#Embeddings

Articles about Embeddings — exploring patterns, best practices, and real-world implementations in production systems.

17 posts tagged with embeddings. ← All posts

#A2A (14)#ADK (8)#AG-UI (6)#AI (9)#AI Agents (311)#AI Architecture (21)#AI Cost (10)#AI Cost Optimization (8)#AI Engineering (227)#AI Evaluation (9)#AI Gateway (8)#AI Governance (29)#AI Red Teaming (9)#AI Research (9)#AI Safety (8)#AI Security (29)#AI in Production (12)#AML (3)#API Design (10)#API Security (8)#APIs (56)#AWS (17)#Accounting (9)#Agent Skills (3)#Agentic AI (24)#Agentic Commerce (12)#Agentic RAG (8)#Agents (4)#Amazon Bedrock (8)#Analytics (3)#Architecture (40)#Audit (3)#Authentication (11)#Authorization (3)#Automation (8)#Azure (11)#Azure AI Foundry (9)#Backend Engineering (310)#Benchmarks (3)#Best Practices (3)#BigQuery (6)#Business Finance (8)#Business Strategy (55)#C (8)#CI/CD (16)#Caching (11)#Capital Markets (14)#Card Payments (12)#Cards (13)#Career (25)#Checkpointing (4)#Claude Code (8)#Cloud (5)#Cloud Architecture (3)#Cloud Native (10)#Code Review (8)#Collaboration (5)#Communication (9)#Compliance (52)#Computer Networking (9)#Computer Science (32)#Computer Vision (5)#Concurrency (39)#Consulting (3)#Containers (10)#Context Engineering (10)#Conversational AI (8)#Cost Optimisation (5)#Credit (14)#Credit Risk (14)#CrewAI (8)#Crypto (12)#Cryptocurrency (12)#Cryptography (8)#Custody (9)#DSPy (8)#Data (13)#Data Engineering (12)#Data Structures (9)#Databases (38)#Deployment (4)#Design Patterns (10)#DevOps (24)#DevSecOps (21)#Developer Experience (5)#Developer Tools (5)#Distributed Systems (95)#Documentation (3)#Edge AI (8)#Embeddings (17)#Emotional Intelligence (8)#Energy (8)#Engineering (11)#Engineering Culture (3)#Engineering Practices (16)#Error Handling (4)#Evaluation (58)#Event-Driven Architecture (8)#FREE-AI (8)#FX (5)#Feedback (4)#FinOps (23)#FinTech (6)#Financial AI (14)#Financial Systems (129)#Fine-Tuning (11)#Fintech (131)#Flutter (8)#Foreign Exchange (5)#Forward Deployed Engineer (16)#Forward Deployed Engineering (8)#Fraud (10)#Function Tools (5)#Functional Programming (3)#Fundraising (8)#GCP (5)#Gemma (4)#Generative AI (3)#Git (8)#Go (220)#Go-to-Market (8)#Google ADK (36)#Governance (59)#Granite (6)#GraphQL (3)#Growth (3)#Guardrails (33)#HIPAA (3)#HTTP (3)#Harness Engineering (8)#Hiring (8)#Hugging Face (8)#Human-in-the-Loop (9)#IBM watsonx (8)#Identity (11)#Integration (3)#Intellectual Property (8)#Interfaces (3)#JavaScript (8)#KYC (11)#KYC and AML (12)#Kafka (10)#Kubernetes (17)#LLM (5)#LLM Inference (8)#LLM Infrastructure (8)#LLM-as-Judge (3)#LLMs (170)#LangChain (8)#LangGraph (11)#Leadership (26)#Ledger (12)#Legal (8)#Lending (14)#Linux (9)#LlamaIndex (8)#Load Balancing (3)#MCP (22)#MLOps (32)#Machine Learning (49)#Marketing (16)#Markets (4)#Memory (15)#Memory Management (5)#Metrics (6)#Microservices (3)#Microsoft Agent Framework (150)#Middleware (6)#Migration (9)#Mixture of Experts (5)#Monitoring (3)#Multi-Agent (10)#Multi-Agent AI (14)#Multi-Agent Systems (73)#Multimodal (3)#Multimodal AI (8)#NIM (5)#NVIDIA (8)#Networking (3)#OAuth (3)#OWASP (7)#Observability (49)#On-Device AI (8)#Open Source (7)#OpenTelemetry (5)#Operating Systems (9)#Operations (10)#Opinion (6)#Orchestration (10)#Organizational Design (8)#Payment Rails (16)#Payments (54)#People (8)#Performance (48)#Personalization (9)#Platform Engineering (9)#PreSales (8)#Privacy (5)#Privacy Engineering (3)#Process (4)#Product (29)#Product Management (8)#Production (11)#Programming (10)#Programming Languages (48)#Prompt Engineering (74)#Prompt Injection (14)#Protocol Buffers (3)#Protocols (9)#Providers (4)#Pydantic AI (8)#Python (142)#Quality (3)#RAG (59)#RBI (3)#REST (5)#Rails (16)#Reasoning Models (8)#Recommender Systems (8)#Reconciliation (3)#RegTech (8)#Regulation (9)#Reliability (52)#Resilience (4)#Responsible AI (5)#Retrieval (3)#Risk (13)#Rust (32)#SLSA (3)#SRE (22)#Sales (9)#Scalability (3)#Security (91)#Security Engineering (8)#Self-Evolving Agents (16)#Sessions (3)#Settlement (9)#Soft Skills (8)#Software (3)#Software Architecture (36)#Software Delivery (9)#Software Engineering (144)#Spanner (4)#Speech (8)#Startups (30)#Strands (8)#Streaming (31)#Structured Output (4)#Supply Chain Security (9)#Sustainability (8)#System Design (32)#Systems Programming (56)#Testing (53)#Threat Modeling (3)#Tool Use (22)#Tooling (5)#Tools (3)#Trading (8)#Treasury (6)#Type System (3)#Type Systems (11)#TypeScript (8)#Vector Databases (22)#Vector Search (11)#Venture Capital (8)#Version Control (8)#Voice AI (9)#Web Development (6)#Workflows (14)#eBPF (8)#gRPC (13)#smolagents (8)
Pratik Dhanave · ·6 min read

