Samuel Matioli

@sama How much data do you share with DoW? Are interactions with ChatGPT (Free or Enterprise) shared with them?

I'd like to answer questions about our work with the DoW and our thinking over the past few days. Please AMA.

Build and test Langflow components directly in VS Code A community-built VS Code extension makes it possible to edit Langflow component code, sync changes back to your local instance, and run flows, all without leaving your IDE. With this extension, developers can: - Browse Langflow projects and flows inside VS Code - Open and edit component Python code - Save and sync changes back to Langflow - Execute flows via API and stream outputs in real time Designed for developers who want a tighter feedback loop when working on custom Langflow components, especially alongside AI-assisted coding tools. Built by @MatioliSamuel 👏 🔗 VS Code Marketplace marketplace.visualstudio.com/items?itemName… 🎥 Demo youtu.be/jSSfBC2b8KY

The NEXT New York Area Cassandra User Group will be held at the NetApp NYC office, 18th February. Help spread the word! luma.com/q6kuetpe

@Oledobrasil Até pq os uniformes parecem o do 7x1

Hoje está com uma cara daquele jogo que todo mundo acha que o Palmeiras vai atropelar mas termina 1 a 0 pro lanterna do campeonato

New data sink for LlamaCloud 🔥 🦙 Connect your @astradb database as a data sink in LlamaCloud for seamless vector storage and retrieval. Setting it up is straightforward - we support both UI configuration and programmatic setup through our Python and TypeScript clients. Here's what you need to know: 🔧 Simple configuration requiring just your AstraDB application token, API endpoint, and collection details 📊 Full support for query operators for precise metadata filtering This is enterprise-grade vector storage that integrates seamlessly with our indexing and retrieval systems, making it perfect for production agentic RAG applications that need reliable, scalable vector search. Read the full integration guide: docs.cloud.llamaindex.ai/llamacloud/int…

I just published Langflow 1.3 — Nova versão do Astra DB JSON Tool medium.com/p/langflow-1-3…

IBM drops a Speech Translation model under Apache 2.0 with the data being permissive and the majority being available No one cares, as IBM does not know how to do social media. They don’t even post it on LinkedIn

Where Did Retrieval Augmented Generation Come From—And Where Is It Going? from @DataStax datastax.com/blog/where-did…

Entendendo Tool Calling Agents, agentes de IA Generativa com @langchain @OpenAI e @DataStax Astra DB: youtube.com/watch?v=J-7bVd…

>@Mar_Sem_Fim: Dragar o Canal do Varadouro: má-fé, insensatez, ou só ignorância? marsemfim.com.br/dragar-o-canal…

Como criar aplicações com #IAGenerativa usando o #Langflow e os modelos da #MaritacaAI? Segue um vídeo que demonstra como criar um fluxo #RAG,com esta stack e usando o DataStax #AstraDB para Vector Search e embeddings NVidia: youtube.com/watch?v=yL5pi1…

DataStax adquiriu a Logspace, startup Brasileira que desenvolveu o Langflow: exame.com/negocios/norte… #VectorDB #Langchain #GenAI

Quer saber como desenvolver apps com IA Generativa? Não perca este workshop!

@AstraDB Cassandra-based Vector DB 🌌 Explore the langchain-astradb integration package! Harness the serverless, vector-capable database built on Apache Cassandra for scalable NoSQL solutions enhanced with the power of vector similarity search. python.langchain.com/docs/integrati…

@thebrianbug You can use MMR to choose which documents will be part of the context. An example with AstraDB is here: #mmr-maximal-marginal-relevance-search" target="_blank" rel="nofollow noopener">python.langchain.com/docs/integrati…

Seeking advice: How have you made your LLM RAG system less brittle when faced with too many potential matches from the vector database? #buildinpublic #rag #llm

#SalvePedro Pedro é filho de Bruno Pereira, um dos indigenistas mais combativos do Brasil, assassinado covardemente em junho de 2022. Toda ajuda é bem vinda! vakinha.com.br/4342271

Astra assistant api makes it so easy to call different LLMs via API and compare so I tried comparing 6 different LLMs using the most scientific methodology available: Increasingly complex kitten ASCII art. See results using the same set of prompts starting with GPT4:

This week in time for #reinvent2023 we added AWS Bedrock support to @DataStax's Astra Assistants API. Just add your AWS creds to your OpenAI object and pick your model (for embedding and completion). Here I'm calling @AnthropicAI claude-2 through @awscloud bedrock with the OpenAI SDK For more examples and details on api coverage check out this github repo github.com/datastax/astra…

Excited to talk with @PatrickMcFadin at @DataStax on November 30th about how they built an open source RAG application for production. Register here: datastax.com/resources/webi…

@quasemarcio Qual curso?