# Qdrant Blog on Qdrant - Vector Search Engine

Recent content in Qdrant Blog on Qdrant - Vector Search Engine

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Does a Code-Tuned Embedding Model Pay Off? papr-embed-code-1 in Qdrant

DevFeed: [Does a Code-Tuned Embedding Model Pay Off? papr-embed-code-1 in Qdrant](<https://devfeed.tech/articles/does-a-code-tuned-embedding-model-pay-off-papr-embed-code-1-in-qdrant-140947.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/papr-embed-code/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-11-18T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [code search](<https://devfeed.tech/topics/code-search.md>), [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [bert](<https://devfeed.tech/tags/bert.md>), [card](<https://devfeed.tech/tags/card.md>), [code](<https://devfeed.tech/tags/code.md>), [code-search](<https://devfeed.tech/tags/code-search.md>), [data](<https://devfeed.tech/tags/data.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embedding-model](<https://devfeed.tech/tags/embedding-model.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [general](<https://devfeed.tech/tags/general.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [leaderboards](<https://devfeed.tech/tags/leaderboards.md>), [matching](<https://devfeed.tech/tags/matching.md>), [model](<https://devfeed.tech/tags/model.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [open](<https://devfeed.tech/tags/open.md>), [open-weights](<https://devfeed.tech/tags/open-weights.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [qwen3](<https://devfeed.tech/tags/qwen3.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [saas](<https://devfeed.tech/tags/saas.md>), [search](<https://devfeed.tech/tags/search.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [test-case](<https://devfeed.tech/tags/test-case.md>), [top](<https://devfeed.tech/tags/top.md>), [training](<https://devfeed.tech/tags/training.md>), [training-data](<https://devfeed.tech/tags/training-data.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

On code retrieval Papr's papr-embed-code-1 improves over its Qwen3-Embedding base on code it did not train on: average nDCG@10 gains are 0.034 for the 4B model and 0.026 for the 0.6B. Both score slightly below the base on prose. In tests across seven code tasks, 1-bit TurboQuant retained 99.7% of the 4B's float32 score without rescoring and all of it with 2x oversampling; the compressed 4B outscored the 0.6B in float32 using 12x less RAM, though it embeds about four times slower. On roughly one million CodeSearchNet snippets, rescored 1-bit search retained 99.5% of exact-search score at 1.0 ms per query versus 1.8 ms for float32 at hnsw_ef 128. Raising hnsw_ef to 256 improved every setup; language filtering also helped. BM25 alone lagged dense search, and fusion generally hurt, with only negligible gains at low weight. The authors recommend the base model for prose-heavy collections and suggest testing compressed 4B vectors, rescoring, and higher hnsw_ef for code search.

### Source excerpt

If you search code, you've probably asked this: is a code-specific embedding model worth it, or is a strong general one good enough? Papr's papr-embed-code-1 is a good test case. It's Qwen3-Embedding trained further on code retrieval, with open weights in two sizes: 0.6B and 4B. Papr reports top scores on CoIR, a code retrieval benchmark. But it trained on most of CoIR's training data, and its model card says so. Papr also reports the 4B at #1 on MTEB's two held-out code leaderboards, RTEB (Code) and CodeRAG.

## How to Run an Embedding Model on Bare Metal

DevFeed: [How to Run an Embedding Model on Bare Metal](<https://devfeed.tech/articles/how-to-run-an-embedding-model-on-bare-metal-135929.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/embeddings-on-bare-metal/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-11-11T01:00:00Z

Content type: tutorial

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Local AI](<https://devfeed.tech/topics/local-ai.md>), [rust-ai](<https://devfeed.tech/topics/rust-ai.md>), [tokenization](<https://devfeed.tech/topics/tokenization.md>), [quantization](<https://devfeed.tech/topics/quantization.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bare-metal](<https://devfeed.tech/tags/bare-metal.md>), [bert](<https://devfeed.tech/tags/bert.md>), [bits](<https://devfeed.tech/tags/bits.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [edge](<https://devfeed.tech/tags/edge.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embedding-model](<https://devfeed.tech/tags/embedding-model.md>), [embeddinggemma](<https://devfeed.tech/tags/embeddinggemma.md>), [embeddinggemma-2](<https://devfeed.tech/tags/embeddinggemma-2.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [inference](<https://devfeed.tech/tags/inference.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [matching](<https://devfeed.tech/tags/matching.md>), [memory](<https://devfeed.tech/tags/memory.md>), [model](<https://devfeed.tech/tags/model.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [qwen3](<https://devfeed.tech/tags/qwen3.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [saas](<https://devfeed.tech/tags/saas.md>), [search](<https://devfeed.tech/tags/search.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [size](<https://devfeed.tech/tags/size.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

A static embedding model can run on an ESP32-S3 without an operating system: the article reports fitting `potion-base-2M` on a board with 16MB flash and 8MB PSRAM using `no_std` Rust. Its weights and tokenizer vocabulary are baked into firmware at build time. Runtime inference tokenizes with a custom WordPiece implementation, looks up token vectors, mean-pools them, and optionally L2-normalizes; it avoids transformer matrix multiplication and dependencies such as PyTorch and Hugging Face `tokenizers`. Because `no_std` lacks filesystem access and `HashMap`, the build script extracts tensor metadata and encodes the sorted vocabulary for binary-search lookup. A heap allocator from `esp-alloc` supports `Vec`. The reported throughput is about 1.2 ms for 10-12 tokens, slower than the article's MacBook comparison, but demonstrated on a chip with far less memory. The approach is specific to small static embedding models.