Deep Learning Recommenders

Modern large-scale recommenders — the ones running at the biggest consumer platforms — are built on neural networks. Deep learning didn't replace the core ideas (embeddings, two stages) so much as supercharge them: neural models learn richer embeddings, ingest far more features, and capture complex non-linear patterns that dot products can't. This post covers the two workhorses — two-tower retrieval and neural ranking — that power today's systems.

Modern large-scale recommenders are built on neural networks — not replacing the core ideas (embeddings, two stages) but supercharging them. This post covers the two workhorses: two-tower models for retrieval (the neural evolution of matrix factorization, built for fast ANN search) and rich neural ranking models that score the shortlist with cross-features, sequences, and multiple objectives.

#Recommender Systems#Deep Learning#Machine Learning#AI Engineering#Personalization#Embeddings
Pratik Dhanave · ·6 min read

Matrix Factorization and Embeddings

The technique that defined the modern era of recommendation is deceptively simple: represent every user and every item as a short list of numbers — a vector of latent factors — such that a user's affinity for an item is just the dot product of their vectors. Matrix factorization turned recommendation into learning good embeddings, and it's the conceptual bridge from classical collaborative filtering to today's deep-learning systems.

Represent every user and item as a short vector of latent factors, and a user's affinity for an item becomes just the dot product of their vectors. Matrix factorization turned recommendation into learning good embeddings — the technique that won the Netflix Prize and the conceptual bridge from classical collaborative filtering to today's deep-learning systems and vector search.

