Improving Retrieval with Auto-Merging
For most RAG applications, where we first have to retrieve the most relevant context, we end up having to split up documents first, and index those smaller splits of documents.
Haystack Blog9 min read
Haystack Blog
Stay updated with the latest developments in Artificial Intelligence
Announcing Our New Short Course with DeepLearning.AI
DeepLearning.AI and Andrew Ng hold a special place in many AI/ML engineers’ careers and development. For many engineers, they’ve played a pivotal role into breaking into AI, or extending their knowledge and capabilities by teaching about core concepts and technologies at the right time.
Haystack Blog2 min readAdvanced RAG: Query Expansion
This is part one of the Advanced Use Cases series: 1️⃣ Extract Metadata from Queries to Improve Retrieval 2️⃣ Query Expansion 3️⃣ Query Decomposition 4️⃣ Automated Metadata Enrichment The quality of RAG (retrieval augmented generation) highly depends on the quality of the first step in the process:…
Haystack Blog7 min readCPU-Optimized Embedding Models with fastRAG and Haystack
One of the main and critical components of a retrieval augmented generation (RAG) pipeline is the embedding process, which forms the foundation for efficient information retrieval by transforming raw text into machine-readable vector representations.
Haystack Blog9 min readMixedbread 🤝 deepset: Announcing our New German/English Embedding Model
It’s 2024 and yet, most models today are still primarily geared towards English speaking markets. Today, deepset and Mixedbread are jointly announcing our latest contribution towards changing that landscape: A new open-source German/English embedding model - deepset-mxbai-embed-de-large-v1.
Haystack Blog2 min readBenchmarking Haystack Pipelines for Optimal Performance
In this article, we will show you how to use Haystack to evaluate the performance of a RAG pipeline. Note that the code in this article is meant to be illustrative and may not run as is; if you want to run the code, please refer to the python script.
Haystack Blog23 min readRAG Evaluation with Prometheus 2
When building real-world applications based on Language Models (such as RAG), evaluation plays an important role. Recently, evaluating generated answers using powerful proprietary Language Models (such as GPT-4) has become popular and correlates well with human judgment, but it comes with its own…
Haystack Blog11 min readBuilding RAG Applications with NVIDIA NIM and Haystack on K8s
Retrieval-augmented generation (RAG) systems combine generative AI with information retrieval for contextualized answer generation. Building reliable and performant RAG applications at scale is challenging.
Haystack Blog17 min readMonitor and trace your Haystack pipelines with Langfuse
Getting your LLM application into production is a huge milestone, but that’s only the beginning. It’s critical to monitor how your pipeline is performing in the real world so you can keep improving performance and cost, and proactively address any issues that might arise.
Haystack Blog9 min readAdvanced Retrieval: Extract Metadata from Queries to Improve Retrieval
This is part one of the Advanced Use Cases series: 1️⃣ Extract Metadata from Queries to Improve Retrieval 2️⃣ Query Expansion 3️⃣ Query Decomposition 4️⃣ Automated Metadata Enrichment In Retrieval-Augmented Generation (RAG) applications, the retrieval step, which provides relevant context to your…
Haystack Blog8 min readChatting with SQL Databases 3 Ways
Let’s talk about how we build AI applications that can interact with, even chat to SQL databases. Heads-up that this is a mini project that I tried out, and it’s objectively a simple approach to interacting with SQL with natural language.
Haystack Blog10 min read
Showing 29 of 29 stories
You're all caught up.
AiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news from Haystack Blog
Join 15,000+ AI enthusiasts