{"schema_version":"onlylabs.public_signal.v1","title":"Databricks (DBRX) Writing: Sizing Lakebase Search: lessons from a real app and 4 million passages","description":"Databricks (DBRX) writing signal with public source context, captured evidence pages, related signals, and category-scoped analysis context.","url":"https://onlylabs.fyi/signals/1990828f-f27d-4c8f-ab07-74c78bec7688","json_url":"https://onlylabs.fyi/signals/1990828f-f27d-4c8f-ab07-74c78bec7688/signal.json","generated_at":"2026-10-25T10:37:38.851Z","evidence_latest_fetched_at":"2026-10-14T12:02:37.731959+00:00","signal_first_seen_at":"2026-10-14T12:00:52.319383+00:00","org":{"slug":"databricks","name":"Databricks (DBRX)","category":"neocloud","category_label":"Neocloud","dossier_url":"https://onlylabs.fyi/labs/databricks","dossier_json_url":"https://onlylabs.fyi/labs/databricks/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/1990828f-f27d-4c8f-ab07-74c78bec7688","signal_json":"https://onlylabs.fyi/signals/1990828f-f27d-4c8f-ab07-74c78bec7688/signal.json","source":"https://www.databricks.com/blog/sizing-lakebase-search-lessons-real-app-and-4-million-passages","lab_dossier":"https://onlylabs.fyi/labs/databricks","lab_dossier_json":"https://onlylabs.fyi/labs/databricks/dossier.json","analysis":"https://onlylabs.fyi/analysis/databricks","analysis_json":"https://onlylabs.fyi/analysis/databricks/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/databricks/evidence.json","category":"https://onlylabs.fyi/neoclouds","category_json":"https://onlylabs.fyi/neoclouds.json","category_feed":"https://onlylabs.fyi/neoclouds/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json?category=neocloud","topic":"https://onlylabs.fyi/topics/talking","topic_signals_json":"https://onlylabs.fyi/topics/talking/signals.json?category=neocloud","topic_feed":"https://onlylabs.fyi/topics/talking/feed.xml?category=neocloud","data_business":null},"answer_pack":{"answer":"Databricks (DBRX) published Sizing Lakebase Search: lessons from a real app and 4 million passages. This talking signal gives public context for research themes, product direction, policy, or launch framing. High-signal details: Substantive technical blog post from Databricks on search scaling. · Sizing Lakebase Search: lessons from a real app and 4 million passages | Databricks Blog Skip to main content Summary Lakebase Search runs vector and BM25 keyword search.... onlylabs links this event to 1 captured evidence page and 6 related writing signals.","signal_desk":"talking","source_context":{"source_url":"https://www.databricks.com/blog/sizing-lakebase-search-lessons-real-app-and-4-million-passages","source_host":"databricks.com","occurred_at":"2026-10-15T00:06:48+00:00","first_seen_at":"2026-10-14T12:00:52.319383+00:00","date_source":"rss.item_date","context":null},"context_markers":[{"label":"Lab","value":"Databricks (DBRX)","source":"signal"},{"label":"Signal desk","value":"talking","source":"signal"},{"label":"Source host","value":"databricks.com","source":"source"},{"label":"Model refs","value":"Alibaba-NLP/gte-large-en-v1.5","source":"model"},{"label":"Notability","value":"Substantive technical blog post from Databricks on search scaling.","source":"signal"},{"label":"Watch term","value":"Eval methodology","source":"evidence"},{"label":"Watch term","value":"Safety and alignment","source":"evidence"},{"label":"Watch term","value":"Agents and tool use","source":"evidence"}],"evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://www.databricks.com/blog/sizing-lakebase-search-lessons-real-app-and-4-million-passages"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-10-14T12:02:37.731959+00:00"},"data_business":{"matches":false,"lanes":[],"matched_terms":[],"score":null,"reason":null},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/1990828f-f27d-4c8f-ab07-74c78bec7688/signal.json","dossier_json":"https://onlylabs.fyi/labs/databricks/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/databricks/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/databricks/evidence.json","topic_signals_json":"https://onlylabs.fyi/topics/talking/signals.json?category=neocloud","topic_feed":"https://onlylabs.fyi/topics/talking/feed.xml?category=neocloud","category_signals_json":"https://onlylabs.fyi/signals.json?category=neocloud","data_radar_json":null,"opportunities_json":null},"analysis_playbook":{"objective":"Turn public writing and discussion into a readable map of