Qdrant Blog
Features and News
Qdrant's Trusted Partners for Hybrid Cloud Deployment
With the launch of Qdrant Hybrid Cloud we provide developers the ability to deploy Qdrant as a managed vector database in any desired environment.
Advancements and Challenges in RAG Systems - Syed Asad | Vector Space Talks
Syed Asad unfolds the challenges of developing multimodal RAG systems at Kiwi Tech, detailing the balance between accuracy and cost-efficiency, and exploring various tools and approaches like GPT 4 and Mixtral to enhance family tree apps and financial chatbots while navigating the hurdles of data privacy and infrastructure demands.
Building Search/RAG for an OpenAPI spec - Nick Khami | Vector Space Talks
Nick Khami discuss Trieve's work with Qdrant's Open API spec for creating powerful and simplified search and recommendation systems, touching on real-world applications, technical specifics, and the potential for improved user experiences.
Gen AI and Vector Search - Iveta Lohovska | Vector Space Talks
Iveta Lohovska discusses the importance of explainability and transparency, discussing high-stakes use cases in sectors like cybersecurity and climate data, and emphasizing the necessity for on-prem solutions and traceable vector databases to ensure data integrity and confidentiality.
Teaching Vector Databases at Scale - Alfredo Deza | Vector Space Talks
Alfredo Deza discusses the practicality of machine learning operations, highlighting how personal interest in topics like wine datasets enhances engagement, while reflecting on the synergies between his professional sportsman discipline and the persistent, straightforward approach required for effectively educating on vector databases and large language models.
How to meow on the long tail with Cheshire Cat AI? - Piero and Nicola | Vector Space Talks
Cheshire Cat AI's Piero Savastano and Nicola Procopio discusses the framework's vector space complexities, community growth, and future cloud-based expansions.
Response to CVE-2024-2221: Arbitrary file upload vulnerability
Upgrade your deployments to at least v1.8.0. Cloud deployments not materially affected.
Introducing FastLLM: Qdrant’s Revolutionary LLM
Lightweight and open-source. Custom made for RAG and completely integrated with Qdrant.
VirtualBrain: Best RAG to unleash the real power of AI - Guillaume Marquis | Vector Space Talks
Guillaume Marquis, CTO & Co-Founder at VirtualBrain, reveals the mechanics of advanced document retrieval with RAG technology, discussing the challenges of scalability, up-to-date information, and navigating user feedback to enhance the productivity of knowledge workers.
Qdrant's Trusted Partners for Hybrid Cloud Deployment
With the launch of Qdrant Hybrid Cloud we provide developers the ability to deploy Qdrant as a managed vector database in any desired environment.
Advancements and Challenges in RAG Systems - Syed Asad | Vector Space Talks
Syed Asad unfolds the challenges of developing multimodal RAG systems at Kiwi Tech, detailing the balance between accuracy and cost-efficiency, and exploring various tools and approaches like GPT 4 and Mixtral to enhance family tree apps and financial chatbots while navigating the hurdles of data privacy and infrastructure demands.
Building Search/RAG for an OpenAPI spec - Nick Khami | Vector Space Talks
Nick Khami discuss Trieve's work with Qdrant's Open API spec for creating powerful and simplified search and recommendation systems, touching on real-world applications, technical specifics, and the potential for improved user experiences.
Gen AI and Vector Search - Iveta Lohovska | Vector Space Talks
Iveta Lohovska discusses the importance of explainability and transparency, discussing high-stakes use cases in sectors like cybersecurity and climate data, and emphasizing the necessity for on-prem solutions and traceable vector databases to ensure data integrity and confidentiality.
Teaching Vector Databases at Scale - Alfredo Deza | Vector Space Talks
Alfredo Deza discusses the practicality of machine learning operations, highlighting how personal interest in topics like wine datasets enhances engagement, while reflecting on the synergies between his professional sportsman discipline and the persistent, straightforward approach required for effectively educating on vector databases and large language models.
How to meow on the long tail with Cheshire Cat AI? - Piero and Nicola | Vector Space Talks
Cheshire Cat AI's Piero Savastano and Nicola Procopio discusses the framework's vector space complexities, community growth, and future cloud-based expansions.
Response to CVE-2024-2221: Arbitrary file upload vulnerability
Upgrade your deployments to at least v1.8.0. Cloud deployments not materially affected.
Introducing FastLLM: Qdrant’s Revolutionary LLM
Lightweight and open-source. Custom made for RAG and completely integrated with Qdrant.
VirtualBrain: Best RAG to unleash the real power of AI - Guillaume Marquis | Vector Space Talks
Guillaume Marquis, CTO & Co-Founder at VirtualBrain, reveals the mechanics of advanced document retrieval with RAG technology, discussing the challenges of scalability, up-to-date information, and navigating user feedback to enhance the productivity of knowledge workers.