### Source excerpt

Running vector search on the edge is something we've been working towards here at Qdrant. The main problem is that vector search is resource-hungry, starting with the embedding step: EmbeddingGemma-2, a small modern model, takes up 310MB of memory when quantized to 8 bits, while Qwen3 Embedding 4B, a larger one, needs 4.28GB. Size is just one side of the coin: transformer-based inference involves expensive computations and often relies on heavy dependencies like PyTorch (or libtorch).

## Faster and Cheaper Search With Qdrant 1.20

DevFeed: [Faster and Cheaper Search With Qdrant 1.20](<https://devfeed.tech/articles/faster-and-cheaper-search-with-qdrant-1-20-113340.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/qdrant-1.20-performance/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-11-02T01:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [cosine similarity search](<https://devfeed.tech/topics/cosine-similarity-search.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [advanced](<https://devfeed.tech/tags/advanced.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [array](<https://devfeed.tech/tags/array.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [bert](<https://devfeed.tech/tags/bert.md>), [bits](<https://devfeed.tech/tags/bits.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [faster](<https://devfeed.tech/tags/faster.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [indexing](<https://devfeed.tech/tags/indexing.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [matching](<https://devfeed.tech/tags/matching.md>), [metadata](<https://devfeed.tech/tags/metadata.md>), [native](<https://devfeed.tech/tags/native.md>), [nested](<https://devfeed.tech/tags/nested.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [performance](<https://devfeed.tech/tags/performance.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [quantization](<https://devfeed.tech/tags/quantization.md>), [recall](<https://devfeed.tech/tags/recall.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [saas](<https://devfeed.tech/tags/saas.md>), [search](<https://devfeed.tech/tags/search.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [semantic-search](<https://devfeed.tech/tags/semantic-search.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

Qdrant 1.20 adds `turbo8` and `turbo16` vector datatypes plus per-element indexes for nested metadata. TurboQuant stores vectors at 8 or 16 bits per dimension, using one-quarter or one-half the space of `float32`. Queries remain `float32` and are only rotated for asymmetric scoring; the article reports server-side latency within 10% of `float32` and near-`float32` recall without rescoring or disk reads. In tests across 14 embedding datasets, `turbo4` saved more space but lost a few recall points on some datasets. For nested filters, indexing each array element separately avoids reading candidate payloads: on one million arXiv papers, this served up to four times the queries per second of regular nested indexes with the same correct results. Flat filters were close in speed but missed 20-33% of the right papers because conditions could match different array elements. Set the datatype when creating a collection; for nested indexes, set `nested` to the array key on each filtered field.

### Source excerpt

With Qdrant 1.20, we shipped two main features that can make your search cheaper and faster: two new quantization-native datatypes (turbo8 and turbo16) and advanced metadata indexing for nested fields. We measured the performance and cost improvements so you don't have to, and in this blog post we go through our findings. Reduce Your Disk Usage, Not Your Recall Storing vectors is always the main expense when it comes to semantic search: they cost disk when cold, and memory when warm.

## Scalable PDF Retrieval with Cohere Embed 5 and Qdrant Asymmetric Quantization

DevFeed: [Scalable PDF Retrieval with Cohere Embed 5 and Qdrant Asymmetric Quantization](<https://devfeed.tech/articles/scalable-pdf-retrieval-with-cohere-embed-5-and-qdrant-asymmetric-quantization-97697.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/cohere-embed-5-qdrant/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-10-23T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Cohere API for embeddings](<https://devfeed.tech/topics/cohere-api-for-embeddings.md>), [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [search-engines](<https://devfeed.tech/topics/search-engines.md>), [cohere](<https://devfeed.tech/topics/cohere.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [cohere](<https://devfeed.tech/tags/cohere.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [family](<https://devfeed.tech/tags/family.md>), [fast](<https://devfeed.tech/tags/fast.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [images](<https://devfeed.tech/tags/images.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [languages](<https://devfeed.tech/tags/languages.md>), [lighter](<https://devfeed.tech/tags/lighter.md>), [matching](<https://devfeed.tech/tags/matching.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [pdf](<https://devfeed.tech/tags/pdf.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [quality](<https://devfeed.tech/tags/quality.md>), [quantization](<https://devfeed.tech/tags/quantization.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [saas](<https://devfeed.tech/tags/saas.md>), [share](<https://devfeed.tech/tags/share.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [space](<https://devfeed.tech/tags/space.md>), [support](<https://devfeed.tech/tags/support.md>), [text](<https://devfeed.tech/tags/text.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [v5](<https://devfeed.tech/tags/v5.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [with](<https://devfeed.tech/tags/with.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

On five public English ViDoRe V3 corpora, Embed 5 Pro's single dense vector for each PDF page image scored above several tested late-interaction models, according to the article's standard nDCG comparison. The authors' Qdrant recipe uses 512-dimensional, 1-bit page vectors and 8-bit query encoding to retrieve 20 candidates, then re-scores them with full vectors. It retained 99.2% of full-vector ranking quality while using 64 bytes per page for search vectors in RAM; full vectors remain on disk and candidate reads add latency and may populate the OS page cache. These figures exclude indexes and payloads, and the authors note possible training-data overlap. If OCR already works in a pipeline, Cohere Rerank 5 can rerank OCR text (it does not take images); on the same corpora, reranking the top 20 improved mean nDCG@10 from 66.8 to 73.2 with full-vector text search and from 66.2 to 71.7 with the compressed recipe.

### Source excerpt

Cohere released Embed 5, a family of embedding models. The family has a quality-focused model, Embed 5 Pro (embed-v5.0-pro), and a lighter one, Embed 5 Fast (embed-v5.0-fast). Both accept text and images, support 100+ languages, and share an embedding space.