research themes, product framing, policy posture, launch narratives, and market attention.","evidence_focus":["post title","source URL","captured page text","HN traction","linked model or paper references","publication date"],"extraction_questions":["Which themes are labs choosing to explain publicly?","Which posts are attracting outside discussion?","Which writing reframes a recent release, model, hiring wave, or policy stance?","Which posts mention data, evals, infrastructure, safety, or deployment workflows?"],"signal_questions":["What public theme, launch framing, or research direction does this writing signal expose?","Which themes are labs choosing to explain publicly?","Which posts are attracting outside discussion?","Do the 6 related writing signals show a repeated pattern?"],"output_fields":["org","theme","public_framing","traction","evidence_url"],"data_business_relevance":"Data-business lane extraction is scoped to frontier labs; for this category, keep conclusions tied to category-specific strategy, source evidence, and follow-up questions.","required_sources":[{"label":"signal_json","url":"https://onlylabs.fyi/signals/1990828f-f27d-4c8f-ab07-74c78bec7688/signal.json","required":true},{"label":"source","url":"https://www.databricks.com/blog/sizing-lakebase-search-lessons-real-app-and-4-million-passages","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/databricks/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/databricks/evidence.json","required":true},{"label":"topic_signals_json","url":"https://onlylabs.fyi/topics/talking/signals.json?category=neocloud","required":false},{"label":"data_radar_json","url":null,"required":false}],"expected_output":["one-paragraph source-grounded interpretation","category-specific implication","confidence and missing evidence","recommended next source to inspect"],"prompt_seed":"Using only the linked onlylabs JSON, captured source context, and cited evidence, analyze Databricks (DBRX)'s writing signal \"Sizing Lakebase Search: lessons from a real app and 4 million passages\" for neocloud strategy."},"semantic_triples":[{"subject":"Databricks (DBRX)","predicate":"published","object":"Sizing Lakebase Search: lessons from a real app and 4 million passages","text":"Databricks (DBRX) published Sizing Lakebase Search: lessons from a real app and 4 million passages."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"is classified as","object":"writing signal","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages is classified as writing signal."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"belongs to","object":"talking desk","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages belongs to talking desk."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"has evidence coverage","object":"1 captured evidence page","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages has evidence coverage 1 captured evidence page."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"has captured page count","object":"1","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages has captured page count 1."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"has readable page count","object":"1","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages has readable page count 1."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"has related signal count","object":"6","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages has related signal count 6."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"has analysis playbook objective","object":"Turn public writing and discussion into a readable map of research themes, product framing, policy posture, launch narratives, and market attention.","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages has analysis playbook objective Turn public writing and discussion into a readable map of research themes, product framing, policy posture, launch narratives, and market attention.."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"has source host","object":"databricks.com","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages has source host databricks.com."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"has lab","object":"Databricks (DBRX)","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages has lab Databricks (DBRX)."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"has signal desk","object":"talking","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages has signal desk talking."