Optimizing RAG Through an Evaluation-Based Methodology
Learn how Qdrant-powered RAG applications can be tested and iteratively improved using LLM evaluation tools like Quotient.
Atita Arora
·June 12, 2024
Learn how Qdrant-powered RAG applications can be tested and iteratively improved using LLM evaluation tools like Quotient.
Atita Arora
·June 12, 2024
Explore how RAG enables LLMs to retrieve and utilize relevant external data when generating responses, rather than being limited to their original training data alone.
Sabrina Aquino
·March 19, 2024
Much faster sparse vectors, optimized indexation of text fields and optional CPU resource management configuration.
David Myriel, Mike Jang
·March 06, 2024
Why are vector databases needed for RAG? We debunk claims of increased LLM accuracy and look into drawbacks of large context windows.
David Myriel
·February 27, 2024
Use Qdrant's Binary Quantization to enhance the performance and efficiency of OpenAI embeddings
Nirant Kasliwal
·February 21, 2024
Explore the key functionalities of vector embeddings and learn how they convert complex data into a format that machines can understand.
Sabrina Aquino
·February 06, 2024
Combining our most popular features to support scalable machine learning solutions.
David Myriel
·February 06, 2024
Qdrant released a new functionality that lets you constrain the space in which a search is performed, relying only on vectors.
Luis Cossío
·January 31, 2024
An overview of vector databases, detailing their functionalities, architecture, and diverse use cases in modern data processing.
Sabrina Aquino
·January 25, 2024
Sparse vectors, Discovery API, user-defined sharding, and snapshot-based shard transfer. That's what you can find in the latest Qdrant 1.7.0 release!
Kacper Łukawski
·December 10, 2023
Sparse vectors are the generalization of TF-IDF and BM25, that allows to leverage the power of neural networks for text retrieval.
Nirant Kasliwal
·December 09, 2023
Why vector search requires a dedicated service.
Andrey Vasnetsov
·November 30, 2023
Qdrant 1.6 brings recommendations strategies and more flexibility to the Recommendation API.
Kacper Łukawski
·October 25, 2023
FastEmbed is a Python library engineered for speed, efficiency, and accuracy
Nirant Kasliwal
·October 18, 2023