#Recommender Systems#Matrix Factorization#Embeddings#Machine Learning#Personalization#Vector Databases
Pratik Dhanave · ·6 min read

Retrieval and RAG

Answering questions over your own data is the most common LLM application, and LangChain gives you the whole pipeline as composable, swappable components — loaders, splitters, embeddings, vector stores, retrievers — behind standard interfaces. The retriever, in particular, is just another Runnable, so RAG becomes a chain like any other.

Answering questions over your own data is the most common LLM application, and LangChain gives you the whole pipeline as composable, swappable components — loaders, splitters, embeddings, vector stores, retrievers. The retriever is just another Runnable.

#LangChain#RAG#AI Engineering#Python#Software Engineering#LLMs#Embeddings#Vector Databases
Pratik Dhanave · ·5 min read

Indexes and Embeddings

An index is the data structure that makes your Nodes findable, and for RAG that almost always means embeddings in a vector store — but LlamaIndex offers more than one index type, and knowing which organizes your data for which query pattern is the point.

An index is the data structure that makes your Nodes findable, and for RAG that almost always means embeddings in a vector store — but LlamaIndex offers more than one index type, and knowing which fits which query pattern is the point.

#LlamaIndex#RAG#Embeddings#AI Engineering#Python#Vector Databases
Pratik Dhanave · ·6 min read

Distance Metrics and the Curse of Dimensionality

"Nearest" is meaningless until you define "distance," and the metric you choose — cosine, dot product, or Euclidean — must match how your embedding model was trained or your search is quietly wrong. And in high dimensions, distance itself behaves so strangely that the naive intuitions you'd bring from 2D geometry actively mislead you.

'Nearest' is meaningless until you define 'distance,' and the metric you choose must match how your embedding model was trained or your search is quietly wrong — and in high dimensions, distance itself behaves so strangely that 2D intuitions mislead you.

#Vector Search#RAG#AI Engineering#Data Structures#Embeddings#Vector Databases
Pratik Dhanave · ·12 min read

Embeddings and Reranking with watsonx

Building RAG's retrieval core with watsonx.ai from Python — turning a corpus into vectors with IBM's slate embedding models, scoring a query against them, and then sharpening the shortlist with a reranking model so the LLM gets the right passages, not just plausible ones.

Use watsonx.ai's slate embedding models and reranking from Python to build RAG's retrieval core: embed_documents vs embed_query, numpy cosine scoring, and a two-stage retrieve-then-rerank pipeline — plus the langchain-ibm WatsonxEmbeddings/WatsonxRerank path.

#IBM watsonx#RAG#Embeddings#Python#AI Engineering#Software Engineering
Pratik Dhanave · ·13 min read

Embeddings and Reranking with NeMo Retriever

Building RAG's retrieval core in Python — turning a corpus and a query into vectors with NeMo Retriever embedding NIMs, scoring by cosine similarity, then sharpening the shortlist with a cross-encoder reranker NIM.

Use NeMo Retriever from Python to build RAG's retrieval core: NVIDIAEmbeddings (embed_documents vs embed_query for the asymmetric passage/query distinction) with cosine scoring, and NVIDIARerank.compress_documents for a two-stage retrieve-then-rerank pipeline.

#NVIDIA#NeMo Retriever#RAG#Python#AI Engineering#Software Engineering#Embeddings
Pratik Dhanave · ·13 min read

Evaluating AI Systems

How to know whether an LLM system actually works — building an eval dataset, the four metric families (deterministic checks, text overlap, embedding similarity, LLM-as-judge) in Go, task-specific eval for RAG and classification, and wiring a scored regression gate into CI so you measure instead of vibe.

How to know whether an LLM system works when outputs are non-deterministic: build an eval dataset, score with deterministic checks, embedding similarity, and LLM-as-judge (with its biases), evaluate RAG and classification, and gate regressions in CI.

#AI Engineering#Evaluation#Go#LLMs#Backend Engineering#RAG#Embeddings
Pratik Dhanave · ·15 min read

Agent Memory and Planning

Give the hand-rolled Go agent from post 11 a memory it can carry between turns and a plan it can follow across many steps — a compacting conversation buffer, retrieval over the post-8 vector store, and a plan-then-execute-then-reflect loop, all built from scratch.