## Qdrant 1.20 - Full-Text Search Improvements

DevFeed: [Qdrant 1.20 - Full-Text Search Improvements](<https://devfeed.tech/articles/qdrant-1-20-full-text-search-improvements-95827.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/qdrant-1.20.x/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-10-22T01:00:00Z

Content type: release

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [search-engines](<https://devfeed.tech/topics/search-engines.md>), [code search](<https://devfeed.tech/topics/code-search.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [bm25](<https://devfeed.tech/tags/bm25.md>), [code](<https://devfeed.tech/tags/code.md>), [code-search](<https://devfeed.tech/tags/code-search.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [faster](<https://devfeed.tech/tags/faster.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [full-text-search](<https://devfeed.tech/tags/full-text-search.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [matching](<https://devfeed.tech/tags/matching.md>), [nested](<https://devfeed.tech/tags/nested.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [payload](<https://devfeed.tech/tags/payload.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [quantization](<https://devfeed.tech/tags/quantization.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [saas](<https://devfeed.tech/tags/saas.md>), [search](<https://devfeed.tech/tags/search.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [storage](<https://devfeed.tech/tags/storage.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [version](<https://devfeed.tech/tags/version.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

Qdrant 1.20 adds BM25 ranking directly on full-text indexes, deriving scoring statistics from payload text and allowing query-level tuning without generating embeddings; the new `code` tokenizer splits identifiers on underscores and case changes while retaining full identifiers. Per-element payload indexes can answer nested filters without payload reads when all conditions use indexed fields on the same array; a benchmark on 100,000 points found them 7-38 times faster than regular indexes with payload reads. New `turbo16` and `turbo8` datatypes reduce vector storage: reported tests found `turbo16` matched `float32` recall@10 within 0.001, while `turbo8` approached `float16` recall at half its size. The release also adds `bits8` quantization, memory-tier controls for the ID tracker, and internal cluster authentication by default when API keys are configured. Upgrades require attention to read-only-key clusters and memory tiers for inline storage, whose vectors now follow the HNSW index tier.

### Source excerpt

Qdrant 1.20.0 is out! Let's look at the main features for this version: BM25 on Full-Text Indexes and Code Search: Rank by BM25 straight from your payload text, with no embeddings to generate. Plus, better code search with a new code tokenizer. Faster Nested Filters: A new per-element payload index answers nested filters without reading payloads, making them faster. 16-Bit and 8-Bit TurboQuant: A 16-bit TurboQuant datatype that halves vector storage without accuracy loss, and an 8-bit TurboQuant datatype and quantization option with recall close to float16.

## UltraBERT Embeddings: Whole Documents Versus Chunks for Retrieval

DevFeed: [UltraBERT Embeddings: Whole Documents Versus Chunks for Retrieval](<https://devfeed.tech/articles/ultrabert-fits-32k-tokens-in-one-vector-rip-chunking-90009.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/ultrabert-embed/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-10-19T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Vectors & LLMs](<https://devfeed.tech/topics/vectors-llms.md>), [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [vector embeddings in AI](<https://devfeed.tech/topics/vector-embeddings-in-ai.md>), [tokenization](<https://devfeed.tech/topics/tokenization.md>), [elasticsearch](<https://devfeed.tech/topics/elasticsearch.md>)

Tags: [1-5](<https://devfeed.tech/tags/1-5.md>), [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [bert](<https://devfeed.tech/tags/bert.md>), [compression](<https://devfeed.tech/tags/compression.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [latency](<https://devfeed.tech/tags/latency.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [quantization](<https://devfeed.tech/tags/quantization.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [saas](<https://devfeed.tech/tags/saas.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

Tests of UltraBERT-Embed-150M in Qdrant found that 512-token chunks generally retrieved document details better than whole-document vectors, though whole-document vectors performed better for queries about an entire episode and for finding passkeys. Combining both representations helped only slightly on two tasks and performed worse on others. The article also reports that 1-bit TurboQuant compression reduced chunk-vector storage for 200,000 articles to about 140 MB, with quality and rescoring latency tradeoffs.

### Source excerpt

Every retrieval pipeline starts with the same call: how big is a chunk? Too small, and a chunk loses its context. Too big, and the embedding model cuts it off. DMIS Lab's UltraBERT-Embed-150M moves that cutoff to 32K tokens. It's a 151M-parameter dense embedding model built on UltraBERT, an English encoder trained for 32K-token inputs. Most documents fit in one pass, and you get back one 768-dimension vector. So is chunking dead? We tested it in Qdrant: one vector per document against 512-token chunks, the two together, and both compressed.

## How Poliscope Made All of Germany's Local Politics Searchable on One Server with Qdrant

DevFeed: [How Poliscope Made All of Germany's Local Politics Searchable on One Server with Qdrant](<https://devfeed.tech/articles/how-poliscope-made-all-of-germany-s-local-politics-searchable-on-one-server-with-qdrant-90008.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/case-study-poliscope/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-10-15T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [self-hosted databases vs managed services](<https://devfeed.tech/topics/self-hosted-databases-vs-managed-services.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [cross-encoder](<https://devfeed.tech/tags/cross-encoder.md>), [data-sovereignty](<https://devfeed.tech/tags/data-sovereignty.md>), [database](<https://devfeed.tech/tags/database.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [saas](<https://devfeed.tech/tags/saas.md>), [server](<https://devfeed.tech/tags/server.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

Poliscope consolidated German municipal records from thousands of council portals into a searchable corpus using Qdrant. The case study describes its hybrid retrieval design, regional filtering, vector compression, and self-hosted single-server setup, along with reported search performance and plans for future growth.