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"has source host","object":"databricks.com","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages has source host databricks.com."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"has model refs","object":"Alibaba-NLP/gte-large-en-v1.5","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages has model refs Alibaba-NLP/gte-large-en-v1.5."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"has notability","object":"Substantive technical blog post from Databricks on search scaling.","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages has notability Substantive technical blog post from Databricks on search scaling.."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"has watch term","object":"Eval methodology","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages has watch term Eval methodology."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"has watch term","object":"Safety and alignment","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages has watch term Safety and alignment."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"has watch term","object":"Agents and tool use","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages has watch term Agents and tool use."}]},"intelligence":{"signal_desk":"talking","answer":"Databricks (DBRX) published Sizing Lakebase Search: lessons from a real app and 4 million passages. This talking signal gives public context for research themes, product direction, policy, or launch framing. High-signal details: Substantive technical blog post from Databricks on search scaling. · Sizing Lakebase Search: lessons from a real app and 4 million passages | Databricks Blog Skip to main content Summary Lakebase Search runs vector and BM25 keyword search.... onlylabs links this event to 1 captured evidence page and 6 related writing signals.","semantic_triples":[{"subject":"Databricks (DBRX)","predicate":"published","object":"Sizing Lakebase Search: lessons from a real app and 4 million passages","text":"Databricks (DBRX) published Sizing Lakebase Search: lessons from a real app and 4 million passages."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"is classified as","object":"writing signal","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages is classified as writing signal."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"belongs to","object":"talking desk","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages belongs to talking desk."},{"subject":"Sizing Lakebase Search: lessons from a real app and 4 million passages","predicate":"has evidence coverage","object":"1 captured evidence page","text":"Sizing Lakebase Search: lessons from a real app and 4 million passages has evidence coverage 1 captured evidence page."}]},"signal":{"id":"1990828f-f27d-4c8f-ab07-74c78bec7688","url":"https://onlylabs.fyi/signals/1990828f-f27d-4c8f-ab07-74c78bec7688","json_url":"https://onlylabs.fyi/signals/1990828f-f27d-4c8f-ab07-74c78bec7688/signal.json","source_url":"https://www.databricks.com/blog/sizing-lakebase-search-lessons-real-app-and-4-million-passages","title":"Sizing Lakebase Search: lessons from a real app and 4 million passages","summary":"Databricks (DBRX) published a writing signal. onlylabs watches public writing for research themes, product direction, and model-launch context.","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"databricks","name":"Databricks (DBRX)","category":"neocloud"},"occurred_at":"2026-10-15T00:06:48+00:00","first_seen_at":"2026-10-14T12:00:52.319383+00:00","date_source":"rss.item_date","evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://www.databricks.com/blog/sizing-lakebase-search-lessons-real-app-and-4-million-passages"]},"facets":{},"traction":{"github_stars":null,"hn_points":null,"hn_comments":null,"hn_story_id":null,"hf_downloads":null,"hf_likes":null},"data_radar":null},"primary_evidence_page":{"is_primary":true,"source_match":true,"url":"https://www.databricks.com/blog/sizing-lakebase-search-lessons-real-app-and-4-million-passages","final_url":"https://www.databricks.com/blog/sizing-lakebase-search-lessons-real-app-and-4-million-passages","title":"Sizing Lakebase Search: lessons from a real app and 4 million