🔎 A provocative paper: "agentic search needs no embeddings or vector DB—just grep the raw corpus directly." Title: Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction URL: ❓ What is Direct Corpus Interaction (DCI)? 💡 A retrieval paradigm where the agent explores the raw corpus directly via grep, find, and shell commands—no embedding model, vector index, or retrieval API. It needs no offline indexing and adapts naturally to evolving local corpora. ❓ Why aren't conventional retrievers enough? 💡 Sparse or dense, they compress the corpus through a fixed similarity interface into top-k before reasoning begins. That makes exact lexical matching, combining weak clues, and checking local context hard—and evidence filtered out early can't be recovered no matter how strong the downstream reasoning. That's fatal for multi-step agent search. ❓ Can it really win without a retriever? 💡 Yes. On BrowseComp-Plus, swapping the retriever for DCI on the same Sonnet 4.6 lifts accuracy 69.0 → 80.0% (+11.0) while cutting cost 29.4%. Multi-hop QA averages 83.0 (+30.7 over the strongest baseline); IR ranking hits 68.5 NDCG@10 (+21.5). Even the lightweight GPT-5.4 nano version beats many baselines. ❓ What's actually driving it? 💡 The authors call it "retrieval interface resolution." Trajectory analysis shows the edge comes less from surfacing more gold documents and more from high-resolution local search and verification after reaching them. #AIAgents# #RAG#

I build small, practical AI systems. On-device chatbots without LLM APIs. Embeddings, BM25, small policy networks, explainable responses. 100+ free browser-side tools for AI, math, dev, security, SEO, and weird utility work. GitHub:

Stop restarting llama-server. llama-swap gives you one endpoint for every local model. Switch coding, chat, vision, embeddings, and backends without breaking Cursor, Open WebUI, or your VRAM.

QVAC Workbench 0.7 is here. We’re making local-first intelligence faster and more intuitive. This update removes friction between your hardware and your workflow, making sovereignty feel much more seamless. Desktop - GPU Embeddings: Faster document processing by leveraging local GPU power - Smart Search: Higher quality results with transparent source links. - Efficiency: New keyboard shortcuts and bulk thread deletion. Mobile - iOS Persistence: Improved background handling so the app stays active when minimized. - Edge Compute: GPU-accelerated embeddings brought to mobile. The foundation of stable intelligence is moving forward. Run it on your own hardware and own your future. Download 0.7 today.

# Weaviate Features and Practical Usage 🚀 Ever wished you could delete all the embedding-API plumbing from your app code? Weaviate's model provider integrations let you wire up vectorization, generation, and reranking just by writing it into your collection config. 📌 Title and Feature URL Title: Model provider integrations URL: 📝 Overview Weaviate integrates with 20+ model providers including OpenAI, Cohere, Google, AWS, Azure OpenAI, Mistral, Anthropic, Hugging Face, and Ollama. You can plug them into automatic embedding at import, automatic embedding of query text, generation for RAG, and reranking of search results. The big win is that your application no longer needs code to call an embedding API and pass vectors in. 🔧 How It Works Integrations fall into three roles: - Vectorizer (embeddings): text or multimodal vectorization. - Generative (LLM): text generation for RAG pipelines. - Reranker: result refinement (offered by Cohere, Jina AI, NVIDIA, Voyage AI). There are also two delivery forms. API-based providers (OpenAI, Google, Cohere, AWS Bedrock, etc.) call external services, while locally hosted options (Ollama, Hugging Face Transformers, Model2vec) run on your own infrastructure. API-based modules are enabled by default in v1.33+. 🛠 Practical Usage - Specify an embedding provider with Configure.Vectors at collection creation, and Weaviate vectorizes automatically at both import and query time. - Configure generation with Configure.Generative to run RAG over your search results. - Configure a reranker with Configure.Reranker. - Automatic vectorization targets text / text[] properties. Weaviate sorts property names alphabetically, concatenates them, optionally prepends the collection name, and sends the string to the model (you can also exclude properties per-field). 🎯 Use Cases - Internal document search: auto-vectorize body text at import, and auto-vectorize the query with the same model so they stay consistent. - Model swapping: change vendor or model by editing collection config only. - Closed-network requirements: use a locally hosted option like Ollama to keep data in-house through embedding generation. - RAG chat: combine retrieval and generation within the same configuration, minimizing external orchestration. ⚠️ Caveats - API-based providers require API keys and incur usage charges. - Rate limits follow each provider's policy; watch out during bulk imports. - For versions before v1.27, the concatenated string is lowercased before being sent to the model. - For versions before v1.33, set ENABLE_API_BASED_MODULES to use API-based modules. #Weaviate# #Embeddings#