### Source excerpt

Poliscope makes Germany's local political data searchable in one place. Germany has about 11,000 municipalities, and almost every one of them publishes through a council information system (in German, a Ratsinformationssystem). That is where agendas, minutes, proposals, and planning documents get published. Many portals serve several municipalities at once, so Poliscope's roughly 4,800 active portals cover about 90% of German municipalities and 98% of the population. They run on roughly a dozen software products, each with its own quirks, and none of them talk to each other.

## Reachy Remembers: Giving a Robot a Local Semantic Memory with Qdrant Edge

DevFeed: [Reachy Remembers: Giving a Robot a Local Semantic Memory with Qdrant Edge](<https://devfeed.tech/articles/reachy-remembers-giving-a-robot-a-local-semantic-memory-with-qdrant-edge-86673.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/reachy-robot-memory-qdrant-edge/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-10-14T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [DuckDB](<https://devfeed.tech/topics/duckdb.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [language](<https://devfeed.tech/tags/language.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [pi](<https://devfeed.tech/tags/pi.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [raspberry](<https://devfeed.tech/tags/raspberry.md>), [raspberry-pi](<https://devfeed.tech/tags/raspberry-pi.md>), [reachy](<https://devfeed.tech/tags/reachy.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [run](<https://devfeed.tech/tags/run.md>), [saas](<https://devfeed.tech/tags/saas.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [source](<https://devfeed.tech/tags/source.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

The article describes adding local semantic memory to Reachy Mini with Qdrant Edge. It explains how retrieval combines image and text vectors, uses score gates and an empty-frame baseline to avoid irrelevant matches, and stores memories on the robot. In the demo, model inference runs on a nearby laptop because the robot lacks enough free RAM, while memory search remains on-device.

### Source excerpt

Reachy Mini is an open-source robot from Pollen Robotics and Hugging Face, run by a Raspberry Pi with 4 GB of RAM. We wanted it to do what a good host does: greet you by name the second time you walk in, remember what you talked about, and tell you what it saw while you were gone. A robot that talks through a language model can't do any of that on its own. The model only knows what's in its context: restart the robot and it knows nobody, talk long enough and the start of the conversation falls out, and nothing in it can be searched.

## Compressing Perplexity's Visual PDF Embeddings with TurboQuant

DevFeed: [Compressing Perplexity's Visual PDF Embeddings with TurboQuant](<https://devfeed.tech/articles/perplexity-s-new-visual-retriever-has-a-size-problem-we-fixed-it-85900.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/pplx-embed-v2/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-10-13T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [document ai](<https://devfeed.tech/topics/document-ai.md>), [Compression](<https://devfeed.tech/topics/compression.md>), [Data visualization](<https://devfeed.tech/topics/data-visualization.md>), [self-hosted runner](<https://devfeed.tech/topics/self-hosted-runner.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [bert](<https://devfeed.tech/tags/bert.md>), [document-retrieval](<https://devfeed.tech/tags/document-retrieval.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [ocr](<https://devfeed.tech/tags/ocr.md>), [pdfs](<https://devfeed.tech/tags/pdfs.md>), [perplexity](<https://devfeed.tech/tags/perplexity.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [report](<https://devfeed.tech/tags/report.md>), [saas](<https://devfeed.tech/tags/saas.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

Qdrant evaluates TurboQuant compression for Perplexity's pplx-embed-v2-late models, which search PDF pages as images. At 1 bit per vector, TurboQuant reduces vector storage by 21 times while retaining 96.5% of float32 retrieval quality; rescoring raises retained quality to 99.9%. The article compares image based retrieval with OCR and Markdown approaches, and reports tests across four ViDoRe v3 datasets. It recommends testing page image retrieval when PDF layout matters, while retaining OCR where applications need extracted text or structured fields.

### Source excerpt

A number in a financial report needs its row, column, and unit to mean anything. A chart needs its labels. When you build search over PDFs, that context is part of what you want to retrieve. Perplexity released pplx-embed-v2-late, two late interaction models that search document pages as images. The model embeds the page image, including its tables, charts, and layout. You can skip the optical character recognition (OCR) step and search the page as it appears.

## Jevjitsu: Or, How We Tried Generalized Classifiers on Everything

DevFeed: [Jevjitsu: Or, How We Tried Generalized Classifiers on Everything](<https://devfeed.tech/articles/jevjitsu-or-how-we-tried-generalized-classifiers-on-everything-67011.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/jevjitsu/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-10-08T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [tgi](<https://devfeed.tech/topics/tgi.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [bert](<https://devfeed.tech/tags/bert.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classifiers](<https://devfeed.tech/tags/classifiers.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [llm](<https://devfeed.tech/tags/llm.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [matching](<https://devfeed.tech/tags/matching.md>), [ml](<https://devfeed.tech/tags/ml.md>), [model](<https://devfeed.tech/tags/model.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [openrouter](<https://devfeed.tech/tags/openrouter.md>), [prompting](<https://devfeed.tech/tags/prompting.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [saas](<https://devfeed.tech/tags/saas.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [training](<https://devfeed.tech/tags/training.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [transformers](<https://devfeed.tech/tags/transformers.md>), [type-safety](<https://devfeed.tech/tags/type-safety.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

The article reports experiments using Jev, a decision model for classification, in search reranking, product result diversity, query understanding, and semantic chunking. It describes improved ranking and chunking metrics in the tested datasets, while noting trade-offs such as latency, API cost, and the risks of filtering ambiguous queries.

