Guides
Vendor-neutral, engineer-written guides to the concepts behind multimodal AI — perception, retrieval, embeddings, and the infrastructure agents use to see, hear, and search unstructured data. Learn the idea first; then see how Mixpeek applies it.
86 guides across 15 topics
How Do I Build a Deep Research Agent Over My Own Data?
Consumer deep research browses the public web — but your evidence lives in PDFs, call recordings, decks, and videos behind your own APIs. The architecture of private-corpus research agents: question decomposition, multimodal retrieval loops, stopping criteria, provenance, and verification, with the retriever stages that implement each step.
What Concepts Exist in My Data That Nobody Has Labeled Yet?
Some queries cannot be answered by keyword search, vector search, or RAG — because the user does not know the ontology ahead of time. How discovered taxonomies answer questions like 'how does this brand visually represent trust?' and 'what stereotypes recur across our advertising?' with six worked examples.
How to Store TwelveLabs Marengo Embeddings in Your Own Vector Store
TwelveLabs' async embed API stores Marengo embeddings for only seven days. This guide shows how to persist Marengo video, text, audio, and image embeddings durably in Mixpeek MVS — create a matching namespace, upsert vectors with temporal payloads, and search them — plus when this pattern beats searching inside TwelveLabs itself.
Video Highlight Detection: How AI Finds the Best Moments
How AI turns hours of footage into highlights: shot and scene decomposition, per-modality moment scoring (visual, audio, transcript), interval merging, and per-video ranking — with the real architectures behind sports highlight generators and meeting recap tools.
How Much Does a Vector Database Cost? A 2026 Pricing Comparison
A vendor-neutral breakdown of vector database pricing in 2026: what drives cost (bytes, RAM vs object storage, replication), how Pinecone, Weaviate, Qdrant, Zilliz, turbopuffer, and Mixpeek MVS price, a worked cost-estimation formula, and which architecture is cheapest for each workload shape.
How to Switch Embedding Models Without Re-Embedding Everything
A vendor-neutral guide to embedding model migration: why vector spaces are incompatible, the three real strategies (full re-embedding behind a dual index, learned vector-space translation with Procrustes or adapters, query-side bridging), a decision table, and how to validate recall parity before cutting over.
Reverse Video Search: How It Works and How to Build One
A vendor-neutral guide to reverse video search: starting from a clip or frame to find matching or similar videos, with timestamps. Covers the two matching paradigms (perceptual fingerprinting vs semantic embeddings), the four-stage pipeline (sample, represent, index, localize), how to build one, and how to evaluate it.
Semantic Caching: How Agents Skip Work They Have Already Done
A vendor-neutral guide to caching by meaning instead of by exact string. Covers why hash-based caches almost never hit on agent traffic, how a semantic cache is really a tiny vector index of query embeddings, the similarity-threshold precision/recall tradeoff that makes or breaks it, the failure modes (false hits, staleness, negation and entity flips), invalidation strategies, and how to cache retrieval results and tool calls, not just answers, for agents that fan out many near-duplicate queries.
Efficient Attention: How Models Read Hour-Long Video and Book-Length Documents
A vendor-neutral guide to the attention tricks that make million-token multimodal context possible. Covers why dense attention hits a quadratic wall, sliding-window and block-sparse patterns (Longformer, BigBird), learned/dynamic sparsity like MiniMax Sparse Attention, linear and state-space attention (the QK^T V reordering, Mamba-style recurrence), the hybrid full-plus-sparse layer stack, and why efficient attention and retrieval are complements, not rivals, for agents that have to watch whole videos or read whole corpora.
Optical Context Compression: Reading Documents as Images, Not Text
A vendor-neutral guide to the 2026 idea that a picture of text can be cheaper than the text itself. Covers optical 2D mapping, the DeepEncoder architecture (SAM window attention, a 16x bridge compressor, CLIP global attention), the compression-vs-precision curve (97% at under 10x, ~60% at 20x), the OmniDocBench results that made people notice, and why vision-token compression matters for agents that have to read long documents.
Multi-Object Tracking: How Agents Follow Objects Across Video Frames
A vendor-neutral guide to tracking-by-detection — motion prediction with a Kalman filter, data association via IoU and the Hungarian algorithm, ByteTrack's low-score recovery, appearance re-identification, and the ID-switch problem — the pipeline that turns per-frame detections into stable per-object tracks an agent can reason over across time.
Monocular Depth Estimation: How Models Infer 3D From a Single Image
A vendor-neutral guide to inferring depth from one 2D image — why the problem is ill-posed, the pictorial cues models learn, relative vs metric depth and scale ambiguity, how self-supervision trains depth without ground truth, and why a depth channel lets an agent reason about scene geometry it otherwise can't see.
From concept to production
These guides explain how multimodal perception and retrieval actually work. Mixpeek is the platform that runs them — point it at your storage and get back relevant, timestamped results.