🎨 Every studio has a "final_final_v7.png." It's often faster to remake old work than to find it, and AI helps with that from an unexpected angle. In creative work, assets pile up faster than anyone can organize them. The catch is that keyword search fails: search "blue environmental concept" and you get nothing if the file is named ENV_ALTSTYLING_DARK_V4. The words and the filenames simply don't share a vocabulary. So flip the approach. Convert images and footage into vector embeddings that represent meaning as numbers. Now "things that mean something similar, however differently phrased, sit close together in vector space," so you can search in natural language. Built on Weaviate, hybrid search combines vector proximity with metadata filters (project, date, type) to land on the right asset. Search tens of thousands of concept images for "a cold, forested biome that feels visually distinct," pull B-roll by shot characteristics, dig up an old drum texture, all without knowing the naming convention. Here, AI isn't the star that generates new content; it's the infrastructure layer that makes existing work accessible, returning to creation the hours lost to organizing and searching. Building Foundry: AI isn't replacing creativity, it's removing friction makes the case for that quiet but essential value. 🔗 #VectorSearch# #CreativeAI#

Mathematicians isolate graphs with extreme traits under simple names that stick for generations. The Balaban 10-cage realizes the (3,10)-cage with 70 vertices. Errera and Kittell graphs relate to the four color theorem. The Frucht graph is the smallest 3-regular with trivial automorphism group. Circuit designers draw on the Goldner-Harary and Wagner graphs for planar embeddings in printed circuit board layouts.

# Weaviate Features and Practical Usage 🚀 Give a single object several meaning spaces at once: one for the title, one for the body, one for the image. Named vectors are the core design pattern for multimodal and purpose-specific search within a single collection. 📌 Title and Feature URL Title: Named vectors (collection definition) URL: 📝 Overview Named vectors let a single object hold multiple vector embeddings simultaneously. Each vector can have its own source properties, vectorizer, index, and compression algorithm, so it behaves as an independent vector space. This lets you switch which vector you search against depending on the use case. 🔧 How It Works - Each named vector can use its own vectorizer (e.g. text2vec-openai, text2vec-cohere). - source_properties controls which object properties feed a given vector (e.g. only title, or only body). - Each named vector has its own index type (hnsw / flat / dynamic) and config, so each space can be optimized independently. - As the docs put it: "Each vector space can set its own index, its own compression algorithm, and its own vectorizer." - The name "default" is reserved for single-vector collections created without explicit vector configuration. 🛠 Practical Usage In the Python client, pass an array to vector_config to define multiple vectors. - Definition: vector_config=[Configure.Vectors.text2vec_openai(name="title", source_properties=["title"]), Configure.Vectors.text2vec_openai(name="body", source_properties=["body"])] - At query time, choose the vector with target_vector. Example: collection.query.near_text(query="AI applications", target_vector="body"). - When supplying your own vectors during batch import, pass a dict keyed by vector name: batch.add_object(properties=row, vector={"title": title_vec, "body": body_vec}). - New named vectors can be added after collection creation. 🎯 Use Cases - Give articles a title vector and a body vector to power "related articles by headline similarity" and "search by body meaning" separately. - In e-commerce, keep a product-image vector and a description vector together for image similarity and text semantic search on the same object. - For multilingual content, maintain language-specific vectors to improve per-language retrieval. - Embed document sections with specialized models for domain-specific search. ⚠️ Caveats - The vectorizer, index type, and source property definitions cannot be changed after collection creation (adding new vectors is allowed). - You cannot combine named vectors (vector_config) with top-level vectorizer / vectorIndexType in the same collection. - More vectors mean more embedding cost and more storage/memory; define only what you actually need. - Queries must specify target_vector; forgetting it is a common mistake. #Weaviate# #Embeddings#

PyTorch-native NeMo AutoModel handles transformer pretraining in @nvidia's end-to-end workflow for building a transaction foundation model. The workflow combines GPU-accelerated data processing and tokenization, decoder-only model pretraining, embedding extraction, and XGBoost fraud classification. On the synthetic @IBM TabFormer dataset, combining raw features with learned embeddings increased Average Precision by 41.76% over the raw-feature baseline. 🔗 Read the full post:

Build and train an LLM "from scratch" yourself and you truly understand what's happening inside 🛠️ A complete educational implementation that runs on a single GPU. Title: FareedKhan-dev/train-llm-from-scratch URL: 🛠️ Overview An educational repository that implements a Transformer from scratch in PyTorch, based on "Attention is All You Need." It promises you can train your own million- to billion-parameter LLM on a single GPU. ❓ Challenges Solved LLMs are ubiquitous, but hands-on chances to train one from scratch and understand its internals are rare. ・Just using off-the-shelf frameworks leaves the Transformer's mechanics opaque ・Learners needed an end-to-end resource spanning pretraining through post-training alignment 💡 Content & Structure It covers the entire LLM lifecycle. ・Data acquisition and preprocessing (from The Pile) ・Core Transformer architecture (embeddings, attention, feed-forward networks) ・Model training (with DDP for distributed processing) ・Post-training alignment: SFT, reward modeling, PPO, DPO, GRPO ・Text generation and inference Code is organized into src/models, scripts, data_loader, configs, and a Streamlit ui. The stack is PyTorch, tiktoken, HDF5, and NumPy. 🌍 Use Cases / Audience For developers and researchers who want hands-on understanding of LLM training — from those with limited GPUs (starting at 13M parameters) to those targeting multi-billion-parameter models on enterprise hardware. #LLM# #MachineLearning#