### Source excerpt

Classification is one of the oldest problems in machine learning. Unlike modern decoding transformers, most classification models were non-autoregressive by nature. Before Jev, the common approaches were training your own classifier, which needs labels, using a zero-shot classifier (compared in this Hugging Face benchmark), or prompting an LLM with some hacky type safety on top. There were also meta-ML methods, but none of them reached the mainstream. With the introduction of Jev, a decision model from TypeSafe served through OpenRouter, the taxonomy of classifiers has changed yet again:

## How Small Can Google's New EmbeddingGemma 2 Get?

DevFeed: [How Small Can Google's New EmbeddingGemma 2 Get?](<https://devfeed.tech/articles/how-small-can-google-s-new-embeddinggemma-2-get-65428.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/embeddinggemma-2/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-10-06T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [gemma](<https://devfeed.tech/topics/gemma.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [gemma](<https://devfeed.tech/tags/gemma.md>), [gemma-4](<https://devfeed.tech/tags/gemma-4.md>), [google-deepmind](<https://devfeed.tech/tags/google-deepmind.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [latency](<https://devfeed.tech/tags/latency.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [quantization](<https://devfeed.tech/tags/quantization.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [saas](<https://devfeed.tech/tags/saas.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

Qdrant's tests of Google's EmbeddingGemma 2 compare vector quantization and reduced dimensions for text retrieval. Full-size 1-bit TurboQuant vectors retained 99% of baseline retrieval quality with 30 times less vector RAM; 256-dimensional vectors with rescoring used 77 times less RAM and retained 94.5%. The article recommends testing relevance and latency on an application's own queries.

### Source excerpt

Google's new EmbeddingGemma 2 can run on a phone. The model travels light. The vectors need their own suitcase. At 10 million documents, full-size float32 vectors alone take 30.7 GB of RAM. We got early access ahead of today's Google DeepMind release and tested how much of that memory we could save in Qdrant. Quantized full-size vectors kept 99% of their retrieval quality with 30x less vector RAM. Shorter vectors with rescoring reached 77x less vector RAM and retained 94.5%.

## Constella Preview: Swap Query Models Without Re-Embedding

DevFeed: [Constella Preview: Swap Query Models Without Re-Embedding](<https://devfeed.tech/articles/constella-preview-swap-query-models-without-re-embedding-61414.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/constella-research-preview/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-09-29T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [sentence-transformers](<https://devfeed.tech/topics/sentence-transformers.md>), [cosine similarity search](<https://devfeed.tech/topics/cosine-similarity-search.md>), [hugging face](<https://devfeed.tech/topics/hugging-face.md>), [lora](<https://devfeed.tech/topics/lora.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [cost](<https://devfeed.tech/tags/cost.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [features](<https://devfeed.tech/tags/features.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [low-power](<https://devfeed.tech/tags/low-power.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [saas](<https://devfeed.tech/tags/saas.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

Constella is a family of query embedding models built around Stella, a 400M-parameter English embedding model. Stella encodes documents, while Zero, Nano, or Stella can encode queries against the same Qdrant collection, allowing query models to be switched without re-embedding stored documents. The research preview evaluates the models across 15 BEIR datasets.

### Source excerpt

As query traffic grows, so does the compute bill for embedding it. On a low-power device, a large model may not fit in memory. A smaller query model could reduce that cost, but switching usually means re-embedding the collection. Constella lets you make that switch. It's a family of models on Hugging Face built around Stella, a 400M-parameter English embedding model. Stella encodes your documents. Zero, Nano, or Stella itself can then encode your queries, all searching the same Qdrant collection.

## Oxidizing Cross-Encoders

DevFeed: [Oxidizing Cross-Encoders](<https://devfeed.tech/articles/oxidizing-cross-encoders-62450.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/oxidizing-cross-encoders/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-09-25T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Python](<https://devfeed.tech/topics/python.md>), [onnx runtime](<https://devfeed.tech/topics/onnx-runtime.md>), [tokenizers](<https://devfeed.tech/topics/tokenizers.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [Transformers](<https://devfeed.tech/topics/transformers.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [onnx](<https://devfeed.tech/tags/onnx.md>), [onnx-runtime](<https://devfeed.tech/tags/onnx-runtime.md>), [python](<https://devfeed.tech/tags/python.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [rust](<https://devfeed.tech/tags/rust.md>), [saas](<https://devfeed.tech/tags/saas.md>), [sentence-transformers](<https://devfeed.tech/tags/sentence-transformers.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

The article describes rewriting cross-encoder inference in Rust as the cross-encode-rs library and comparing it with Python implementations that use the same ONNX Runtime C++ engine. The Rust version was 1.1x faster at the median on a small reranking model and about 1.4x faster on a larger one, while model load time did not improve.

### Source excerpt

We rewrote cross-encoder inference in Rust, benchmarked it against Python, and on a small reranking model it came out only 1.1x faster at the median. That is not a sign of a slow Rust implementation. The Python libraries we compared against, fastembed and sentence-transformers, hand the same work to the same C++ engine, onnxruntime, so all three spend almost all of their time in the same compiled code. In the Rust community, rewriting code in Rust is called "oxidizing" it, since rust is also what iron turns into when it oxidizes. This post covers how we oxidized cross-encoder inference into a library, cross-encode-rs, how it works, where it does pull ahead (about 1.4x on a larger model), and where it does not (model load time).