Talk with YouTube without paying a cent - Francesco Saverio Zuppichini | Vector Space Talks
Francesco Zuppichini outlines the process of converting YouTube video subtitles into searchable vector databases, leveraging tools like YouTube DL and Hugging Face, and addressing the challenges of coding without conventional frameworks in machine learning engineering.
Production-scale RAG for Real-Time News Distillation - Robert Caulk | Vector Space Talks
Robert Caulk, founder of Emergent Methods, discusses the complexities of context engineering, the power of Newscatcher API for broader news access, and the sophisticated use of tools like Qdrant for improved recommendation systems, all while emphasizing the importance of efficiency and modularity in technology stacks for real-time data management.
Insight Generation Platform for LifeScience Corporation - Hooman Sedghamiz | Vector Space Talks
Hooman Sedghamiz discloses the potential of AI in life sciences, from custom knowledge applications to improving crop yield predictions, while tearing apart the nuances of in-house AI deployment for multi-faceted enterprise efficiency.
The challenges in using LLM-as-a-Judge - Sourabh Agrawal | Vector Space Talks
Everything you need to know about chatbots, Sourabh Agrawal goes in to detail on evaluating their performance, from real-time to post-feedback assessments, and introduces uptrendAI—an open-source tool for enhancing chatbot interactions through customized and logical evaluations.
Vector Search for Content-Based Video Recommendation - Gladys and Samuel from Dailymotion
Gladys Roch and Samuel Leonardo Gracio from Dailymotion, discussed optimizing video recommendations using Qdrant's vector search alongside challenges and solutions in content-based recommender systems.
IrisAgent and Qdrant: Redefining Customer Support with AI
Learn how IrisAgent leverages Qdrant for RAG to automate support, and improve resolution times, transforming customer service
Dailymotion's Journey to Crafting the Ultimate Content-Driven Video Recommendation Engine with Qdrant Vector Database
Dailymotion's Journey to Crafting the Ultimate Content-Driven Video Recommendation Engine with Qdrant Vector Database
Qdrant Summer of Code 24
Introducing Qdrant Summer of Code 2024 program. GSoC alternative.
Dust and Qdrant: Using AI to Unlock Company Knowledge and Drive Employee Productivity
Using AI to Unlock Company Knowledge and Drive Employee Productivity
The Bitter Lesson of Retrieval in Generative Language Model Workflows - Mikko Lehtimäki | Vector Space Talks
Mikko Lehtimäki delves into the intricate world of retrieval-augmented generation, discussing how Yokot AI manages vast diverse data inputs and how focusing on re-ranking can massively improve LLM workflows and output quality.
Indexify Unveiled - Diptanu Gon Choudhury | Vector Space Talks
Diptanu Gon Choudhury shares insights on re-imaging Spark and data infrastructure while discussing his work on Indexify to enhance AI-driven workflows and knowledge bases.
Qdrant x Dust: How Vector Search helps make work work better - Stan Polu | Vector Space Talks
Stanislas Polu shares insights on integrating SaaS platforms into workflows, reflects on his experiences at Stripe and OpenAI, and discusses his company Dust's focus on enhancing enterprise productivity through tailored AI assistants and their recent switch to Qdrant for database management.
Introducing Qdrant Cloud on Microsoft Azure
Learn the benefits of Qdrant Cloud on Azure.
Qdrant Updated Benchmarks 2024
We've compared how Qdrant performs against the other vector search engines to give you a thorough performance analysis
Navigating challenges and innovations in search technologies
Podcast on search and LLM with Datatalk.club
Open Source Vector Search Engine and Vector Database - Andrey Vasnetsov
Andrey Vasnetsov, CTO and Co-founder of Qdrant, presents an in-depth look into the intricacies of their open-source vector search engine and database, detailing its optimized architecture, data structure challenges, and innovative filtering techniques for efficient vector similarity searches.
Vector Search Complexities: Insights from Projects in Image Search and RAG - Noé Achache | Vector Space Talks
Noé Achache shares insights on vector search complexities, discussing projects on image matching, document retrieval, and handling sensitive medical data with practical solutions and industry challenges.
Superpower your Semantic Search using Vector Database - Nicolas Mauti | Vector Space Talks
Nicolas Mauti discusses the improvements to Malt's semantic search capabilities to enhance freelancer and project matching, highlighting the transition to retriever-ranker architecture, implementation of a multilingual encoder model, and the deployment of Qdrant to significantly reduce latency.
Building LLM Powered Applications in Production - Hamza Farooq | Vector Space Talks
Hamza Farooq presents the future of large language models, complex search, and copilot, discussing real-world applications and the challenges of implementing these technologies in production.