passages","http_status":200,"content_type":"text/html; charset=utf-8","capture_method":"plain","fetched_at":"2026-10-14T12:02:37.731959+00:00","bytes":748792,"raw_path":"a2edc021467beebcacbd86556de6d66a9ba46042391fe401a5d2b64a4d2fba85.html","content_hash":"776ce4e1d1318268741219e76f7f5455585d701d464db78b9f05cf4697bcc5b2","excerpt_chars":1200,"truncated":true,"excerpt":"Sizing Lakebase Search: lessons from a real app and 4 million passages | Databricks Blog Skip to main content Summary Lakebase Search runs vector and BM25 keyword search as Postgres extensions inside the application database, so developers get hybrid search without maintaining a separate search system or a second transaction path. Benchmarks show that sizing the Local File Cache to roughly match the vector index keeps 95~98% of pages in memory, dropping warm vector latency to single-digit milliseconds, while reducing the candidate pool from 1,000 to 200 preserves 90.5% of top-10 results at one-third the page reads. Lakebase Postgres bills compute only while it runs, and a 14-minute load test serving 109k requests used just $0.02 of Lakebase Postgres compute, making a $31~40/month always-on 0.5 CU floor the recommended production baseline to avoid cold starts. Slide Hub is an internal Databricks app. Field engineers use it to find and reuse slides from about 700 internal presentations: event talks, product decks, and architecture decks. A search bar finds single slides by meaning and by keyword, and a Model Context Protocol (MCP) server gives AI agents the same search. The app..."},"evidence_pages":[],"related_signals":[{"id":"920667f2-0cd8-45db-be58-e49fa10cdd71","url":"https://onlylabs.fyi/signals/920667f2-0cd8-45db-be58-e49fa10cdd71","source_url":"https://www.databricks.com/blog/real-time-energy-trading-and-analytics-databricks","title":"Real-time energy trading and analytics on Databricks","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"databricks","name":"Databricks (DBRX)","category":"neocloud"},"occurred_at":"2026-10-23T19:00:00+00:00","first_seen_at":"2026-10-23T20:00:52.51603+00:00","date_source":"rss.item_date"},{"id":"9a22cf92-8815-45fb-8969-75e85b3c5841","url":"https://onlylabs.fyi/signals/9a22cf92-8815-45fb-8969-75e85b3c5841","source_url":"https://www.databricks.com/blog/built-agents-case-spark-declarative-pipelines","title":"Built for Agents: The Case for Spark Declarative Pipelines","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"databricks","name":"Databricks (DBRX)","category":"neocloud"},"occurred_at":"2026-10-23T19:00:00+00:00","first_seen_at":"2026-10-23T20:00:52.51603+00:00","date_source":"rss.item_date"},{"id":"14c0e9b8-7031-4f35-b95d-e1218f9de99b","url":"https://onlylabs.fyi/signals/14c0e9b8-7031-4f35-b95d-e1218f9de99b","source_url":"https://www.databricks.com/blog/databricks-vs-oracle-2026","title":"Databricks vs. Oracle in 2026","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"databricks","name":"Databricks (DBRX)","category":"neocloud"},"occurred_at":"2026-10-23T13:45:42+00:00","first_seen_at":"2026-10-23T16:00:52.856617+00:00","date_source":"rss.item_date"},{"id":"a131fabe-bf8d-46eb-989d-346f90800313","url":"https://onlylabs.fyi/signals/a131fabe-bf8d-46eb-989d-346f90800313","source_url":"https://www.databricks.com/blog/ai-cost-management","title":"The new economics of AI cost management","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"databricks","name":"Databricks (DBRX)","category":"neocloud"},"occurred_at":"2026-10-22T19:14:24+00:00","first_seen_at":"2026-10-22T20:00:52.861392+00:00","date_source":"rss.item_date"},{"id":"51b9ff87-7930-44c4-ad0a-d1e2990ac808","url":"https://onlylabs.fyi/signals/51b9ff87-7930-44c4-ad0a-d1e2990ac808","source_url":"https://www.databricks.com/blog/fraud-analyst-ai-coworker-detecting-telecom-fraud-real-time-one-platform","title":"The Fraud Analyst AI Coworker: Detecting Telecom Fraud in Real-Time on One Platform","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"databricks","name":"Databricks (DBRX)","category":"neocloud"},"occurred_at":"2026-10-22T18:30:00+00:00","first_seen_at":"2026-10-22T20:00:52.861392+00:00","date_source":"rss.item_date"},{"id":"c0f25b9a-599b-4a8c-ae03-ad62deda6b77","url":"https://onlylabs.fyi/signals/c0f25b9a-599b-4a8c-ae03-ad62deda6b77","source_url":"https://www.databricks.com/blog/ai-bill-coming","title":"The AI Bill is coming","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"databricks","name":"Databricks (DBRX)","category":"neocloud"},"occurred_at":"2026-10-22T18:12:49+00:00","first_seen_at":"2026-10-22T20:00:52.861392+00:00","date_source":"rss.item_date"}]}