## How Lucy Built a Source-of-Truth Retrieval Layer for 2.8M+ SEC and DART Filings with Qdrant

DevFeed: [How Lucy Built a Source-of-Truth Retrieval Layer for 2.8M+ SEC and DART Filings with Qdrant](<https://devfeed.tech/articles/how-lucy-built-a-source-of-truth-retrieval-layer-for-2-8m-sec-and-dart-filings-with-qdrant-62911.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/case-study-lucy/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-09-21T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [managing large-scale text data in AI](<https://devfeed.tech/topics/managing-large-scale-text-data-in-ai.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [data](<https://devfeed.tech/tags/data.md>), [data-infrastructure](<https://devfeed.tech/tags/data-infrastructure.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [latency](<https://devfeed.tech/tags/latency.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [provenance](<https://devfeed.tech/tags/provenance.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [regulatory](<https://devfeed.tech/tags/regulatory.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [saas](<https://devfeed.tech/tags/saas.md>), [securities-and-exchange-commission](<https://devfeed.tech/tags/securities-and-exchange-commission.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [source-of-truth](<https://devfeed.tech/tags/source-of-truth.md>), [structured](<https://devfeed.tech/tags/structured.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

Lucy builds a retrieval layer for more than 2.8 million SEC and DART filings, preparing them as structured data that AI systems can search. The article describes preserving table structure, standardized XBRL facts, and links back to source documents, while narrowing retrieval to rank the right chunk first. It also identifies cost and latency as concerns with frontier models.

### Source excerpt

Lucy builds data infrastructure for financial AI. The company turns large-scale regulatory filings from the U.S. Securities and Exchange Commission (SEC) EDGAR system and Korea's DART disclosure system into structured data that AI systems can search, retrieve, and reason over.

## How Himalayas Built Semantic Job Matching for 100,000+ Remote Listings with Qdrant

DevFeed: [How Himalayas Built Semantic Job Matching for 100,000+ Remote Listings with Qdrant](<https://devfeed.tech/articles/how-himalayas-built-semantic-job-matching-for-100-000-remote-listings-with-qdrant-65427.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/case-study-himalayas/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-09-18T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>), [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [voyage-ai](<https://devfeed.tech/topics/voyage-ai.md>)

Tags: [ai-job-search](<https://devfeed.tech/tags/ai-job-search.md>), [algolia](<https://devfeed.tech/tags/algolia.md>), [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [elasticsearch](<https://devfeed.tech/tags/elasticsearch.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [hybrid-search](<https://devfeed.tech/tags/hybrid-search.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [job](<https://devfeed.tech/tags/job.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [remote](<https://devfeed.tech/tags/remote.md>), [saas](<https://devfeed.tech/tags/saas.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

Himalayas uses Qdrant Cloud to power hybrid semantic and keyword search, structured filters, personalized job matches, and related-job recommendations across its remote job platform. The article describes the move from Algolia and Elasticsearch, a production retrieval system handling more than 25 million monthly requests, and offline search-quality improvements of about 19 percentage points in recall and roughly four times fewer irrelevant results.

### Source excerpt

Himalayas is a remote job board and AI job search platform. It brings together more than 100,000 live remote job listings and over 300,000 public talent profiles, and it works both sides of the market. Job seekers explore roles by skills, salary, location, and time zone, research remote companies, and receive personalized job matches. Employers advertise remote roles and discover candidates. Around that core, Himalayas offers tools to tailor resumes and cover letters, practice interviews, and track applications.

## SHIFTing Languages in Multilingual RAG

DevFeed: [SHIFTing Languages in Multilingual RAG](<https://devfeed.tech/articles/shifting-languages-in-multilingual-rag-46737.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/shift-multilingual-rag/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-09-16T07:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [qwen](<https://devfeed.tech/topics/qwen.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [information-retrieval](<https://devfeed.tech/tags/information-retrieval.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [qwen](<https://devfeed.tech/tags/qwen.md>), [qwen3](<https://devfeed.tech/tags/qwen3.md>), [rag](<https://devfeed.tech/tags/rag.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [saas](<https://devfeed.tech/tags/saas.md>), [search](<https://devfeed.tech/tags/search.md>), [semantic-search](<https://devfeed.tech/tags/semantic-search.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

This article examines language bias in multilingual retrieval-augmented generation systems. It explains how multilingual embedding models can favor documents written in the query language, making relevant answers in other languages harder to retrieve, and discusses translation, per-language search, and larger embedding models as possible responses.

### Source excerpt

If you speak more than one language, you know the feeling when the mental switch in your head starts up with the rattling sound of a struggling engine, mixing every word you have to produce into some Denglish, Frenglish, or Spanglish. Work-related thoughts come back from your inner search engine of a brain in English, life wisdom - in the mother tongue, and the mix is unpredictable, a little weird, but it works.

## Qdrant Releases Large-Scale, Reproducible Datasets and Tooling for Vector Search Benchmarking

DevFeed: [Qdrant Releases Large-Scale, Reproducible Datasets and Tooling for Vector Search Benchmarking](<https://devfeed.tech/articles/enough-with-the-bad-benchmarks-tools-for-production-grade-research-46716.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/qdrant-fineweb-10b-release/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-09-01T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [dataset](<https://devfeed.tech/topics/dataset.md>), [Ground truth / benchmark quality](<https://devfeed.tech/topics/ground-truth-benchmark-quality.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Developer Tools](<https://devfeed.tech/topics/developer-tools.md>), [reproducibility](<https://devfeed.tech/topics/reproducibility.md>), [GPU](<https://devfeed.tech/topics/gpu.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [bert](<https://devfeed.tech/tags/bert.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [production](<https://devfeed.tech/tags/production.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [reproducibility](<https://devfeed.tech/tags/reproducibility.md>), [research](<https://devfeed.tech/tags/research.md>), [saas](<https://devfeed.tech/tags/saas.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [tooling](<https://devfeed.tech/tags/tooling.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

Qdrant describes Qdrant-FineWeb-10B, a large vector-search benchmarking dataset with exact top-1000 ground truth for 120,000 queries across a 10-billion-document corpus. The article also announces additional dense, sparse, and multimodal datasets and open-sources Supernova, a distributed framework for large-scale dataset generation and ground-truth computation.

### Source excerpt

Real world vector search workloads are increasingly large and complex. Enterprises are not using vector search to occasionally search through a couple of PDF files. They are indexing and searching billions of vectors at thousands of requests per second (RPS) and sub 50ms tail latency. Large enterprises also can't tolerate faulty assumptions. Too many benchmarks use gated, proprietary managed services. And even worse, the data is synthetic, the queries are hidden, and the engines are locked behind paywalls.

## How to Tune Vector Search Without Guessing

DevFeed: [How to Tune Vector Search Without Guessing](<https://devfeed.tech/articles/how-to-tune-vector-search-without-guessing-46743.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/tuning-retrieval-which-knob-first/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-08-24T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [AI search](<https://devfeed.tech/topics/ai-search.md>), [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [data](<https://devfeed.tech/topics/data.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [bm25](<https://devfeed.tech/tags/bm25.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [queries](<https://devfeed.tech/tags/queries.md>), [rank](<https://devfeed.tech/tags/rank.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [saas](<https://devfeed.tech/tags/saas.md>), [search](<https://devfeed.tech/tags/search.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

This article explains how to tune vector search by measuring collection settings and separating retrieval failures from ranking failures. It highlights issues involving sparse-vector weighting, BM25 configuration, candidate depth, fusion, and reranking, based on tests across five public datasets.

### Source excerpt

Your collection works. Queries return in a few milliseconds, results are mostly right, and product keeps forwarding you the ones that aren't. You open the search API reference and get exact definitions for hnsw_ef, reciprocal rank fusion k, and quantization oversampling. The definitions are correct. They still don't tell you which setting is failing on your data. So you change one setting, rerun the queries, and the score moves by 0.01. Did relevance improve, or did the same queries land differently?

## How Bayer Built an Enterprise-Scale Search Engine with Qdrant

DevFeed: [How Bayer Built an Enterprise-Scale Search Engine with Qdrant](<https://devfeed.tech/articles/how-bayer-built-an-enterprise-scale-search-engine-with-qdrant-46593.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/case-study-bayer/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-08-13T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [AI Platform](<https://devfeed.tech/topics/ai-platform.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Redis](<https://devfeed.tech/topics/redis.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-platform](<https://devfeed.tech/tags/ai-platform.md>), [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [production](<https://devfeed.tech/tags/production.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [saas](<https://devfeed.tech/tags/saas.md>), [search](<https://devfeed.tech/tags/search.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

A case study of Bayer's enterprise generative AI platform, myGenAssist, and its use of Qdrant for vector search. The article describes the platform's growth from an initial drug-discovery application to company-wide use, with retrieval designed to support large language models, handle sustained workloads, and reduce hallucinations.

### Source excerpt

Bayer is a global life sciences company operating at the intersection of two of the most consequential fields in human life: health and nutrition. Its pharmaceutical work supports drug discovery and patient care, while its crop science work supports food production at planetary scale. The company's guiding ambition, "Health for all, hunger for none," frames how it thinks about technology: AI is not a side project, but a lever applied across the entire organization, from improving the productivity of colleagues to accelerating yield prediction and drug discovery.

## Qdrant and Minima Deliver 2.92x More Agentic RAG Tasks per GPU-Hour

DevFeed: [Qdrant and Minima Deliver 2.92x More Agentic RAG Tasks per GPU-Hour](<https://devfeed.tech/articles/qdrant-and-minima-deliver-2-92x-more-agentic-rag-tasks-per-gpu-hour-46617.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/case-study-minima/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-08-13T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [NVIDIA Blackwell](<https://devfeed.tech/topics/nvidia-blackwell.md>), [payload](<https://devfeed.tech/topics/payload.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [blackwell-gpu](<https://devfeed.tech/tags/blackwell-gpu.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [inference](<https://devfeed.tech/tags/inference.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [latency](<https://devfeed.tech/tags/latency.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [payload](<https://devfeed.tech/tags/payload.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [rag](<https://devfeed.tech/tags/rag.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [saas](<https://devfeed.tech/tags/saas.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

This case study describes how Minima built a bounded retrieval agent with Qdrant hybrid search, payload filtering, late-interaction reranking, and Qwen3.6-27B generation. Across evaluated tasks and agent episodes, the stack improved throughput, latency, and grounded task success compared with dense retrieval using BF16 inference.

### Source excerpt

Reducing Retrieval and Calls When a retrieval-augmented generation (RAG) agent runs, it often has to plan a search, check the evidence it gets back, and try again when that evidence falls short. Those inefficiencies compound. Every extra retrieval and every extra model call adds latency, context, and inference cost.

## How to Clean Up a Qdrant Collection

DevFeed: [How to Clean Up a Qdrant Collection](<https://devfeed.tech/articles/how-to-clean-up-a-qdrant-collection-46640.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/clean-vector-database-collection/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-08-10T00:00:00Z

Content type: tutorial

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [data](<https://devfeed.tech/topics/data.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [data](<https://devfeed.tech/tags/data.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [points](<https://devfeed.tech/tags/points.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [query](<https://devfeed.tech/tags/query.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [results](<https://devfeed.tech/tags/results.md>), [retry](<https://devfeed.tech/tags/retry.md>), [saas](<https://devfeed.tech/tags/saas.md>), [search](<https://devfeed.tech/tags/search.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

A tutorial on cleaning Qdrant vector collections whose repeated ingestion creates duplicate or stale points that displace useful search results. It explains how to inspect collection contents, deduplicate records, and use stable point IDs to make retries idempotent.

### Source excerpt

Every crawl, retried job, and embedding pipeline change writes points into a vector collection. The stored data keeps moving even when the query code never changes, and the top results move with it. At first, little looks wrong. Search returns results, and latency stays normal. In our baseline run, the context-relevance score sat at 0.92 out of 1.00 while four answers in ten came back wrong, because duplicate chunks and one outdated record were filling the five results the agent could read.

## Pre-Filtering vs Post-Filtering (and Why Qdrant Does Neither)

DevFeed: [Pre-Filtering vs Post-Filtering (and Why Qdrant Does Neither)](<https://devfeed.tech/articles/pre-filtering-vs-post-filtering-and-why-qdrant-does-neither-46691.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/pre-filtering-vs-post-filtering/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-08-07T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [Graphs](<https://devfeed.tech/topics/graphs.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [bert](<https://devfeed.tech/tags/bert.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [filter](<https://devfeed.tech/tags/filter.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [saas](<https://devfeed.tech/tags/saas.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

This article compares pre-filtering and post-filtering for vector search and explains Qdrant's in-place filtering approach. It describes how metadata filters can reduce recall and how Qdrant uses filtered HNSW traversal and graph repairs to preserve search quality.

### Source excerpt

Adding a metadata filter to vector search can make good results disappear without making the query look broken. It still runs fast, returns something, and keeps the dashboards quiet, while some of the true nearest matches drop out. In the benchmark behind this post, a broad-value filter lowers recall to 90.8% and an AND filter over two broad values lowers it to 39.7%, while every other filter shape stays above 97%.

## Qdrant 1.19 - TurboQuant Datatype & Memory Tiers

DevFeed: [Qdrant 1.19 - TurboQuant Datatype & Memory Tiers](<https://devfeed.tech/articles/qdrant-1-19-turboquant-datatype-memory-tiers-46702.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/qdrant-1.19.x/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-08-05T01:00:00Z

Content type: release

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [Compression](<https://devfeed.tech/topics/compression.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [cloud-infrastructure](<https://devfeed.tech/topics/cloud-infrastructure.md>), [Collections](<https://devfeed.tech/topics/collections.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [bm25](<https://devfeed.tech/tags/bm25.md>), [compression](<https://devfeed.tech/tags/compression.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [precision](<https://devfeed.tech/tags/precision.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [quantization](<https://devfeed.tech/tags/quantization.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [saas](<https://devfeed.tech/tags/saas.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [storage](<https://devfeed.tech/tags/storage.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

Qdrant 1.19 introduces the Turbo4 datatype, which stores vectors as 4-bit TurboQuant representations without retaining full-precision copies, reducing storage by up to nine times. The release also adds unified memory tiers, tenant-specific IDF statistics, filtering improvements, and Web UI enhancements.

### Source excerpt

Qdrant 1.19.0 is out! Let's look at the main features for this version: TurboQuant Datatype: A new storage format that compresses vectors to four bits without keeping their original full-precision representation, reducing storage by up to nine times compared to TurboQuant quantization. Memory Tiers: A single memory parameter unifies per-component memory tier placement, with three tiers: pinned, cached, and cold. Per-Tenant IDF Statistics: Narrow the IDF corpus to a specific tenant so term rarity reflects that tenant's vocabulary rather than the whole dataset, improving BM25 scoring in multi-tenant deployments.

## Lessons From Building E-Commerce Search on Qdrant

DevFeed: [Lessons From Building E-Commerce Search on Qdrant](<https://devfeed.tech/articles/lessons-from-building-e-commerce-search-on-qdrant-46651.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/ecommerce-search-qdrant/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-07-24T00:00:00Z

Content type: article

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [API](<https://devfeed.tech/topics/api.md>), [GitHub](<https://devfeed.tech/topics/github.md>), [personalization](<https://devfeed.tech/topics/personalization.md>), [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [bm25](<https://devfeed.tech/tags/bm25.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [e-commerce](<https://devfeed.tech/tags/e-commerce.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [github](<https://devfeed.tech/tags/github.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [latency](<https://devfeed.tech/tags/latency.md>), [matching](<https://devfeed.tech/tags/matching.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [personalization](<https://devfeed.tech/tags/personalization.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [recommendations](<https://devfeed.tech/tags/recommendations.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [saas](<https://devfeed.tech/tags/saas.md>), [search](<https://devfeed.tech/tags/search.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

This article explains lessons from building an e-commerce search storefront on Qdrant. It describes combining dense-vector and BM25 retrieval with reciprocal rank fusion, applying filters during search, and indexing payload fields for reliable production queries.

### Source excerpt

Relevance, filtering, personalization, merchandising, and recommendations usually arrive as five separate services, and the final ranking gets stitched across all of them. Each service ranks by its own rules, and none of them owns the order a shopper ends up seeing. We built Qdrant Shopping, a storefront over 5.8 million real Amazon fashion products, to find out how many of those pieces collapse into one. Every text search is a single request to Qdrant's Query API that returns a ranked shelf in about 40 milliseconds, and the code is on GitHub. The decisions below apply to almost any product catalog, and we got several of them wrong before we got them right.

[Next page](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md?cursor=WyIyMDI2LTA3LTI0VDAwOjAwOjAwKzAwOjAwIiwgIjExMjAwYjc3LWNhMzYtNGZmYy1hNzg5LTdlY2IyZjJiZGUxYiJd>)