Give the agent memory and planning in Go: a compacting short-term conversation buffer, long-term memory as timestamped embeddings in the vector store, and planning — plan-then-execute, reflection and re-planning when observations contradict the plan, and task decomposition.

#AI Engineering#AI Agents#Go#Memory#Backend Engineering#Embeddings#Vector Databases
Pratik Dhanave · ·13 min read

Retrieval-Augmented Generation

Wire the embedding client, vector store, and chat client from the last five posts into one working RAG pipeline in Go — ingest and chunk documents, retrieve the top matches for a question, inject them as grounded context, and generate a cited answer, all from scratch.

Assemble embeddings and vector search into a working RAG pipeline in Go: chunk documents, embed and store them, retrieve the top-k for a query, augment the prompt with grounded context (and cite sources), then generate — a baseline end-to-end Answer() built from scratch.

#AI Engineering#RAG#Go#Vector Search#Backend Engineering#Embeddings#Vector Databases#Prompt Engineering
Pratik Dhanave · ·16 min read

Vector Search from Scratch

Build a working in-memory vector store and exact k-nearest-neighbor search in Go by hand — no vector database — then understand precisely what HNSW, FAISS, and pgvector optimize when brute force finally runs out of road.

Build an in-memory vector store and exact k-NN search in Go by hand: a VectorStore with Add and Search, top-k selection with container/heap, normalize-on-insert, an honest look at when brute force is right, and when ANN (HNSW, FAISS, pgvector) earns its keep.

#AI Engineering#Vector Search#Go#Embeddings#Backend Engineering#Vector Databases
Pratik Dhanave · ·13 min read

Embeddings

Turn text into a `[]float32` that places meaning in space — what an embedding is, cosine similarity implemented by hand in Go, calling an OpenAI-compatible /embeddings endpoint with net/http, and a worked pairwise-similarity example that scores related sentences higher.

Turn text into a []float32 that places meaning in space — what an embedding is, cosine similarity implemented by hand in Go, calling an OpenAI-compatible /embeddings endpoint with net/http, and a worked pairwise-similarity example that scores related sentences higher.

#AI Engineering#Embeddings#Go#Vector Search#Backend Engineering#Vector Databases
Pratik Dhanave · ·13 min read

Structs, Embedding, and Tags

How Go builds aggregate types from value semantics up — why a struct is a copy, when it stops being comparable, what embedding actually promotes (and what it deliberately doesn't), and how a backtick string in a field definition ends up steering `encoding/json`.

How Go builds aggregate types from value semantics up — why a struct is a copy, when it stops being comparable, what embedding actually promotes (and what it deliberately doesn't), and how a backtick string...

#Go#Structs#Data Structures#Backend Engineering#Embeddings
Pratik Dhanave · ·8 min read

Connecting Modalities: CLIP and Shared Embedding Spaces

The magic trick at the heart of modern multimodal AI is deceptively simple: train an image encoder and a text encoder together so that a picture of a dog and the words "a photo of a dog" land at the same spot in a shared space. Once images and text live in one common representational space, a cascade of capabilities follows — searching images by text, classifying without task-specific training, and grounding language generation in vision. CLIP is the model that made this idea famous, and understanding it is understanding how modalities actually get connected.

The magic trick at the heart of modern multimodal AI is deceptively simple: train an image encoder and a text encoder together so a picture of a dog and the words 'a photo of a dog' land at the same spot in a shared space. Once images and text live in one common space, a cascade of capabilities follows. CLIP is the model that made this famous.

#Multimodal AI#Machine Learning#Computer Vision#AI Engineering#Embeddings

All posts on this site are written by Pratik Dhanave, an Agentic AI Architect with 7+ years building production distributed systems, multi-agent AI platforms, and cloud-native infrastructure. About the author → Each article includes working code, architecture diagrams, and references to the specific frameworks and standards discussed. Browse all posts or explore related topics using the tag cloud above.