos with 21 LLMs arxiv.org/abs/2404.16019

Today, we’re excited to announce RAG 2.0, our end-to-end system for developing production-grade AI. Using RAG 2.0, we’ve created Contextual Language Models (CLMs), which achieve state-of-the-art performance on a variety of industry benchmarks. CLMs outperform strong RAG baselines built using GPT-4 and top open-source models like Mixtral, according to our research and customers. Read more in our blog post: rag2.ai

RAG 2.0 is turning LLMs from being an awesome toy to a tool that one can safely rely on - so businesses can actually start using AI in their workflows. We at Contextual AI have done an awesome groundbreaking work to make it work. Please see the break down of how and why it works here: