Build and customize complex AI applications with a flexible framework in this new short course, Building AI Applications with Haystack. Created in collaboration with @deepset_ai, and taught by @tuanacelik, who is the developer relations lead for Haystack at deepset. Generative AI technology is changing rapidly and it can be challenging to integrate APIs from different LLMs, vector databases, and various tools such as web search. In this course, you will learn how to use the Haystack framework to make your development process more modular, allowing you to manage complexity and focus more on building your application. In detail, you’ll: - Build a RAG pipeline using Haystack’s main building blocks – components, pipelines, and document stores. - Create custom components in your pipeline by building a Hacker News summarizer that extends your app’s ability to access APIs. - Use conditional routing to create a branching pipeline with a fallback to web search mechanism when the LLM does not have the necessary context to respond to the user's query. - Build a self-reflecting agent for named entity recognition that loops using an output validator custom component. - Create a chat agent using OpenAI's function-calling capabilities which allow you to provide Haystack pipelines as tools to the LLM, enhancing that agent's capabilities. By the end of this course, you will learn a high-level orchestration framework that can help make your applications flexible, extendible, and maintainable, even as the technology stack changes, new user needs arise, and you add new features to your application. Please sign up here: deeplearning.ai/short-course…

We finally did it 🎉 There are so many great examples of Haystack being used in very specific scenarios and together with several other technologies, and we've finally started to collect them in one place. I present to you, the 👩🏻‍🍳 Haystack Cookbok. We will of course be adding more to this repo, and welcome any contributions that add notebooks. So far we have examples with: - Google Vertex AI for Gemini - Mixtral-8x7B by @MistralAI - Multilingual QA with @cohere - RAG with generators from @Gradient_AI_ - legal docs QA with embeddings from @JinaAI_ - podcast QA using Whisper from @OpenAI ..and the list goes on. Looking forward to seeing this repo grow and honestly, I'm happy for future me who can just go to ONE place to find the short showcases we built 💙 👉 github.com/deepset-ai/haysta…

We’re excited to announce the launch of Qdrant Hybrid Cloud, the first-ever managed vector database you can deploy anywhere—cloud, on-premise, or edge— designed for true deployment flexibility, data sovereignty, privacy, and control. Why is this big? 🚀 Deployment flexibility and data sovereignty are critical as the industry moves from prototyping to deploying production-ready AI applications. Easy integration with existing systems complements these advantages, streamlining development and operations. Key benefits of the Hybrid Cloud: ✔️ Deploy Anywhere: Deploy Qdrant in any environment of choice with our Kubernetes-native design. ✔️ Full Data Sovereignty: Enjoy privacy control with decoupled data and control planes with complete database isolation. ✔️ Fully Managed: Enjoy the benefits of a managed vector database within your own environment. ✔️ Effortless Setup: One-line installation by simply adding your environment to your Qdrant Cloud account. Thank you to our trusted launch partners for their collaboration: @OracleCloud, @RedHat, @Vultr, @OVHcloud, @Scaleway, @DigitalOcean, STACKIT, @llama_index, @langchain, @AirbyteHQ, @CivoCloud, @JinaAI_, @Aleph__Alpha, @Haystack_AI by @deepset_ai.

#RAG apps require clean, searchable data to help the #LLM produce correct answers. Do you know how to manage it with @Haystack_AI 2.0? 🔍 Let's talk about this often-forgotten side of RAG apps: indexing pipelines 📚 📬Check out my post here: zansara.dev/posts/2023-11-05… #AI #NLP

Join our hosts, @_lewtun & @lvwerra for the O’Reilly Book Club: Natural Language Processing with Transformers OCT 24, 10AM EDT. Learn about a variety of NLP tasks transformers can help you solve. Presented thanks to @deepset_ai. oreil.ly/XI00x

Another post for my @Haystack_AI 2.0 series is out! 📨 I've talked at length about the Pipeline concept and its quirks. In Haystack 2.0 we have a plan to fix them all: it's called Canals. Want to learn more? zansara.dev/posts/2023-10-26… #AI #LLM #Python

We’re excited to host our next Anthropic Hackathon in London. Come build apps with the Claude API, connect with expert judges, and win prizes. Nov 4-5. Apply here: partiful.com/e/pQHQrWPg1A6P3…

Finally, jina-embeddings-v3 is here! A frontier multilingual embedding model with 570M parameters, 8192-token length, achieving SOTA performance on multilingual and long-context retrieval tasks. It outperforms the latest proprietary models from OpenAI and Cohere, and outperforms multilingual-e5-large-instruct across all multilingual tasks. In fact, as of today, jina-embeddings-v3 is the best multilingual model and ranks 2nd on the MTEB English leaderboard for models < 1B parameters.