EdTech Tracker

← Coding lens

text embedding

technique judged 99% likely a named technique or architecture

First seen
2022-06-23
Independent sources
11
Articles
50
Last 4 weeks vs prior
0 vs 6

See how it has spread across media tiers

Mentions over time

Articles per week (by publish date) using the term, in any spelling.
0362022-W252026-W072026-W41
Table view
WeekArticlesSources
2022-W2511
2023-W1411
2023-W4311
2024-W0111
2024-W0211
2024-W0511
2024-W1111
2024-W2211
2024-W2411
2024-W2611
2024-W3311
2024-W4111
2024-W4511
2025-W0311
2025-W2411
2025-W2711
2025-W4911
2026-W0711
2026-W0931
2026-W1011
2026-W1161
2026-W1211
2026-W1311
2026-W1811
2026-W1911
2026-W2431
2026-W2522
2026-W3322
2026-W3411
2026-W3511
2026-W3611
2026-W3711
2026-W3811
2026-W4054
2026-W4111

In their words

get ( " version " , " 1.0 " ), } Phase 2: Embedding & Vector Storage Embedding Model Selection Model Dimensions Speed Quality Cost Best For text-embedding-3-small 1536 Fast Good $0.02/M General purpose text-embedding-3-large 3072 Medium Best $0.13/M High accuracy needs bge-base-en-v1.5 768 Fast Good Free (local) Privacy/offline bge-large-en-v1.5 1024 Medium Better Free (local) Quality + privacy e5

It names autonomous agent planning, production tool integrations, durable persistence, vector embeddings and Milvus RAG, authentication, rate limiting, distributed tracing, and automatic compensation execution.

Here's what my logs showed, roughly, on the same internal docs corpus: Old model (ada-002) New model (text-embedding-3-small) Top-1 score, questions with a real answer ~0.84 median ~0.55 median Score between two random unrelated chunks ~0.72 median ~0.18 median Look at the right column first.

If your scraper loses the <h1> vs <h3> distinction, your vector embeddings will fail to capture the importance of headers, leading to poor retrieval performance.

Keeping them in one database makes it one transaction commit: CREATE TABLE agent_sessions ( session_id VARCHAR2(64) PRIMARY KEY, messages JSON NOT NULL, -- native JSON, not a CLOB you parse version NUMBER DEFAULT 1 NOT NULL, -- optimistic concurrency updated_at TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL ); CREATE TABLE agent_memory ( memory_id VARCHAR2(64) PRIMARY KEY, session_id VARCH

You send it conversations, and it extracts, transforms, and stores the parts worth keeping as memories, using vector embeddings and LLM-powered processing.

The prompt hook reuses the text embedding already computed for learning recall and compares it with the embeddings of the project’s approved skills.

Long text properties and embedding vectors bloat the request and bury the fields that matter.