Haystack Blog
Articles about Haystack, NLP, LLMs and open source tools.
All articles
CPU-Optimized Embedding Models with fastRAG and Haystack
Discover how to use optimized embedding models on CPUs to reduce latency, and improve throughput of retrieval and indexing
August 1, 2024
Mixedbread π€ deepset: Announcing our New German/English Embedding Model
Learn about the new open-source German/English embedding model by deepset and Mixedbread
July 18, 2024
Benchmarking Haystack Pipelines for Optimal Performance
Step-by-step instructions to evaluate and optimize your RAG pipeline's performance
June 24, 2024
RAG Evaluation with Prometheus 2
Prometheus 2 is a SOTA open-source model trained specifically for evaluation. Learn about how it works, and how to evaluate RAG pipelines with it.
June 17, 2024
Building RAG Applications with NVIDIA NIM and Haystack on K8s
How to self-host and orchestrate NVIDIA NIMs for Haystack RAG pipelines in Kubernetes.
June 2, 2024
Monitor and trace your Haystack pipelines with Langfuse
With the new Langfuse integration, it's easier than ever to have visibility into how your pipelines are performing.
May 17, 2024
Advanced Retrieval: Extract Metadata from Queries to Improve Retrieval
Use LLMs to extract metadata from queries to use as filters that improve retrieval in RAG applications.
May 13, 2024
Chatting with SQL Databases 3 Ways
Using Haystack to talk to SQL in natural language
April 22, 2024
Level up Your RAG Application with Speaker Diarization
Leverage speaker labels with AssemblyAI and Haystack
March 21, 2024
Hosted or self-hosted RAG? Full flexibility with NVIDIA NIM integration in Haystack 2.0
New integrations with microservices from the NVIDIA AI Enterprise software platform, including NVIDIA NIM and NeMo Retriever, now allow you to iterate even faster across your RAG development cycle
March 18, 2024No articles found
You may want to try different keywords or check for any possible typos.