Building a High-Performance Entity Matching Solution with Qdrant - Rishabh Bhardwaj | Vector Space Talks
Rishabh Bhardwaj, a Data Engineer at HRS Group, discusses building a high-performance hotel matching solution with Qdrant, addressing data inconsistency, duplication, and real-time processing challenges.
FastEmbed: Fast & Lightweight Embedding Generation - Nirant Kasliwal | Vector Space Talks
Nirant Kasliwal discusses the efficiency and optimization techniques of FastEmbed, a Python library designed for speedy, lightweight embedding generation in machine learning applications.
When music just doesn't match our vibe, can AI help? - Filip Makraduli | Vector Space Talks
Filip Makraduli discusses using human language and AI to capture music vibes, encoding text with sentence transformers, generating recommendations through vector spaces, integrating Streamlit and Spotify API, and future improvements for AI-powered music recommendations.
Binary Quantization - Andrey Vasnetsov | Vector Space Talks
Andrey Vasnetsov, CTO of Qdrant, discusses the concept of binary quantization and its benefits in vector indexing, including the challenges and potential future developments of this technique.
Loading Unstructured.io Data into Qdrant from the Terminal
Learn how to simplify the process of loading unstructured data into Qdrant using the Qdrant Unstructured destination.
Chat with a codebase using Qdrant and N8N
Building a RAG-based chatbot using Qdrant and N8N to chat with a codebase on GitHub
"Vector search and applications" by Andrey Vasnetsov, CTO at Qdrant
Andrey Vasnetsov, Co-founder and CTO at Qdrant has shared about vector search and applications with Learn NLP Academy.
From Content Quality to Compression: The Evolution of Embedding Models at Cohere with Nils Reimers
Nils Reimers head of machine learning at Cohere comes on the recent vector space talks to share details about their latest embedding V3 model.
Powering Bloop semantic code search
Bloop is a fast code-search engine that combines semantic search, regex search and precise code navigation
Pienso & Qdrant: Future Proofing Generative AI for Enterprise-Level Customers
Why Pienso chose Qdrant as a cornerstone for building domain-specific foundation models.
Full-text filter and index are already available!
Qdrant v0.10 introduced full-text filters and indexes to enable more search capabilities for those working with textual data.
Storing multiple vectors per object in Qdrant
Discover how Qdrant continues to push the boundaries of data indexing, providing insights into the practical applications and benefits of this novel vector storage strategy.
Batch vector search with Qdrant
Discover the latest feature designed to streamline and optimize large-scale searches.
Qdrant supports ARM architecture!
Qdrant's support for ARM architecture marks a pivotal step in enhancing accessibility and performance. This development optimizes data indexing and retrieval.
Qdrant has joined NVIDIA Inception Program
Along with the various opportunities it gives, we are the most excited about GPU support since it is an essential feature in Qdrant's roadmap. Stay tuned for our new updates.
Qdrant and Jina integration: storage backend support for DocArray
We are happy to announce that Jina.AI integrates Qdrant engine as a storage backend to their DocArray solution.
Vultr and Qdrant Hybrid Cloud Support Next-Gen AI Projects
Providing a flexible platform for high-performance vector search in next-gen AI workloads.
STACKIT and Qdrant Hybrid Cloud for Best Data Privacy
Empowering German AI development with a data privacy-first platform.
Qdrant Hybrid Cloud and Scaleway Empower GenAI
Supporting innovation in AI with the launch of a revolutionary managed database for startups and enterprises.
Red Hat OpenShift and Qdrant Hybrid Cloud Offer Seamless and Scalable AI
Qdrant brings managed vector databases to Red Hat OpenShift for large-scale GenAI.
Qdrant and OVHcloud Bring Vector Search to All Enterprises
Collaborating to support startups and enterprises in Europe with a strong focus on data control and privacy.
New RAG Horizons with Qdrant Hybrid Cloud and LlamaIndex
Unlock the most advanced RAG opportunities with Qdrant Hybrid Cloud and LlamaIndex.
Developing Advanced RAG Systems with Qdrant Hybrid Cloud and LangChain
Empowering engineers and scientists globally to easily and securely develop and scale their GenAI applications.
Cutting-Edge GenAI with Jina AI and Qdrant Hybrid Cloud
Build your most successful app with Jina AI embeddings and on Qdrant Hybrid Cloud.
Qdrant Hybrid Cloud and Haystack for Enterprise RAG
A winning combination for enterprise-scale RAG consists of a strong framework and a scalable database.
Qdrant Hybrid Cloud and DigitalOcean for Scalable and Secure AI Solutions
Enabling developers to deploy a managed vector database in their DigitalOcean Environment.
Enhance AI Data Sovereignty with Aleph Alpha and Qdrant Hybrid Cloud
Empowering the world’s best companies in their AI journey.
Elevate Your Data With Airbyte and Qdrant Hybrid Cloud
Leverage Airbyte and Qdrant Hybrid Cloud for best-in-class data performance.